Package 'psycModel' reference manual

Title:	Integrated Toolkit for Psychological Analysis and Modeling in R
Description:	A beginner-friendly R package for modeling in psychology or related field. It allows fitting models, plotting, checking goodness of fit, and model assumption violations all in one place. It also produces beautiful and easy-to-read output.
Authors:	Jason Moy [aut, cre]
Maintainer:	Jason Moy <[email protected]>
License:	GPL (>= 3)
Version:	0.5.0.9000
Built:	2025-03-04 05:20:47 UTC
Source:	https://github.com/jasonmoy28/psycmodel

Acitelli

Description

Acitelli, L. K. (1997). Sampling couples to understand them: Mixing the theoretical with the practical. Journal of Social and Personal Relationships, 14, 243-261.

Usage

acitelli
acitelli

Format

A data frame with 296 rows and 16 variables:

CoupleID: each couple has 1 couple id
Yearsmar: each couple has 1 value for years married (centered; 11.214 subtracted)
Partnum: A variable to distinguish the two members (1 and 2)
Gender_A: -1 Female; 1 Male
SelfPos_A: Mean of positive self variables (uncentered)
OtherPos_A: Mean of positive partner variables (uncentered)(both variables the average of Cooperative, Mature, Friendly, Hard Working and Care about Others)
Satisfaction_A: Mean of four variables (theoretical range from 1 to 4)
Tension_A: Mean of two disagreement and tension (theoretical range from 1 to 4)
SimHob_A: Perception of having similar hobbies (1 = very true; 0 = somewhat true; -1 = not at all true)
Gender_P: -1 Female; 1 Male
SelfPos_P: Mean of positive self variables (uncentered)
OtherPos_P: Mean of positive partner variables (uncentered) (both variables the average of Cooperative, Mature, Friendly, Hard Working and Care about Others)
Satisfaction_P: Mean of four variables (theoretical range from 1 to 4)
Tension_P: Mean of two disagreement and tension (theoretical range from 1 to 4)
SimHob_P: Perception of having similar hobbies (1 = very true; 0 = somewhat true; -1 = not at all true)
Gender: String variable with Husband and Wife

Source

https://journals.sagepub.com/doi/10.1177/0265407597142006

ANOVA Plot

Description

Plot categorical variable with barplot. Continuous moderator are plotted at ± 1 SD from the mean.

Usage

anova_plot(model, predictor = NULL, graph_label_name = NULL, y_lim = NULL)
anova_plot(model, predictor = NULL, graph_label_name = NULL, y_lim = NULL)

Arguments

`model`	fitted model (usually `lm` or `aov` object). Variables must be converted to correct data type before fitting the model. Specifically, continuous variables must be converted to type `numeric` and categorical variables to type `factor`.
`predictor`	predictor variable. Must specified for non-interaction plot and must not specify for interaction plot.
`graph_label_name`	vector or function. Vector should be passed in the form of `c(response_var, predict_var1, predict_var2, ...)`. Function should be passed as a switch function that return the label based on the name passed (e.g., a switch function)
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`

Value

a ggplot object

Examples

# Main effect plot with 1 categorical variable
fit_1 = lavaan::HolzingerSwineford1939 %>% 
  dplyr::mutate(school = as.factor(school)) %>% 
  lm(data = ., grade ~ school)
anova_plot(fit_1,predictor = school)

# Interaction effect plot with 2 categorical variables 
fit_2 = lavaan::HolzingerSwineford1939 %>% 
  dplyr::mutate(dplyr::across(c(school,sex),as.factor)) %>% 
  lm(data = ., grade ~ school*sex)
anova_plot(fit_2)

# Interaction effect plot with 1 categorical variable and 1 continuous variable
fit_3 = lavaan::HolzingerSwineford1939 %>% 
  dplyr::mutate(school = as.factor(school)) %>% 
  dplyr::mutate(ageyr = as.numeric(ageyr)) %>% 
  lm(data = ., grade ~ ageyr*school)
anova_plot(fit_3)


# Main effect plot with 1 categorical variable
fit_1 = lavaan::HolzingerSwineford1939 %>% 
  dplyr::mutate(school = as.factor(school)) %>% 
  lm(data = ., grade ~ school)
anova_plot(fit_1,predictor = school)

# Interaction effect plot with 2 categorical variables 
fit_2 = lavaan::HolzingerSwineford1939 %>% 
  dplyr::mutate(dplyr::across(c(school,sex),as.factor)) %>% 
  lm(data = ., grade ~ school*sex)
anova_plot(fit_2)

# Interaction effect plot with 1 categorical variable and 1 continuous variable
fit_3 = lavaan::HolzingerSwineford1939 %>% 
  dplyr::mutate(school = as.factor(school)) %>% 
  dplyr::mutate(ageyr = as.numeric(ageyr)) %>% 
  lm(data = ., grade ~ ageyr*school)
anova_plot(fit_3)

APIM Actor-Partner Interdependence Model (SEM)

Description

Usage

APIM_sem(
  data,
  mod_type,
  predictor_a,
  predictor_p,
  outcome_a,
  outcome_p,
  med_a = NULL,
  med_p = NULL,
  mod_a = NULL,
  mod_p = NULL,
  bootstrap = NULL,
  standardized = FALSE,
  return_result = FALSE,
  quite = FALSE
)
APIM_sem(
  data,
  mod_type,
  predictor_a,
  predictor_p,
  outcome_a,
  outcome_p,
  med_a = NULL,
  med_p = NULL,
  mod_a = NULL,
  mod_p = NULL,
  bootstrap = NULL,
  standardized = FALSE,
  return_result = FALSE,
  quite = FALSE
)

Arguments

`data`	data frame object
`mod_type`	options are "simple" (main effect), "med" (mediation), and "mod" (moderation)
`predictor_a`	predictor variable name for actor
`predictor_p`	predictor variable name for partner
`outcome_a`	dependent variable name for actor
`outcome_p`	dependent variable name for partner
`med_a`	mediation variable name for actor
`med_p`	mediation variable name for partner
`mod_a`	moderation variable name for actor
`mod_p`	moderation variable name for partner
`bootstrap`	number of bootstrapping (e.g., 5000). Default is not using bootstrap
`standardized`	standardized coefficient
`return_result`	return `lavaan::parameterestimates()`. Default is `FALSE`
`quite`	suppress printing output. Default is `FALSE`

Details

Actor-partner interdependence model using SEM approach (with lavaan). Indistinguishable dyads only. Results should be the same as those from Kenny (2015a, 2015b).

Value

data.frame from lavaan::parameterestimates()

References

Kenny, D. A. (2015, October). An interactive tool for the estimation and testing mediation in the Actor-Partner Interdependence Model using structural equation modeling. Computer software. Available from https://davidakenny.shinyapps.io/APIMeM/. Kenny, D. A. (2015, October). An interactive tool for the estimation and testing moderation in the Actor-Partner Interdependence Model using structural equation modeling. Computer software. Available from https://davidakenny.shinyapps.io/APIMoM/. Stas, L, Kenny, D. A., Mayer, A., & Loeys, T. (2018). Giving Dyadic Data Analysis Away: A User-Friendly App for Actor-Partner Interdependence Models. Personal Relationships, 25 (1), 103-119. https://doi.org/10.1111/pere.12230.

Examples

APIM_sem(data = acitelli,
        predictor_a = 'Tension_A',
        predictor_p = 'Tension_P',
        outcome_a = 'Satisfaction_A',
        outcome_p = 'Satisfaction_P',
        mod_type = 'simple')
        
APIM_sem(data = acitelli,
        predictor_a = 'Tension_A',
        predictor_p = 'Tension_P',
        outcome_a = 'Satisfaction_A',
        outcome_p = 'Satisfaction_P',
        mod_type = 'simple')

APIM Actor-Partner Interdependence Model Table with Multiple Moderators

Description

Actor-partner interdependence model that test multiple moderators simultaneously.

Usage

APIM_table(
  data,
  predictor_a,
  predictor_p,
  outcome_a,
  outcome_p,
  mod_a = NULL,
  mod_p = NULL,
  mod_type = "mod",
  return_result = FALSE
)
APIM_table(
  data,
  predictor_a,
  predictor_p,
  outcome_a,
  outcome_p,
  mod_a = NULL,
  mod_p = NULL,
  mod_type = "mod",
  return_result = FALSE
)

Arguments

`data`	data frame object
`predictor_a`	predictor variable name for actor
`predictor_p`	predictor variable name for partner
`outcome_a`	dependent variable name for actor
`outcome_p`	dependent variable name for partner
`mod_a`	moderation variable name for actor. Support `dplyr::select()` syntax.
`mod_p`	moderation variable name for partner. Support `dplyr::select()` syntax.
`mod_type`	only 'mod' is supported for now
`return_result`	return `lavaan::parameterestimates()`. Default is `FALSE`

Value

data.frame of the APIM table

Examples

APIM_table(data = acitelli,
           predictor_a = 'Tension_A',
           predictor_p = 'Tension_P',
           outcome_a = 'Satisfaction_A',
           outcome_p = 'Satisfaction_P',
           mod_a = c('SelfPos_A','OtherPos_A','SimHob_A'),
           mod_p = c('SelfPos_P','OtherPos_P','SimHob_P'))

APIM_table(data = acitelli,
           predictor_a = 'Tension_A',
           predictor_p = 'Tension_P',
           outcome_a = 'Satisfaction_A',
           outcome_p = 'Satisfaction_P',
           mod_a = c('SelfPos_A','OtherPos_A','SimHob_A'),
           mod_p = c('SelfPos_P','OtherPos_P','SimHob_P'))

Confirmatory Factor Analysis (groupwise)

Description

This function will run N number of CFA where N = length(group), and report the fit measures of CFA in each group. The function is intended to help you get a better understanding of which group has abnormal fit indicator

Usage

cfa_groupwise(data, ..., group, model = NULL, ordered = FALSE)
cfa_groupwise(data, ..., group, model = NULL, ordered = FALSE)

Arguments

`data`	data frame
`...`	CFA items. Support `dplyr::select()` syntax.
`group`	character. group variable. Support `dplyr::select()` syntax.
`model`	explicit `lavaan` model. Must be specify with `model = lavaan_model_syntax`.
`ordered`	logical. default is `FALSE`. If it is set to `TRUE`, lavaan will treat it as a ordinal variable and use `DWLS` instead of `ML`

Details

All argument must be explicitly specified. If not, all arguments will be treated as CFA items

Value

a data.frame with group-wise CFA result

Examples

# The example is used as the illustration of the function output only.
# It does not imply the data is appropriate for the analysis.
cfa_groupwise(
  data = lavaan::HolzingerSwineford1939,
  group = "school",
  x1:x3,
  x4:x6,
  x7:x9
)
# The example is used as the illustration of the function output only.
# It does not imply the data is appropriate for the analysis.
cfa_groupwise(
  data = lavaan::HolzingerSwineford1939,
  group = "school",
  x1:x3,
  x4:x6,
  x7:x9
)

Confirmatory Factor Analysis

Description

The function fits a CFA model using the lavaan::cfa(). Users can fit single and multiple factors CFA, and it also supports multilevel CFA (by specifying the group). Users can fit the model by passing the items using dplyr::select() syntax or an explicit lavaan model for more versatile usage. All arguments (except the CFA items) must be explicitly named (e.g., model = your-model; see example for inappropriate behavior).

Usage

cfa_summary(
  data,
  ...,
  model = NULL,
  group = NULL,
  ordered = FALSE,
  digits = 3,
  estimator = "ML",
  model_covariance = TRUE,
  model_variance = TRUE,
  plot = TRUE,
  group_partial = NULL,
  streamline = FALSE,
  quite = FALSE,
  return_result = FALSE
)
cfa_summary(
  data,
  ...,
  model = NULL,
  group = NULL,
  ordered = FALSE,
  digits = 3,
  estimator = "ML",
  model_covariance = TRUE,
  model_variance = TRUE,
  plot = TRUE,
  group_partial = NULL,
  streamline = FALSE,
  quite = FALSE,
  return_result = FALSE
)

Arguments

`data`	data frame
`...`	CFA items. Multi-factor CFA items should be separated by comma (as different argument). See below for examples. Support `dplyr::select()` syntax.
`model`	explicit `lavaan` model. Must be specify with `model = lavaan_model_syntax`.
`group`	optional character. used for multi-level CFA. the nested variable for multilevel dataset (e.g., Country). Support `dplyr::select()` syntax.
`ordered`	Default is `FALSE`. If it is set to `TRUE`, `lavaan` will treat it as a ordinal variable and use `DWLS` instead of `ML`
`digits`	number of digits to round to
`estimator`	estimator for lavaan. Default is `ML`
`model_covariance`	print model covariance. Default is `TRUE`
`model_variance`	print model variance. Default is `TRUE`
`plot`	print a path diagram. Default is `TRUE`
`group_partial`	Items for partial equivalence. The form should be c('DV =~ item1', 'DV =~ item2').
`streamline`	print streamlined output
`quite`	suppress printing output
`return_result`	If it is set to `TRUE`, it will return the `lavaan` model

Details

First, just like researchers have argued against p value of 0.05 is not a good cut-of, researchers have also argue against that fit indicies (more importantly, the cut-off criteria) are not completely representative of the goodness of fit. Nonetheless, you are required to report them if you are publishing an article anyway. I will summarize the general recommended cut-off criteria for CFA model below. Researchers consider models with CFI (Bentler, 1990) that is > 0.95 to be excellent fit (Hu & Bentler, 1999), and > 0.9 to be acceptable fit. Researchers considered a model is excellent fit if CFI > 0.95 (Hu & Bentler, 1999), RMSEA < 0.06 (Hu & Bentler, 1999), TLI > 0.95, SRMR < 0.08. The model is considered an acceptable fit if CFI > 0.9 and RMSEA < 0.08. I need some time to find all the relevant references, but this should be the general consensus.

Value

a lavaan object if return_result is TRUE

References

Hu, L., & Bentler, P. M. (1999). Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternatives. Structural Equation Modeling, 6, 1–55. https://doi.org/10.1080/10705519909540118

Examples

# REMEMBER, YOU MUST NAMED ALL ARGUMENT EXCEPT THE CFA ITEMS ARGUMENT
# Fitting a multilevel single factor CFA model
fit <- cfa_summary(
  data = lavaan::HolzingerSwineford1939,
  x1:x3,
  x4:x6,
  x7:x9,
  group = "sex",
  model_variance = FALSE, # do not print the model_variance
  model_covariance = FALSE # do not print the model_covariance
)


# Fitting a CFA model by passing explicit lavaan model (equivalent to the above model)
# Note in the below function how I added `model = ` in front of the lavaan model.
# Similarly, the same rule apply for all arguments (e.g., `ordered = FALSE` instead of just `FALSE`)

fit <- cfa_summary(
  model = "visual  =~ x1 + x2 + x3",
  data = lavaan::HolzingerSwineford1939,
  quite = TRUE # silence all output
)

## Not run: 
# This will fail because I did not add `model = ` in front of the lavaan model.
# Therefore,you must add the tag in front of all arguments
# For example, `return_result = 'model'` instaed of `model`
cfa_summary("visual  =~ x1 + x2 + x3
             textual =~ x4 + x5 + x6
             speed   =~ x7 + x8 + x9 ",
  data = lavaan::HolzingerSwineford1939
)

## End(Not run)
# REMEMBER, YOU MUST NAMED ALL ARGUMENT EXCEPT THE CFA ITEMS ARGUMENT
# Fitting a multilevel single factor CFA model
fit <- cfa_summary(
  data = lavaan::HolzingerSwineford1939,
  x1:x3,
  x4:x6,
  x7:x9,
  group = "sex",
  model_variance = FALSE, # do not print the model_variance
  model_covariance = FALSE # do not print the model_covariance
)


# Fitting a CFA model by passing explicit lavaan model (equivalent to the above model)
# Note in the below function how I added `model = ` in front of the lavaan model.
# Similarly, the same rule apply for all arguments (e.g., `ordered = FALSE` instead of just `FALSE`)

fit <- cfa_summary(
  model = "visual  =~ x1 + x2 + x3",
  data = lavaan::HolzingerSwineford1939,
  quite = TRUE # silence all output
)

## Not run: 
# This will fail because I did not add `model = ` in front of the lavaan model.
# Therefore,you must add the tag in front of all arguments
# For example, `return_result = 'model'` instaed of `model`
cfa_summary("visual  =~ x1 + x2 + x3
             textual =~ x4 + x5 + x6
             speed   =~ x7 + x8 + x9 ",
  data = lavaan::HolzingerSwineford1939
)

## End(Not run)

Comparison of Model Fit

Description

Compare the fit indices of models (see below for model support)

Usage

compare_fit(
  ...,
  digits = 3,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)
compare_fit(
  ...,
  digits = 3,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)

Arguments

`...`	model. If it is a `lavaan` object, it will try to compute the measurement invariance. Other model types will be passed to `performance::compare_performance()`.
`digits`	number of digits to round to
`quite`	suppress printing output
`streamline`	print streamlined output
`return_result`	If it is set to `TRUE`, it will return the the compare fit data frame.

Value

a dataframe with fit indices and change in fit indices

Examples

# lme model

fit1 <- lm_model(
  data = popular,
  response_variable = popular,
  predictor_var = c(sex, extrav)
)

fit2 <- lm_model(
  data = popular,
  response_variable = popular,
  predictor_var = c(sex, extrav),
  two_way_interaction_factor = c(sex, extrav)
)

compare_fit(fit1, fit2)

# see ?measurement_invariance for measurement invariance example
# lme model

fit1 <- lm_model(
  data = popular,
  response_variable = popular,
  predictor_var = c(sex, extrav)
)

fit2 <- lm_model(
  data = popular,
  response_variable = popular,
  predictor_var = c(sex, extrav),
  two_way_interaction_factor = c(sex, extrav)
)

compare_fit(fit1, fit2)

# see ?measurement_invariance for measurement invariance example

Correlation table

Description

This function uses the correlation::correlation() to generate the correlation table.

Usage

cor_test(
  data,
  cols,
  ...,
  digits = 3,
  show_p = FALSE,
  method = "pearson",
  p_adjust = "none",
  streamline = FALSE,
  verbose = TRUE,
  return_result = FALSE
)
cor_test(
  data,
  cols,
  ...,
  digits = 3,
  show_p = FALSE,
  method = "pearson",
  p_adjust = "none",
  streamline = FALSE,
  verbose = TRUE,
  return_result = FALSE
)

Arguments

`data`	data frame
`cols`	correlation items. Support `dplyr::select()` syntax.
`...`	additional arguments passed to correlation::correlation(). See ?correlation::correlation. Note that the return data.frame from correlation::correlation() must contains `r` and `p` (e.g., passing `baysesian = TRUE` will not work)
`digits`	number of digits to round to
`show_p`	Default is `FALSE`. If `TRUE`, show the p-value in parenthesis.
`method`	Default is "pearson". Options are "kendall", "spearman","biserial", "polychoric", "tetrachoric", "biweight", "distance", "percentage", "blomqvist", "hoeffding", "gamma", "gaussian","shepherd", or "auto". See ?correlation::correlation for detail
`p_adjust`	Default is "holm". Options are "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr", "somers" or "none". See ?stats::p.adjust for more detail
`streamline`	print streamlined output.
`verbose`	deafult is `TRUE`.
`return_result`	If it is set to `TRUE`, it will return the data frame of the correlation table

Value

a data.frame of the correlation table

Examples

cor_test(iris, where(is.numeric))
cor_test(iris, where(is.numeric))

Cronbach alpha

Description

Computing the Cronbach alphas for multiple factors.

Usage

cronbach_alpha(
  ...,
  data,
  var_name,
  group = NULL,
  quite = FALSE,
  return_result = FALSE
)
cronbach_alpha(
  ...,
  data,
  var_name,
  group = NULL,
  quite = FALSE,
  return_result = FALSE
)

Arguments

`...`	Items. Group each latent factors using c() with when computing Cronbach alpha for 2+ factors (see example below)
`data`	`data.frame`. Must specify
`var_name`	character or a vector of characters. The order of `var_name` must be same as the order of the `...`
`group`	optional character. Specify this argument for computing Cronbach alpha for group separetely
`quite`	suppress printing output
`return_result`	If it is set to `TRUE`, it will return a `dataframe` object

Value

a data.frame object if return_result is TRUE

Examples

cronbach_alpha(
  data = lavaan::HolzingerSwineford1939,
  var_name = c('Visual','Textual','Speed'),
  c(x1,x2,x3), # one way to pass the items of a factor is by wrapping it with c()
  x4:x6, # another way to pass the items is use tidyselect syntax 
  x7:x9)
cronbach_alpha(
  data = lavaan::HolzingerSwineford1939,
  var_name = c('Visual','Textual','Speed'),
  c(x1,x2,x3), # one way to pass the items of a factor is by wrapping it with c()
  x4:x6, # another way to pass the items is use tidyselect syntax 
  x7:x9)

Descriptive Statistics Table

Description

This function generates a table of descriptive statistics (mainly using psych::describe()) and or a correlation table. User can export this to a csv file (optionally, using the file_path argument). Users can open the csv file with MS Excel then copy and paste the table into MS Word table.

Usage

descriptive_table(
  data,
  cols,
  ...,
  digits = 3,
  descriptive_indicator = c("mean", "sd", "cor"),
  file_path = NULL,
  streamline = FALSE,
  quite = FALSE,
  show_p = FALSE,
  return_result = FALSE
)
descriptive_table(
  data,
  cols,
  ...,
  digits = 3,
  descriptive_indicator = c("mean", "sd", "cor"),
  file_path = NULL,
  streamline = FALSE,
  quite = FALSE,
  show_p = FALSE,
  return_result = FALSE
)

Arguments

`data`	`data.frame`
`cols`	column(s) need to be included in the table. Support `dplyr::select()` syntax.
`...`	additional arguments passed to cor_test. See ?cor_test.
`digits`	number of digit for the descriptive table
`descriptive_indicator`	Default is mean, sd, cor. Options are missing (missing value count), non_missing (non-missing value count), cor (correlation table), n, mean, sd, median, trimmed (trimmed mean), median, mad (median absolute deviation from the median), min, max, range, skew, kurtosis, se (standard error)
`file_path`	file path for export. The function will implicitly pass this argument to the write.csv(file = file_path)
`streamline`	print streamlined output
`quite`	suppress printing output
`show_p`	Default is `FALSE`. If `TRUE`, show the p-value in parenthesis for correlations.
`return_result`	If it is set to `TRUE`, it will return the data frame of the descriptive table

Value

a data.frame of the descriptive table

Examples

descriptive_table(iris, cols = where(is.numeric)) # all numeric columns

descriptive_table(iris,
  cols = where(is.numeric),
  # get missing count, non-missing count, and mean & sd & correlation table
  descriptive_indicator = c("missing", "non_missing", "mean", "sd", "cor")
)
descriptive_table(iris, cols = where(is.numeric)) # all numeric columns

descriptive_table(iris,
  cols = where(is.numeric),
  # get missing count, non-missing count, and mean & sd & correlation table
  descriptive_indicator = c("missing", "non_missing", "mean", "sd", "cor")
)

Exploratory Factor Analysis

Description

The function is used to fit a exploratory factor analysis model. It will first find the optimal number of factors using parameters::n_factors. Once the optimal number of factor is determined, the function will fit the model using psych::fa(). Optionally, you can request a post-hoc CFA model based on the EFA model which gives you more fit indexes (e.g., CFI, RMSEA, TLI)

Usage

efa_summary(
  data,
  cols,
  rotation = "varimax",
  optimal_factor_method = FALSE,
  efa_plot = TRUE,
  digits = 3,
  n_factor = NULL,
  post_hoc_cfa = FALSE,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)
efa_summary(
  data,
  cols,
  rotation = "varimax",
  optimal_factor_method = FALSE,
  efa_plot = TRUE,
  digits = 3,
  n_factor = NULL,
  post_hoc_cfa = FALSE,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)

Arguments

`data`	`data.frame`
`cols`	columns. Support `dplyr::select()` syntax.
`rotation`	the rotation to use in estimation. Default is 'oblimin'. Options are 'none', 'varimax', 'quartimax', 'promax', 'oblimin', or 'simplimax'
`optimal_factor_method`	Show a summary of the number of factors by optimization method (e.g., BIC, VSS complexity, Velicer's MAP)
`efa_plot`	show explained variance by number of factor plot. default is `TRUE`.
`digits`	number of digits to round to
`n_factor`	number of factors for EFA. It will bypass the initial optimization algorithm, and fit the EFA model using this specified number of factor
`post_hoc_cfa`	a CFA model based on the extracted factor
`quite`	suppress printing output
`streamline`	print streamlined output
`return_result`	If it is set to `TRUE` (default is `FALSE`), it will return a `fa` object from `psych`

Value

a fa object from psych

Examples

efa_summary(lavaan::HolzingerSwineford1939, starts_with("x"), post_hoc_cfa = TRUE)
efa_summary(lavaan::HolzingerSwineford1939, starts_with("x"), post_hoc_cfa = TRUE)

get interaction term

Description

get interaction term

Usage

get_interaction_term(model)
get_interaction_term(model)

Arguments

model

model

Value

a list with predict vars names

get factor df to combine with mean_df

Description

get factor df to combine with mean_df

Usage

get_predict_df(data)
get_predict_df(data)

Arguments

data

data

Value

factor_df

Generalized Linear Regression

Description

Fit a generalized linear regression using glm(). This function is still in early development stage.

Usage

glm_model(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_factor = NULL,
  three_way_interaction_factor = NULL,
  family,
  quite = FALSE
)
glm_model(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_factor = NULL,
  three_way_interaction_factor = NULL,
  family,
  quite = FALSE
)

Arguments

`data`	`data.frame`
`response_variable`	response variable. Support `dplyr::select()` syntax.
`predictor_variable`	predictor variable. Support `dplyr::select()` syntax.
`two_way_interaction_factor`	two-way interaction factors. You need to pass 2+ factor. Support `dplyr::select()` syntax.
`three_way_interaction_factor`	three-way interaction factor. You need to pass exactly 3 factors. Specifying three-way interaction factors automatically included all two-way interactions, so please do not specify the two_way_interaction_factor argument. Support `dplyr::select()` syntax.
`family`	a GLM family. It will passed to the family argument in glm See `?glm` for possible options.
`quite`	suppress printing output

Value

an object class of glm representing the linear regression fit

Examples

fit <- glm_model(
  response_variable = incidence,
  predictor_variable = period,
  family = "poisson", # or you can enter as poisson(link = 'log'),
  data = lme4::cbpp
)
fit <- glm_model(
  response_variable = incidence,
  predictor_variable = period,
  family = "poisson", # or you can enter as poisson(link = 'log'),
  data = lme4::cbpp
)

Exploratory Linear Regression Model Table

Description

Exploratory analyses for linear regression models with multiple response, predictor, and two-way interaction variables. (lm models). At the moment, multi-categorical variables are not supported as predictors or interactions (but control is fine). Binary variable should be numeric instead of factor

Usage

glm_model_explore(
  data,
  response_variable,
  predictor_variable,
  family,
  two_way_interaction_variable = NULL,
  three_way_interaction_variable = NULL,
  control_variable = NULL,
  marginal_alpha = 0.1,
  verbose = TRUE,
  show_p = TRUE,
  return_result = FALSE,
  print_control = FALSE,
  plot_interaction = FALSE,
  file_dir = NULL,
  device = "jpeg",
  width = 8.5,
  height = 5,
  units = "in",
  y_lim = c(0, 1)
)
glm_model_explore(
  data,
  response_variable,
  predictor_variable,
  family,
  two_way_interaction_variable = NULL,
  three_way_interaction_variable = NULL,
  control_variable = NULL,
  marginal_alpha = 0.1,
  verbose = TRUE,
  show_p = TRUE,
  return_result = FALSE,
  print_control = FALSE,
  plot_interaction = FALSE,
  file_dir = NULL,
  device = "jpeg",
  width = 8.5,
  height = 5,
  units = "in",
  y_lim = c(0, 1)
)

Arguments

`data`	`data.frame`
`response_variable`	Response variable. Support `dplyr::select()` syntax.
`predictor_variable`	Pred variable. Support `dplyr::select()` syntax.
`family`	a GLM family. It will passed to the family argument in glm See `?glm` for possible options.
`two_way_interaction_variable`	Two-way interaction variable. Each two-way interaction variable will interact with each pred variable. Support `dplyr::select()` syntax.
`three_way_interaction_variable`	Three-way interaction variable. Each three-way interaction variable will interact with each pred and two-way interaction variables. Support `dplyr::select()` syntax.
`control_variable`	Control variables. Support `dplyr::select()` syntax.
`marginal_alpha`	Set marginal_alpha level for marginally significant (denoted by `.`). Set to 0.05 if do not want marginally significant denotation.
`verbose`	Default is `TRUE`. Set to `FALSE` to suppress outputs
`show_p`	Default is `TRUE`. When `TRUE`, show the p-value in parenthesis.
`return_result`	Default is `FALSE`. If `TRUE`, it returns the model estimates as a data frame.
`print_control`	Default is `FALSE`. If `TRUE`, print coefficients of control variables.
`plot_interaction`	Default is `FALSE`. If `TRUE`, interactions will be plotted and saved on your laptop.
`file_dir`	Path of the directory to save plot to
`device`	Default is "jpeg". See ggplot2::ggsave() for all options.
`width`	Default is 8.5 (i.e., letter size width).
`height`	Default is 5.
`units`	Default is inches. Options are "in", "cm", "mm" or "px".
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`

Value

data.frame

Examples


test = data.frame(y1 = sample(c(0, 1), size = 1000, replace = TRUE),
y2 = sample(c(0, 1), size = 1000, replace = TRUE),
y3 = sample(c(0, 1), size = 1000, replace = TRUE),
x1 = rnorm(1000,100,10),
x2 = rnorm(1000,10,1),
x3 = rnorm(1000,6,2),
m1 = rnorm(1000,3,1),
m2 = rnorm(1000,2,0.5),
m3 = rnorm(1000,9,0.1),
c1 = rnorm(1000,5,0.4),
c2 = rnorm(1000,2,0.2),
c3 = rnorm(1000,7,0.9)
)

glm_model_explore(data = test, 
                 response_variable = c(y1,y2,y3),
                 predictor_variable = c(x1,x2,x3),
                 two_way_interaction_variable = c(m1,m2,m3),
                 family = binomial(link = 'logit'),
                 control_variable = c(c1,c2,c3))
test = data.frame(y1 = sample(c(0, 1), size = 1000, replace = TRUE),
y2 = sample(c(0, 1), size = 1000, replace = TRUE),
y3 = sample(c(0, 1), size = 1000, replace = TRUE),
x1 = rnorm(1000,100,10),
x2 = rnorm(1000,10,1),
x3 = rnorm(1000,6,2),
m1 = rnorm(1000,3,1),
m2 = rnorm(1000,2,0.5),
m3 = rnorm(1000,9,0.1),
c1 = rnorm(1000,5,0.4),
c2 = rnorm(1000,2,0.2),
c3 = rnorm(1000,7,0.9)
)

glm_model_explore(data = test, 
                 response_variable = c(y1,y2,y3),
                 predictor_variable = c(x1,x2,x3),
                 two_way_interaction_variable = c(m1,m2,m3),
                 family = binomial(link = 'logit'),
                 control_variable = c(c1,c2,c3))

Convert HTML to PDF

Description

This is a helper function for knitting Rmd. Due to technological limitation, the output cannot knit to PDF in Rmd directly (the problem is with the latex engine printing unicode character). Therefore, to bypass this problem, you will first need to knit to html file first, then use this function to convert it to a PDF file.

Usage

html_to_pdf(file_path = NULL, dir = NULL, scale = 1, render_exist = FALSE)
html_to_pdf(file_path = NULL, dir = NULL, scale = 1, render_exist = FALSE)

Arguments

`file_path`	file path to the HTML file (can be relative if you are in a R project)
`dir`	file path to the directory of all HTML files (can be relative if you are in a R project)
`scale`	the scale of the PDF
`render_exist`	overwrite exist PDF. Default is `FALSE`

Value

no return value

Examples

## Not run: 
html_to_pdf(file_path = "html_name.html")
# all HTML files in the my_html_folder will be converted
html_to_pdf(dir = "Users/Desktop/my_html_folder")

## End(Not run)
## Not run: 
html_to_pdf(file_path = "html_name.html")
# all HTML files in the my_html_folder will be converted
html_to_pdf(dir = "Users/Desktop/my_html_folder")

## End(Not run)

Interaction plot

Description

The function creates interaction plot. By default, it will create an interaction plot using -1 SD and +1 SD of continuous variables, or the two levels of binary variables.

Usage

interaction_plot(
  model,
  interaction_term = NULL,
  response_var_name = NULL,
  predict_var1_name = NULL,
  predict_var2_name = NULL,
  predict_var3_name = NULL,
  predict_var1_level = NULL,
  predict_var2_level = NULL,
  predict_var3_level = NULL,
  predict_var1_level_name = NULL,
  predict_var2_level_name = NULL,
  predict_var3_level_name = NULL,
  y_lim = NULL,
  plot_color = FALSE,
  return_plot_data = FALSE,
  return_plot = FALSE,
  verbose = TRUE,
  print_plot = TRUE,
  data = NULL
)
interaction_plot(
  model,
  interaction_term = NULL,
  response_var_name = NULL,
  predict_var1_name = NULL,
  predict_var2_name = NULL,
  predict_var3_name = NULL,
  predict_var1_level = NULL,
  predict_var2_level = NULL,
  predict_var3_level = NULL,
  predict_var1_level_name = NULL,
  predict_var2_level_name = NULL,
  predict_var3_level_name = NULL,
  y_lim = NULL,
  plot_color = FALSE,
  return_plot_data = FALSE,
  return_plot = FALSE,
  verbose = TRUE,
  print_plot = TRUE,
  data = NULL
)

Arguments

`model`	a regression model object from effect.
`interaction_term`	default is the first highest order interaction term in the model. The term should be given explicitly if you want to plot other interaction terms.
`response_var_name`	The name of the response variable can be changed using this setting.
`predict_var1_name`	The name of the first predictor can be changed using this setting.
`predict_var2_name`	The name of the second predictor can be changed using this setting.
`predict_var3_name`	The name of the third predictor can be changed using this setting.
`predict_var1_level`	The default is -1 SD and +1 SD for a continuous variable, and it is the two levels for a binary variable. These can be changed using this setting.
`predict_var2_level`	The default is -1 SD and +1 SD for a continuous variable, and it is the two levels for a binary variable. These can be changed using this setting.
`predict_var3_level`	The default is -1 SD and +1 SD for a continuous variable, and it is the two levels for a binary variable. These can be changed using this setting.
`predict_var1_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the left to right on the x-axis.
`predict_var2_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the top to down on the legend.
`predict_var3_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the left to right on the facets.
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`
`plot_color`	default if `FALSE`. Set to `TRUE` if you want to plot in color
`return_plot_data`	default is `FALSE`. Set to `TRUE` to return the plot data.
`return_plot`	default is `FALSE`. Set to `TRUE` to return the plot.
`verbose`	deafult is `TRUE`.
`print_plot`	default is `TRUE`. Set to `TRUE` to print the plot.
`data`	Optional data.frame. Only used when it is not possible to extract data from the model object.

Value

a ggplot object

Examples


model_1 <- lm(Sepal.Length ~ Petal.Width * Sepal.Width,
              data = iris)
interaction_plot(model_1)

model_2 <- lm(Sepal.Length ~ Petal.Width * Sepal.Width * Petal.Length,
              data = iris
)

interaction_plot(model_2, # it will automatically select the first three-way interaction term

                 # change the name of the variables of the plot
                 response_var_name = 'SEPAL LENGTH',
                 predict_var1_name = 'PETAL WIDTH',
                 predict_var2_name = 'SEPAL WIDTH',
                 predict_var3_name = 'PETAL LENGTH',
                           
                 # change the number of levels of the variables (e.g., adding the mean)
                 predict_var1_level = c(0.43, 1.19,1.96), 
                 predict_var2_level = c(2.62, 3.05,3.49), 
                 predict_var3_level = c(1.99,3.758,5.52),
                 predict_var1_level_name = c('-1 SD','Mean','+1 SD'),
                 predict_var2_level_name = c('-1 SD','Mean','+1 SD'),
                 predict_var3_level_name = c('-1 SD','Mean','+1 SD')) 
model_1 <- lm(Sepal.Length ~ Petal.Width * Sepal.Width,
              data = iris)
interaction_plot(model_1)

model_2 <- lm(Sepal.Length ~ Petal.Width * Sepal.Width * Petal.Length,
              data = iris
)

interaction_plot(model_2, # it will automatically select the first three-way interaction term

                 # change the name of the variables of the plot
                 response_var_name = 'SEPAL LENGTH',
                 predict_var1_name = 'PETAL WIDTH',
                 predict_var2_name = 'SEPAL WIDTH',
                 predict_var3_name = 'PETAL LENGTH',
                           
                 # change the number of levels of the variables (e.g., adding the mean)
                 predict_var1_level = c(0.43, 1.19,1.96), 
                 predict_var2_level = c(2.62, 3.05,3.49), 
                 predict_var3_level = c(1.99,3.758,5.52),
                 predict_var1_level_name = c('-1 SD','Mean','+1 SD'),
                 predict_var2_level_name = c('-1 SD','Mean','+1 SD'),
                 predict_var3_level_name = c('-1 SD','Mean','+1 SD'))

Knit Rmd Files Instruction

Description

This is a helper function that instruct users of the package how to knit a R Markdown (Rmd) files

Usage

knit_to_Rmd()
knit_to_Rmd()

Value

no return value

Examples

knit_to_Rmd()
knit_to_Rmd()

get label name

Description

get label name

Usage

label_name(
  graph_label_name,
  response_var_name,
  predict_var1_name,
  predict_var2_name,
  predict_var3_name
)
label_name(
  graph_label_name,
  response_var_name,
  predict_var1_name,
  predict_var2_name,
  predict_var3_name
)

Arguments

`graph_label_name`	label name
`response_var_name`	outcome variable name
`predict_var1_name`	predictor 1 name
`predict_var2_name`	predictor 2 name
`predict_var3_name`	predictor 3 name

Value

vector of var name

Linear Regressions / ANOVA / ANCOVA

Description

Fit a linear regression using lm(). Linear regression is used to explore the effect of continuous variables / categorical variables in predicting a normally-distributed continuous variables.

Usage

lm_model(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_factor = NULL,
  three_way_interaction_factor = NULL,
  quite = FALSE
)
lm_model(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_factor = NULL,
  three_way_interaction_factor = NULL,
  quite = FALSE
)

Arguments

`data`	`data.frame`
`response_variable`	response variable. Support `dplyr::select()` syntax.
`predictor_variable`	predictor variable. Support `dplyr::select()` syntax. It will automatically remove the response variable from predictor variable, so you can use `contains()` or `start_with()` safely.
`two_way_interaction_factor`	two-way interaction factors. You need to pass 2+ factor. Support `dplyr::select()` syntax.
`three_way_interaction_factor`	three-way interaction factor. You need to pass exactly 3 factors. Specifying three-way interaction factors automatically included all two-way interactions, so please do not specify the two_way_interaction_factor argument. Support `dplyr::select()` syntax.
`quite`	suppress printing output

Value

an object class of lm representing the linear regression fit

Examples

fit <- lm_model(
  data = iris,
  response_variable = Sepal.Length,
  predictor_variable = dplyr::everything(),
  two_way_interaction_factor = c(Sepal.Width, Species)
)
fit <- lm_model(
  data = iris,
  response_variable = Sepal.Length,
  predictor_variable = dplyr::everything(),
  two_way_interaction_factor = c(Sepal.Width, Species)
)

Exploratory Linear Regression Model Table

Description

Usage

lm_model_explore(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  three_way_interaction_variable = NULL,
  control_variable = NULL,
  marginal_alpha = 0.1,
  verbose = TRUE,
  show_p = TRUE,
  return_result = FALSE,
  print_control = FALSE,
  plot_interaction = FALSE,
  file_dir = NULL,
  device = "jpeg",
  width = 8.5,
  height = 5,
  units = "in",
  y_lim = NULL
)
lm_model_explore(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  three_way_interaction_variable = NULL,
  control_variable = NULL,
  marginal_alpha = 0.1,
  verbose = TRUE,
  show_p = TRUE,
  return_result = FALSE,
  print_control = FALSE,
  plot_interaction = FALSE,
  file_dir = NULL,
  device = "jpeg",
  width = 8.5,
  height = 5,
  units = "in",
  y_lim = NULL
)

Arguments

`data`	`data.frame`
`response_variable`	Response variable. Support `dplyr::select()` syntax.
`predictor_variable`	Pred variable. Support `dplyr::select()` syntax.
`two_way_interaction_variable`	Two-way interaction variable. Each two-way interaction variable will interact with each pred variable. Support `dplyr::select()` syntax.
`three_way_interaction_variable`	Three-way interaction variable. Each three-way interaction variable will interact with each pred and two-way interaction variables. Support `dplyr::select()` syntax.
`control_variable`	Control variables. Support `dplyr::select()` syntax.
`marginal_alpha`	Set marginal_alpha level for marginally significant (denoted by `.`). Set to 0.05 if do not want marginally significant denotation.
`verbose`	Default is `TRUE`. Set to `FALSE` to suppress outputs
`show_p`	Default is `TRUE`. When `TRUE`, show the p-value in parenthesis.
`return_result`	Default is `FALSE`. If `TRUE`, it returns the model estimates as a data frame.
`print_control`	Default is `FALSE`. If `TRUE`, print coefficients of control variables.
`plot_interaction`	Default is `FALSE`. If `TRUE`, interactions will be plotted and saved on your laptop.
`file_dir`	Path of the directory to save plot to
`device`	Default is "jpeg". See ggplot2::ggsave() for all options.
`width`	Default is 8.5 (i.e., letter size width).
`height`	Default is 5.
`units`	Default is inches. Options are "in", "cm", "mm" or "px".
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`

Value

data.frame

Examples


test = data.frame(y1 = rnorm(1000,2,3),
y2 = rnorm(1000,10,2),
y3 = rnorm(1000,1,4),
x1 = rnorm(1000,100,10),
x2 = rnorm(1000,10,1),
x3 = rnorm(1000,6,2),
m1 = rnorm(1000,3,1),
m2 = rnorm(1000,2,0.5),
m3 = rnorm(1000,9,0.1),
c1 = rnorm(1000,5,0.4),
c2 = rnorm(1000,2,0.2),
c3 = rnorm(1000,7,0.9)
)


lm_model_explore(data = test, 
                 response_variable = c(y1,y2,y3),
                 predictor_variable = c(x1,x2,x3),
                 two_way_interaction_variable = c(m1,m2,m3),
                 control_variable = c(c1,c2,c3))

test = data.frame(y1 = rnorm(1000,2,3),
y2 = rnorm(1000,10,2),
y3 = rnorm(1000,1,4),
x1 = rnorm(1000,100,10),
x2 = rnorm(1000,10,1),
x3 = rnorm(1000,6,2),
m1 = rnorm(1000,3,1),
m2 = rnorm(1000,2,0.5),
m3 = rnorm(1000,9,0.1),
c1 = rnorm(1000,5,0.4),
c2 = rnorm(1000,2,0.2),
c3 = rnorm(1000,7,0.9)
)


lm_model_explore(data = test, 
                 response_variable = c(y1,y2,y3),
                 predictor_variable = c(x1,x2,x3),
                 two_way_interaction_variable = c(m1,m2,m3),
                 control_variable = c(c1,c2,c3))

Model Summary for Linear Regression

Description

An integrated function for fitting a linear regression model. This function will no longer be updated. Please use the these functions separately instead: model_summary, interaction_plot,and simple_slope.

Usage

lm_model_summary(
  data,
  response_variable = NULL,
  predictor_variable = NULL,
  two_way_interaction_factor = NULL,
  three_way_interaction_factor = NULL,
  family = NULL,
  cateogrical_var = NULL,
  graph_label_name = NULL,
  model_summary = TRUE,
  interaction_plot = TRUE,
  y_lim = NULL,
  plot_color = FALSE,
  digits = 3,
  simple_slope = FALSE,
  assumption_plot = FALSE,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)
lm_model_summary(
  data,
  response_variable = NULL,
  predictor_variable = NULL,
  two_way_interaction_factor = NULL,
  three_way_interaction_factor = NULL,
  family = NULL,
  cateogrical_var = NULL,
  graph_label_name = NULL,
  model_summary = TRUE,
  interaction_plot = TRUE,
  y_lim = NULL,
  plot_color = FALSE,
  digits = 3,
  simple_slope = FALSE,
  assumption_plot = FALSE,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)

Arguments

`data`	`data.frame`
`response_variable`	DV (i.e., outcome variable / response variable). Length of 1. Support `dplyr::select()` syntax.
`predictor_variable`	IV. Support `dplyr::select()` syntax.
`two_way_interaction_factor`	two-way interaction factors. You need to pass 2+ factor. Support `dplyr::select()` syntax.
`three_way_interaction_factor`	three-way interaction factor. You need to pass exactly 3 factors. Specifying three-way interaction factors automatically included all two-way interactions, so please do not specify the two_way_interaction_factor argument. Support `dplyr::select()` syntax.
`family`	a GLM family. It will passed to the family argument in glm. See `?glm` for possible options.
`cateogrical_var`	list. Specify the upper bound and lower bound directly instead of using ± 1 SD from the mean. Passed in the form of `list(var_name1 = c(upper_bound1, lower_bound1),var_name2 = c(upper_bound2, lower_bound2))`
`graph_label_name`	optional vector or function. vector of length 2 for two-way interaction graph. vector of length 3 for three-way interaction graph. Vector should be passed in the form of c(response_var, predict_var1, predict_var2, ...). Function should be passed as a switch function (see ?two_way_interaction_plot for an example)
`model_summary`	print model summary. Required to be `TRUE` if you want `assumption_plot`.
`interaction_plot`	generate the interaction plot. Default is `TRUE`
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`
`plot_color`	If it is set to `TRUE` (default is `FALSE`), the interaction plot will plot with color.
`digits`	number of digits to round to
`simple_slope`	Slope estimate at +1/-1 SD and the mean of the moderator. Uses `interactions::sim_slope()` in the background.
`assumption_plot`	Generate an panel of plots that check major assumptions. It is usually recommended to inspect model assumption violation visually. In the background, it calls `performance::check_model()`
`quite`	suppress printing output
`streamline`	print streamlined output
`return_result`	If it is set to `TRUE` (default is `FALSE`), it will return the `model`, `model_summary`, and `plot` (if the interaction term is included)

Value

a list of all requested items in the order of model, model_summary, interaction_plot, simple_slope

Examples

fit <- lm_model_summary(
  data = iris,
  response_variable = "Sepal.Length",
  predictor_variable = dplyr::everything(),
  two_way_interaction_factor = c(Sepal.Width, Species),
  interaction_plot = FALSE, # you can also request the interaction plot
  simple_slope = FALSE, # you can also request simple slope estimate 
  assumption_plot = FALSE, # you can also request assumption plot
  streamline = FALSE #you can change this to get the least amount of info
)
fit <- lm_model_summary(
  data = iris,
  response_variable = "Sepal.Length",
  predictor_variable = dplyr::everything(),
  two_way_interaction_factor = c(Sepal.Width, Species),
  interaction_plot = FALSE, # you can also request the interaction plot
  simple_slope = FALSE, # you can also request simple slope estimate 
  assumption_plot = FALSE, # you can also request assumption plot
  streamline = FALSE #you can change this to get the least amount of info
)

Linear Regression Model Table

Description

Generate tables with multiple response, predictor, or two-way interaction variables (only lm models are supported). You can pass multiple variables for one type of variable (either response, pred, or interaction) only. If you want to pass multiple variables for multiple type of variable, try lm_model_explore instead. At the moment, multi-categorical variables are not supported as predictors or interactions (but control is fine). Binary variable should be numeric instead of factor

Usage

lm_model_table(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  control_variable = NULL,
  other_parameters = NULL,
  marginal_alpha = 0.1,
  return_result = FALSE,
  verbose = TRUE,
  show_p = FALSE
)
lm_model_table(
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  control_variable = NULL,
  other_parameters = NULL,
  marginal_alpha = 0.1,
  return_result = FALSE,
  verbose = TRUE,
  show_p = FALSE
)

Arguments

`data`	`data.frame`
`response_variable`	response variable. Support `dplyr::select()` syntax.
`predictor_variable`	predictor variable. Support `dplyr::select()` syntax. It will automatically remove the response variable from predictor variable, so you can use `contains()` or `start_with()` safely.
`two_way_interaction_variable`	Two-way interaction variable. Each two-way interaction variable will interact with the predictor variable. Support `dplyr::select()` syntax.
`control_variable`	control variables. Support `dplyr::select()` syntax.
`other_parameters`	catch call for all other parameters that need to be entered (e.g., non-changing interaction terms). Have to be `character` type.
`marginal_alpha`	the set marginal_alpha level for marginally significant (denoted by `.`). Set to 0.05 if do not want marginally significant denotation.
`return_result`	It set to `TRUE`, it return the model estimates data frame.
`verbose`	default is `TRUE`. Set to `FALSE` to suppress outputs
`show_p`	show the p-value in parenthesis

Value

data.frame

Examples

# If you want all varibles to be changing, try lm_model_explore.

test = data.frame(y1 = rnorm(1000,2,3),
y2 = rnorm(1000,10,2),
y3 = rnorm(1000,1,4),
x1 = rnorm(1000,100,10),
x2 = rnorm(1000,10,1),
x3 = rnorm(1000,6,2),
m1 = rnorm(1000,3,1),
m2 = rnorm(1000,2,0.5),
m3 = rnorm(1000,9,0.1),
c1 = rnorm(1000,5,0.4),
c2 = rnorm(1000,2,0.2),
c3 = rnorm(1000,7,0.9)
)

# Changing response variable 
lm_model_table(data = test, 
               response_variable = c(y1,y2,y3),
               predictor_variable = x1,
               control_variable = c(c1,c2,c3))
 
# Changing predictors 
lm_model_table(data = test, 
               response_variable = y1,
               predictor_variable = c(x1,x2,x3),
               control_variable = c(c1,c2,c3))
                 
                 
# Changing interaction terms with a non-changing response variable
lm_model_table(data = test, 
               response_variable = y1,
               predictor_variable = x1,
               two_way_interaction_variable = c(m1,m2,m3),
               control_variable = c(c1,c2,c3))
                 
# A non-changing interaction term with changing response variables                 
lm_model_table(data = test, 
               response_variable = c(y1,y2,y3),
               predictor_variable = x1,
               other_parameters = c('x1*m1'),
               control_variable = c(c1,c2,c3))                  
# If you want all varibles to be changing, try lm_model_explore.

test = data.frame(y1 = rnorm(1000,2,3),
y2 = rnorm(1000,10,2),
y3 = rnorm(1000,1,4),
x1 = rnorm(1000,100,10),
x2 = rnorm(1000,10,1),
x3 = rnorm(1000,6,2),
m1 = rnorm(1000,3,1),
m2 = rnorm(1000,2,0.5),
m3 = rnorm(1000,9,0.1),
c1 = rnorm(1000,5,0.4),
c2 = rnorm(1000,2,0.2),
c3 = rnorm(1000,7,0.9)
)

# Changing response variable 
lm_model_table(data = test, 
               response_variable = c(y1,y2,y3),
               predictor_variable = x1,
               control_variable = c(c1,c2,c3))
 
# Changing predictors 
lm_model_table(data = test, 
               response_variable = y1,
               predictor_variable = c(x1,x2,x3),
               control_variable = c(c1,c2,c3))
                 
                 
# Changing interaction terms with a non-changing response variable
lm_model_table(data = test, 
               response_variable = y1,
               predictor_variable = x1,
               two_way_interaction_variable = c(m1,m2,m3),
               control_variable = c(c1,c2,c3))
                 
# A non-changing interaction term with changing response variables                 
lm_model_table(data = test, 
               response_variable = c(y1,y2,y3),
               predictor_variable = x1,
               other_parameters = c('x1*m1'),
               control_variable = c(c1,c2,c3))

Exploratory Linear Mixed Effect Model Table

Description

Exploratory analyses for linear regression models with multiple response, predictor, and two-way interaction variables. (lmer models). At the moment, multi-categorical variables are not supported as predictors or interactions (but control is fine). Binary variable should be numeric instead of factor This function also do not supports changing random slopes.

Usage

lme_model_explore(
  ...,
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  three_way_interaction_variable = NULL,
  random_effect,
  control_variable = NULL,
  marginal_alpha = 0.1,
  return_result = FALSE,
  print_control = FALSE,
  verbose = TRUE,
  show_p = TRUE,
  show_formula = FALSE
)
lme_model_explore(
  ...,
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  three_way_interaction_variable = NULL,
  random_effect,
  control_variable = NULL,
  marginal_alpha = 0.1,
  return_result = FALSE,
  print_control = FALSE,
  verbose = TRUE,
  show_p = TRUE,
  show_formula = FALSE
)

Arguments

`...`	additional parameters pass to lme4::lmer()
`data`	`data.frame`
`response_variable`	Response variable. Support `dplyr::select()` syntax.
`predictor_variable`	Pred variable. Support `dplyr::select()` syntax.
`two_way_interaction_variable`	Two-way interaction variable. Each two-way interaction variable will interact with each pred variable. Support `dplyr::select()` syntax.
`three_way_interaction_variable`	Three-way interaction variable. Each three-way interaction variable will interact with each pred and two-way interaction variables. Support `dplyr::select()` syntax.
`random_effect`	The random-effects terms in the format of `⁠(\|)⁠`. See lm4::lmer for specifics.
`control_variable`	Control variables. Support `dplyr::select()` syntax.
`marginal_alpha`	Set marginal_alpha level for marginally significant (denoted by `.`). Set to 0.05 if do not want marginally significant denotation.
`return_result`	Default is `FALSE`. If `TRUE`, it returns the model estimates as a data frame.
`print_control`	Default is `FALSE`. If `TRUE`, print coefficients of control variables.
`verbose`	Default is `TRUE`. Set to `FALSE` to suppress outputs
`show_p`	Default is `TRUE`. When `TRUE`, show the p-value in parenthesis.
`show_formula`	Default is `FALSE`. Set to `TRUE` to show the formula.

Value

data.frame

Examples


lme_model_explore(data = popular,
                  response_variable = c(popular,extrav),
                  predictor_variable = c(texp),
                  two_way_interaction_variable = sex,
                  random_effect = '(1 | class)')


lme_model_explore(data = popular,
                  response_variable = c(popular,extrav),
                  predictor_variable = c(texp),
                  two_way_interaction_variable = sex,
                  random_effect = '(1 | class)')

Linear Mixed Effect Model Table

Description

Generate tables with multiple response, predictor, or two-way interaction variables (only lmer models are supported). You can pass multiple variables for one type of variable (either response, pred, or interaction) only. If you want to pass multiple variables for multiple type of variable, try lmer_model_explore instead. At the moment, multi-categorical variables are not supported as predictors or interactions (but control is fine). Binary variable should be numeric instead of factor This function also do not supports changing random slopes. Please use other_parameters if you want to add non-changing interaction term.

Usage

lme_model_table(
  ...,
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  random_effect,
  control_variable = NULL,
  other_parameters = NULL,
  marginal_alpha = 0.1,
  return_result = FALSE,
  verbose = TRUE,
  show_p = FALSE
)
lme_model_table(
  ...,
  data,
  response_variable,
  predictor_variable,
  two_way_interaction_variable = NULL,
  random_effect,
  control_variable = NULL,
  other_parameters = NULL,
  marginal_alpha = 0.1,
  return_result = FALSE,
  verbose = TRUE,
  show_p = FALSE
)

Arguments

`...`	additional parameters pass to lmerTest::lmer()
`data`	`data.frame`
`response_variable`	response variable. Support `dplyr::select()` syntax.
`predictor_variable`	predictor variable. Support `dplyr::select()` syntax. It will automatically remove the response variable from predictor variable, so you can use `contains()` or `start_with()` safely.
`two_way_interaction_variable`	Two-way interaction variable. Each two-way interaction variable will interact with the predictor variable. Support `dplyr::select()` syntax.
`random_effect`	The random-effects terms in the format of `⁠(\|)⁠`. See lm4::lmer for specifics.
`control_variable`	control variables. Support `dplyr::select()` syntax.
`other_parameters`	catch call for all other parameters that need to be entered (e.g., non-changing interaction terms). Have to be `character` type.
`marginal_alpha`	the set marginal_alpha level for marginally significant (denoted by `.`). Set to 0.05 if do not want marginally significant denotation.
`return_result`	It set to `TRUE`, it return the model estimates data frame.
`verbose`	default is `TRUE`. Set to `FALSE` to suppress outputs
`show_p`	show the p-value in parenthesis

Value

data.frame

Examples

# If you want all varibles to be changing, try lmer_model_explore.
# For more examples, see ?lm_model_table. 

# Changing interaction terms with a non-changing response variable
lme_model_table(data = popular,
                 response_variable = popular,
                 predictor_variable = texp,
                 two_way_interaction_variable = c(extrav,sex),
                 random_effect = '(1 | class)')

# A non-changing interaction term with changing response variables
lme_model_table(data = popular,
                 response_variable = c(popular,sex),
                 predictor_variable = texp,
                 other_parameters = 'texp*extrav',
                 random_effect = '(1 | class)')
# If you want all varibles to be changing, try lmer_model_explore.
# For more examples, see ?lm_model_table. 

# Changing interaction terms with a non-changing response variable
lme_model_table(data = popular,
                 response_variable = popular,
                 predictor_variable = texp,
                 two_way_interaction_variable = c(extrav,sex),
                 random_effect = '(1 | class)')

# A non-changing interaction term with changing response variables
lme_model_table(data = popular,
                 response_variable = c(popular,sex),
                 predictor_variable = texp,
                 other_parameters = 'texp*extrav',
                 random_effect = '(1 | class)')

Measurement Invariance

Description

Compute the measurement invariance model (i.e., measurement equivalence model) using multi-group confirmatory factor analysis (MGCFA; Jöreskog, 1971). This function uses the lavaan::cfa() in the backend. Users can run the configural-metric or the configural-metric-scalar comparisons (see below for detail instruction). All arguments (except the CFA items) must be explicitly named (like model = your-model; see example for inappropriate behavior).

Usage

measurement_invariance(
  data,
  ...,
  model = NULL,
  group,
  ordered = FALSE,
  group_partial = NULL,
  invariance_level = "scalar",
  estimator = "ML",
  digits = 3,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)
measurement_invariance(
  data,
  ...,
  model = NULL,
  group,
  ordered = FALSE,
  group_partial = NULL,
  invariance_level = "scalar",
  estimator = "ML",
  digits = 3,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)

Arguments

`data`	`data.frame`
`...`	CFA items. Multi-factor CFA items should be separated by comma (as different argument). See below for examples. Support `dplyr::select()` syntax.
`model`	explicit `lavaan` model. Must be specify with `model = lavaan_model_syntax`.
`group`	the nested variable for multilevel dataset (e.g., Country). Support `dplyr::select()` syntax.
`ordered`	Default is `FALSE`. If it is set to `TRUE`, `lavaan` will treat it as a ordinal variable and use `DWLS` instead of `ML`
`group_partial`	items for partial equivalence. The form should be c('DV =~ item1', 'DV =~ item2'). See details for recommended practice.
`invariance_level`	"metric" or "scalar". Default is 'metric'. Set as 'metric' for configural-metric comparison, and set as 'scalar' for configural-metric-scalar comparison.
`estimator`	estimator for lavaan. Default is `ML`
`digits`	number of digits to round to
`quite`	suppress printing output except the model summary.
`streamline`	print streamlined output
`return_result`	If it is set to `TRUE`, it will return a data frame of the fit measure summary

Details

Chen (2007) suggested that change in CFI <= |-0.010| supplemented by RMSEA <= 0.015 indicate non-invariance when sample sizes were equal across groups and larger than 300 in each group (Chen, 2007). And, Chen (2007) suggested that change in CFI <= |-0.005| and change in RMSEA <= 0.010 for unequal sample size with each group smaller than 300. For SRMR, Chen (2007) recommend change in SRMR < 0.030 for metric-invariance and change in SRMR < 0.015 for scalar-invariance. For large group size, Rutowski & Svetina (2014) recommended a more liberal cut-off for metric non-invariance for CFI (change in CFI <= |-0.020|) and RMSEA (RMSEA <= 0.030). However, this more liberal cut-off DOES NOT apply to testing scalar non-invariance. If measurement-invariance is not achieved, some researchers suggesting partial invariance is acceptable (by releasing the constraints on some factors). For example, Steenkamp and Baumgartner (1998) suggested that ideally more than half of items on a factor should be invariant. However, it is important to note that no empirical studies were cited to support the partial invariance guideline (Putnick & Bornstein, 2016).

Value

a data.frame of the fit measure summary

References

Chen, F. F. (2007). Sensitivity of Goodness of Fit Indexes to Lack of Measurement Invariance. Structural Equation Modeling: A Multidisciplinary Journal, 14(3), 464–504. https://doi.org/10.1080/10705510701301834

Jöreskog, K. G. (1971). Simultaneous factor analysis in several populations. Psychometrika, 36(4), 409-426.

Putnick, D. L., & Bornstein, M. H. (2016). Measurement Invariance Conventions and Reporting: The State of the Art and Future Directions for Psychological Research. Developmental Review: DR, 41, 71–90. https://doi.org/10.1016/j.dr.2016.06.004

Rutkowski, L., & Svetina, D. (2014). Assessing the Hypothesis of Measurement Invariance in the Context of Large-Scale International Surveys. Educational and Psychological Measurement, 74(1), 31–57. https://doi.org/10.1177/0013164413498257

Steenkamp, J.-B. E. M., & Baumgartner, H. (n.d.). Assessing Measurement Invariance in Cross-National Consumer Research. JOURNAL OF CONSUMER RESEARCH, 13.

Examples

# REMEMBER, YOU MUST NAMED ALL ARGUMENT EXCEPT THE CFA ITEMS ARGUMENT
# Fitting a multiple-factor measurement invariance model by passing items.
measurement_invariance(
  x1:x3,
  x4:x6,
  x7:x9,
  data = lavaan::HolzingerSwineford1939,
  group = "school",
  invariance_level = "scalar" # you can change this to metric
)

# Fitting measurement invariance model by passing explicit lavaan model
# I am also going to only test for metric invariance instead of the default scalar invariance

measurement_invariance(
  model = "visual  =~ x1 + x2 + x3;
           textual =~ x4 + x5 + x6;
           speed   =~ x7 + x8 + x9",
  data = lavaan::HolzingerSwineford1939,
  group = "school",
  invariance_level = "metric"
)


## Not run: 
# This will fail because I did not add `model = ` in front of the lavaan model.
# Therefore,you must add the tag in front of all arguments
# For example, `return_result = 'model'` instaed of `model`
measurement_invariance(
  "visual  =~ x1 + x2 + x3;
             textual =~ x4 + x5 + x6;
             speed   =~ x7 + x8 + x9",
  data = lavaan::HolzingerSwineford1939
)

## End(Not run)

# REMEMBER, YOU MUST NAMED ALL ARGUMENT EXCEPT THE CFA ITEMS ARGUMENT
# Fitting a multiple-factor measurement invariance model by passing items.
measurement_invariance(
  x1:x3,
  x4:x6,
  x7:x9,
  data = lavaan::HolzingerSwineford1939,
  group = "school",
  invariance_level = "scalar" # you can change this to metric
)

# Fitting measurement invariance model by passing explicit lavaan model
# I am also going to only test for metric invariance instead of the default scalar invariance

measurement_invariance(
  model = "visual  =~ x1 + x2 + x3;
           textual =~ x4 + x5 + x6;
           speed   =~ x7 + x8 + x9",
  data = lavaan::HolzingerSwineford1939,
  group = "school",
  invariance_level = "metric"
)


## Not run: 
# This will fail because I did not add `model = ` in front of the lavaan model.
# Therefore,you must add the tag in front of all arguments
# For example, `return_result = 'model'` instaed of `model`
measurement_invariance(
  "visual  =~ x1 + x2 + x3;
             textual =~ x4 + x5 + x6;
             speed   =~ x7 + x8 + x9",
  data = lavaan::HolzingerSwineford1939
)

## End(Not run)

Mediation analysis A Monte Carlo simulation method to assess mediation based on Selig & Preacher (2008).

Description

Mediation analysis A Monte Carlo simulation method to assess mediation based on Selig & Preacher (2008).

Usage

mediation(
  model_med,
  model_y,
  model_med2 = NULL,
  x,
  med,
  med2 = NULL,
  mod = NULL,
  mod_stage = NULL,
  mod_level = NULL,
  conf = 95,
  rep = 20000,
  verbose = TRUE,
  digits = 3
)
mediation(
  model_med,
  model_y,
  model_med2 = NULL,
  x,
  med,
  med2 = NULL,
  mod = NULL,
  mod_stage = NULL,
  mod_level = NULL,
  conf = 95,
  rep = 20000,
  verbose = TRUE,
  digits = 3
)

Arguments

`model_med`	a fitted model object for mediator.
`model_y`	a fitted model object for outcome
`model_med2`	a fitted model object for the second mediator for serial mediation
`x`	a character string indicating the name of the independent variable used in the models.
`med`	a character string indicating the name of the mediator used in the models.
`med2`	a character string indicating the name of the second mediator used in the models (for serial mediations)
`mod`	a character string indicating the name of the moderator used in the models.
`mod_stage`	a character string specifying the stage at which the moderating effect occurs. For instance, in a first-stage moderated mediation, where the moderator influences the effect of X on the mediator (Med), set this to "model_med". In a second-stage moderated mediation, where the moderator affects the relationship between the mediator (Med) and the outcome variable (Y), set this to "model_y".#'
`mod_level`	The default is -1 SD and +1 SD for a continuous variable, and it is the two levels for a binary variable.
`conf`	level of the returned two-sided confidence intervals. Default is to return the 2.5 and 97.5 percentiles of the simulated quantities (i.e., 95%).
`rep`	number of Monte Carlo draws
`verbose`	deafult is `TRUE`.
`digits`	number of digits to round to

Value

Nothing to return. Print the indirect effect.

References

Selig, J. P., & Preacher, K. J. (2008, June). Monte Carlo method for assessing mediation: An interactive tool for creating confidence intervals for indirect effects. http://quantpsy.org/.

Examples

new_dat = iris %>% 
  dplyr::rename(x = Petal.Length) %>% 
  dplyr::rename(m = Sepal.Length) %>% 
  dplyr::rename(moderator = Sepal.Width) %>% 
  dplyr::rename(y = Petal.Width)

model_1 = lm(data = new_dat, m ~ x)
model_2 = lm(data = new_dat, y ~ x*moderator + m)


mediation(model_med = model_1,
          model_y = model_2,
          rep = 20000,
          x = 'x', 
          med = 'm',
          mod = 'moderator',
          mod_stage = 'model_y',
          digits = 3)
          
new_dat = iris %>% 
  dplyr::rename(x = Petal.Length) %>% 
  dplyr::rename(m = Sepal.Length) %>% 
  dplyr::rename(moderator = Sepal.Width) %>% 
  dplyr::rename(y = Petal.Width)

model_1 = lm(data = new_dat, m ~ x)
model_2 = lm(data = new_dat, y ~ x*moderator + m)


mediation(model_med = model_1,
          model_y = model_2,
          rep = 20000,
          x = 'x', 
          med = 'm',
          mod = 'moderator',
          mod_stage = 'model_y',
          digits = 3)

Mediation Analysis

Description

It currently only support simple mediation analysis using the path analysis approach with the lavaan package. I am trying to implement multilevel mediation in lavaan. In the future, I will try supporting moderated mediation (through lavaan or mediation) and mediation with latent variable (through lavaan).

Usage

mediation_summary(
  data,
  response_variable,
  mediator,
  predictor_variable,
  control_variable = NULL,
  group = NULL,
  standardize = TRUE,
  digits = 3,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)
mediation_summary(
  data,
  response_variable,
  mediator,
  predictor_variable,
  control_variable = NULL,
  group = NULL,
  standardize = TRUE,
  digits = 3,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)

Arguments

`data`	`data.frame`
`response_variable`	response variable. Support `dplyr::select()` syntax.
`mediator`	mediator. Support `dplyr::select()` syntax.
`predictor_variable`	predictor variable. Support `dplyr::select()` syntax.
`control_variable`	control variables / covariate. Support `dplyr::select()` syntax.
`group`	nesting variable for multilevel mediation. Not confident about the implementation method.
`standardize`	standardized coefficients. Default is `TRUE`
`digits`	number of digits to round to
`quite`	suppress printing output
`streamline`	print streamlined output
`return_result`	If it is set to `TRUE`, it will return the `lavaan` object

Value

an object from lavaan

Examples

mediation_summary(
  data = lmerTest::carrots,
  response_variable = Preference,
  mediator = Sweetness,
  predictor_variable = Crisp
)
mediation_summary(
  data = lmerTest::carrots,
  response_variable = Preference,
  mediator = Sweetness,
  predictor_variable = Crisp
)

Model Summary for Regression Models

Description

The function will extract the relevant coefficients from the regression models (see below for supported model).

Usage

model_summary(
  model,
  digits = 3,
  assumption_plot = FALSE,
  quite = FALSE,
  streamline = TRUE,
  return_result = FALSE,
  standardize = NULL,
  ci_method = "satterthwaite"
)
model_summary(
  model,
  digits = 3,
  assumption_plot = FALSE,
  quite = FALSE,
  streamline = TRUE,
  return_result = FALSE,
  standardize = NULL,
  ci_method = "satterthwaite"
)

Arguments

`model`	an model object. The following model are tested for accuracy: `lm`, `glm`, `lme`, `lmer`, `glmer`. Other model object may work if it work with parameters::model_parameters()
`digits`	number of digits to round to
`assumption_plot`	Generate an panel of plots that check major assumptions. It is usually recommended to inspect model assumption violation visually. In the background, it calls `performance::check_model()`.
`quite`	suppress printing output
`streamline`	print streamlined output. Only print model estimate and performance.
`return_result`	It set to `TRUE`, it return the model estimates data frame.
`standardize`	The method used for standardizing the parameters. Can be NULL (default; no standardization), "refit" (for re-fitting the model on standardized data) or one of "basic", "posthoc", "smart", "pseudo". See 'Details' in parameters::standardize_parameters()
`ci_method`	see options in the `⁠Mixed model⁠` section in ?parameters::model_parameters()

Value

a list of model estimate data frame, model performance data frame, and the assumption plot (an ggplot object)

References

Nakagawa, S., & Schielzeth, H. (2013). A general and simple method for obtaining R2 from generalized linear mixed-effects models. Methods in Ecology and Evolution, 4(2), 133–142. https://doi.org/10.1111/j.2041-210x.2012.00261.x

Examples

# I am going to show the more generic usage of this function
# You can also use this package's built in function to fit the models
# I recommend using the integrated_multilevel_model_summary to get everything

# lme example
lme_fit <- lme4::lmer("popular ~ texp  + (1 | class)",
  data = popular
)

model_summary(lme_fit)

# lm example

lm_fit <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width,
  data = iris
)

model_summary(lm_fit)
# I am going to show the more generic usage of this function
# You can also use this package's built in function to fit the models
# I recommend using the integrated_multilevel_model_summary to get everything

# lme example
lme_fit <- lme4::lmer("popular ~ texp  + (1 | class)",
  data = popular
)

model_summary(lme_fit)

# lm example

lm_fit <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width,
  data = iris
)

model_summary(lm_fit)

Polynomial Regression Plot

Description

The function create a simple regression plot (no interaction). Can be used to visualize polynomial regression.

Usage

polynomial_regression_plot(
  model,
  model_data = NULL,
  predictor,
  graph_label_name = NULL,
  x_lim = NULL,
  y_lim = NULL,
  plot_color = FALSE
)
polynomial_regression_plot(
  model,
  model_data = NULL,
  predictor,
  graph_label_name = NULL,
  x_lim = NULL,
  y_lim = NULL,
  plot_color = FALSE
)

Arguments

`model`	object from `lm`
`model_data`	optional dataframe (in case data cannot be retrieved from the model)
`predictor`	predictor variable name (must be character)
`graph_label_name`	vector of length 3 or function. Vector should be passed in the form of `c(response_var, predict_var1, predict_var2)`. Function should be passed as a switch function that return the label based on the name passed (e.g., a switch function)
`x_lim`	the plot's upper and lower limit for the x-axis. Length of 2. Example: `c(lower_limit, upper_limit)`
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`
`plot_color`	default if `FALSE`. Set to `TRUE` if you want to plot in color

Details

It appears that predict cannot handle categorical factors. All variables are converted to numeric before plotting.

Value

an object of class ggplot

Examples

fit = lm(data = iris, Sepal.Length ~ poly(Petal.Length,2))
polynomial_regression_plot(model = fit,predictor = 'Petal.Length')
fit = lm(data = iris, Sepal.Length ~ poly(Petal.Length,2))
polynomial_regression_plot(model = fit,predictor = 'Petal.Length')

Popular dataset

Description

Classic data-set from Chapter 2 of Joop Hox’s Multilevel Analysis (2010). The popular dataset included student from different class (i.e., class is the nesting variable). The outcome variable is a self-rated popularity scale. Individual-level (i.e., level 1) predictors are sex, extroversion. Class level (i.e., level 2) predictor is teacher experience.

Usage

popular
popular

Format

A data frame with 2000 rows and 6 variables:

pupil: Subject ID
popular: Self-rated popularity scale ranging from 1 to 10
class: the class that students belong to (nesting variable)
extrav: extraversion scale (individual-level)
sex: gender of the student (individual-level)
texp: teacher experience (class-level)

Source

http://joophox.net/mlbook2/DataExchange.zip

Reliability Analysis

Description

First, it will determine whether the data is uni-dimensional or multi-dimensional using parameters::n_factors(). If the data is uni-dimensional, then it will print a summary consists of alpha, G6, single-factor CFA, and descriptive statistics result. If it is multi-dimensional, it will print a summary consist of alpha, G6, omega result. You can bypass this by specifying the dimensionality argument.

Usage

reliability_summary(
  data,
  cols,
  dimensionality = NULL,
  digits = 3,
  descriptive_table = TRUE,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)
reliability_summary(
  data,
  cols,
  dimensionality = NULL,
  digits = 3,
  descriptive_table = TRUE,
  quite = FALSE,
  streamline = FALSE,
  return_result = FALSE
)

Arguments

`data`	`data.frame`
`cols`	items for reliability analysis. Support `dplyr::select()` syntax.
`dimensionality`	Specify the dimensionality. Either `uni` (uni-dimensionality) or `multi` (multi-dimensionality). Default is `NULL` that determines the dimensionality using EFA.
`digits`	number of digits to round to
`descriptive_table`	Get descriptive statistics. Default is `TRUE`
`quite`	suppress printing output
`streamline`	print streamlined output
`return_result`	If it is set to `TRUE` (default is `FALSE`), it will return `psych::alpha` for uni-dimensional scale, and `psych::omega` for multidimensional scale.

Value

a psych::alpha object for unidimensional scale, and a psych::omega object for multidimensional scale.

Examples


fit <- reliability_summary(data = lavaan::HolzingerSwineford1939, cols = x1:x3)
fit <- reliability_summary(data = lavaan::HolzingerSwineford1939, cols = x1:x9)
fit <- reliability_summary(data = lavaan::HolzingerSwineford1939, cols = x1:x3)
fit <- reliability_summary(data = lavaan::HolzingerSwineford1939, cols = x1:x9)

Slope Estimate at Varying Level of Moderators

Description

The function uses the interaction::sim_slopes() to calculate the slope estimate at varying level of moderators (+/- 1 SD and mean). Additionally, it will produce a Johnson-Newman plot that shows when the slope estimate is not significant

Usage

simple_slope(model, data = NULL)
simple_slope(model, data = NULL)

Arguments

`model`	model object from `lm`, `lme`,`lmer`
`data`	`data.frame`

Value

a list with the slope estimate data frame and a Johnson-Newman plot.

Examples

fit <- lm_model(
  data = iris,
  response_variable = Sepal.Length,
  predictor_variable = dplyr::everything(),
  three_way_interaction_factor = c(Sepal.Width, Petal.Width, Petal.Length)
)

simple_slope_fit <- simple_slope(
  model = fit,
)
fit <- lm_model(
  data = iris,
  response_variable = Sepal.Length,
  predictor_variable = dplyr::everything(),
  three_way_interaction_factor = c(Sepal.Width, Petal.Width, Petal.Length)
)

simple_slope_fit <- simple_slope(
  model = fit,
)

Three-way Interaction Plot

Description

The function creates a three-way interaction plot. By default, it will create an interaction plot with -1 SD and +1 SD of the two continuous variables, or the two levels of the binary variables or dummy-coded multi-categorical variable It has been superseded by interaction_plot.

Usage

three_way_interaction_plot(
  model,
  interaction_term = NULL,
  response_var_name = NULL,
  predict_var1_name = NULL,
  predict_var2_name = NULL,
  predict_var3_name = NULL,
  predict_var1_level = NULL,
  predict_var2_level = NULL,
  predict_var3_level = NULL,
  predict_var1_level_name = NULL,
  predict_var2_level_name = NULL,
  predict_var3_level_name = NULL,
  y_lim = NULL,
  plot_color = FALSE,
  return_plot_data = FALSE,
  return_plot = FALSE,
  verbose = TRUE,
  print_plot = TRUE,
  data = NULL
)
three_way_interaction_plot(
  model,
  interaction_term = NULL,
  response_var_name = NULL,
  predict_var1_name = NULL,
  predict_var2_name = NULL,
  predict_var3_name = NULL,
  predict_var1_level = NULL,
  predict_var2_level = NULL,
  predict_var3_level = NULL,
  predict_var1_level_name = NULL,
  predict_var2_level_name = NULL,
  predict_var3_level_name = NULL,
  y_lim = NULL,
  plot_color = FALSE,
  return_plot_data = FALSE,
  return_plot = FALSE,
  verbose = TRUE,
  print_plot = TRUE,
  data = NULL
)

Arguments

`model`	a regression model object from effect.
`interaction_term`	default is the first interaction term in the model. The term should be given explicitly if you want to plot other interaction terms.
`response_var_name`	The name of the response variable can be changed using this setting.
`predict_var1_name`	The name of the first predictor can be changed using this setting.
`predict_var2_name`	The name of the second predictor can be changed using this setting.
`predict_var3_name`	The name of the third predictor can be changed using this setting.
`predict_var1_level`	The default is -1 SD and +1 SD for a continuous variable, and it is the two levels for a binary variable. These can be changed using this setting.
`predict_var2_level`	The default is -1 SD and +1 SD for a continuous variable, and it is the two levels for a binary variable. These can be changed using this setting.
`predict_var3_level`	The default is -1 SD and +1 SD for a continuous variable, and it is the two levels for a binary variable. These can be changed using this setting.
`predict_var1_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the left to right on the x-axis.
`predict_var2_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the top to down on the legend.
`predict_var3_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the left to right on the facets.
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`
`plot_color`	default if `FALSE`. Set to `TRUE` if you want to plot in color
`return_plot_data`	default is `FALSE`. Set to `TRUE` to return the plot data.
`return_plot`	default is `FALSE`. Set to `TRUE` to return the plot.
`verbose`	deafult is `TRUE`.
`print_plot`	default is `TRUE`. Set to `TRUE` to print the plot.
`data`	Optional data.frame. Only used when it is not possible to extract data from the model object.

Value

an object of class ggplot

Two-way Interaction Plot

Description

Usage

two_way_interaction_plot(
  model,
  interaction_term = NULL,
  response_var_name = NULL,
  predict_var1_name = NULL,
  predict_var2_name = NULL,
  predict_var1_level = NULL,
  predict_var2_level = NULL,
  predict_var1_level_name = NULL,
  predict_var2_level_name = NULL,
  y_lim = NULL,
  plot_color = FALSE,
  return_plot_data = FALSE,
  return_plot = FALSE,
  verbose = FALSE,
  print_plot = TRUE,
  data = NULL
)
two_way_interaction_plot(
  model,
  interaction_term = NULL,
  response_var_name = NULL,
  predict_var1_name = NULL,
  predict_var2_name = NULL,
  predict_var1_level = NULL,
  predict_var2_level = NULL,
  predict_var1_level_name = NULL,
  predict_var2_level_name = NULL,
  y_lim = NULL,
  plot_color = FALSE,
  return_plot_data = FALSE,
  return_plot = FALSE,
  verbose = FALSE,
  print_plot = TRUE,
  data = NULL
)

Arguments

`model`	a regression model object from effect.
`interaction_term`	default is the first interaction term in the model. The term should be given explicitly if you want to plot other interaction terms.
`response_var_name`	The name of the response variable can be changed using this value.
`predict_var1_name`	The name of the first predictor can be changed using this value.
`predict_var2_name`	The name of the second predictor can be changed using this value.
`predict_var1_level`	default is the -1 SD and +1 SD for continuous variable. They can be changed using this value.
`predict_var2_level`	default is the -1 SD and +1 SD for continuous variable. They can be changed using this value.
`predict_var1_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the left to right on the x-axis.
`predict_var2_level_name`	The labels of the level can be change using this value (e.g., `c('-1 SD','+1 SD')`). The order should be from the top to down on the legend.
`y_lim`	the plot's upper and lower limit for the y-axis. Length of 2. Example: `c(lower_limit, upper_limit)`
`plot_color`	default if `FALSE`. Set to `TRUE` if you want to plot in color
`return_plot_data`	default is `FALSE`. Set to `TRUE` to return the plot data.
`return_plot`	default is `FALSE`. Set to `TRUE` to return the plot.
`verbose`	deafult is `TRUE`.
`print_plot`	default is `TRUE`. Set to `TRUE` to print the plot.
`data`	Optional data.frame. Only used when it is not possible to extract data from the model object.

Details

It appears that “predict' cannot handle categorical factors. All variables are converted to numeric before plotting.

Value

an object of class ggplot

Package 'psycModel'

Help Index

Acitelli

Description

Usage

Format

Source

ANOVA Plot

Description

Usage

Arguments

Value

Examples

APIM Actor-Partner Interdependence Model (SEM)

Description

Usage

Arguments

Details

Value

References

Examples

APIM Actor-Partner Interdependence Model Table with Multiple Moderators

Description

Usage

Arguments

Value

Examples

Confirmatory Factor Analysis (groupwise)

Description

Usage

Arguments

Details

Value

Examples

Confirmatory Factor Analysis

Description

Usage

Arguments

Details

Value

References

Examples

Comparison of Model Fit

Description

Usage

Arguments

Value

Examples

Correlation table

Description

Usage

Arguments

Value

Examples

Cronbach alpha

Description

Usage

Arguments

Value

Examples

Descriptive Statistics Table

Description

Usage

Arguments

Value

Examples

Exploratory Factor Analysis

Description

Usage

Arguments

Value

Examples

get interaction term

Description

Usage

Arguments

Value

get factor df to combine with mean_df

Description

Usage