Package 'dySEM'

Description

Creates a dvn structure for use with dySEM population scripters and simulation workflows. Variable names are generated directly from naming conventions without requiring an actual data frame. Compatible with scrapeVarCross naming patterns.

Usage

build_dvn(
  n_items_x,
  x_order = "sip",
  x_stem = "x",
  x_delim1 = "",
  x_delim2 = "_",
  distinguish_1 = "A",
  distinguish_2 = "B",
  n_items_y = NULL,
  y_order = NULL,
  y_stem = NULL,
  y_delim1 = NULL,
  y_delim2 = NULL
)

Arguments

Value

A list compatible with dySEM dvn structure:

See Also

Other variable-scraping functions: scrapeVarCross()

Examples

dvn <- build_dvn(
  n_items_x = 3,
  x_order = "sip",
  x_stem = "x",
  x_delim1 = "",
  x_delim2 = "_",
  distinguish_1 = "A",
  distinguish_2 = "B"
)
# Produces x1_A, x2_A, x3_A and x1_B, x2_B, x3_B

Description

A data set containing 5 ratings of satisfaction and 5 ratings of commitment for each member of a mixed-sex romantic dyad. Measured using the Investment Model Scale subscales (Rusbult, Martz, & Agnew, 1998). Data are from Sakaluk, Fisher, and Kilshaw's (2021) study of dyadic invariance. Variable names have been re-coded to follow a stem-item-partner ("sip") order, with a delimiter ("_") between the item number and partner distinguishing character.

Usage

data(commitmentM)

Format

A data frame with 282 rows and 20 variables:

sat.g1_f

Satisfaction item 1 for female partner

sat.g2_f

Satisfaction item 2 for female partner

sat.g3_f

Satisfaction item 3 for female partner

sat.g4_f

Satisfaction item 4 for female partner

sat.g5_f

Satisfaction item 5 for female partner

com1_f

Commitment items item 1 for female partner

com2_f

Commitment items item 2 for female partner

com3_f

Commitment items item 3 for female partner

com4_f

Commitment items item 4 for female partner

com5_f

Commitment items item 5 for female partner

sat.g1_m

Satisfaction item 1 for male partner

sat.g2_m

Satisfaction item 2 for male partner

sat.g3_m

Satisfaction item 3 for male partner

sat.g4_m

Satisfaction item 4 for male partner

sat.g5_m

Satisfaction item 5 for male partner

com1_m

Commitment items item 1 for male partner

com2_m

Commitment items item 2 for male partner

com3_m

Commitment items item 3 for male partner

com4_m

Commitment items item 4 for male partner

com5_m

Commitment items item 5 for male partner

References

Sakaluk, J. K., Fisher, A. N., & Kilshaw, R. E.(2021). Dyadic measurement invariance and its importance for replicability in romantic relationship research. Personal Relationships, 28(1), 190-226. .

Description

A data set containing 5 ratings of satisfaction and 5 ratings of commitment for each member of a dyad in which one or more members identify as LGBTQ+. Measured using the Investment Model Scale subscales (Rusbult, Martz, & Agnew, 1998). Data are from Sakaluk, Fisher, and Kilshaw (2021). Variable names follow a stem-partner-item ("spi") order, with a delimiter (".") between the stem and distinguishing partner character, and another delimiter ("_") between the distinguishing partner character and item number.

Usage

data(commitmentQ)

Format

A data frame with 118 rows and 20 variables:

sat.g.1_1

Satisfaction item 1 for partner1

sat.g.1_2

Satisfaction item 2 for partner1

sat.g.1_3

Satisfaction item 3 for partner1

sat.g.1_4

Satisfaction item 4 for partner1

sat.g.1_5

Satisfaction item 5 for partner1

com.1_1

Commitment items item 1 for partner1

com.1_2

Commitment items item 2 for partner1

com.1_3

Commitment items item 3 for partner1

com.1_4

Commitment items item 4 for partner1

com.1_5

Commitment items item 5 for partner1

sat.g.2_1

Satisfaction item 1 for partner 2

sat.g.2_2

Satisfaction item 2 for partner 2

sat.g.2_3

Satisfaction item 3 for partner 2

sat.g.2_4

Satisfaction item 4 for partner 2

sat.g.2_5

Satisfaction item 5 for partner 2

com.2_1

Commitment items item 1 for partner 2

com.2_2

Commitment items item 2 for partner 2

com.2_3

Commitment items item 3 for partner 2

com.2_4

Commitment items item 4 for partner 2

com.2_5

Commitment items item 5 for partner 2

References

Sakaluk, J. K., Fisher, A. N., & Kilshaw, R. E.(2021). Dyadic measurement invariance and its importance for replicability in romantic relationship research. Personal Relationships, 28(1), 190-226. .#'

Description

A dataset containing 9 observed indicators of relationship quality (PRQC) and 5 observed indicators of sexual satisfaction from 121 couples in the DRES (Daily Relationship Experiences Study; Raposo, Impett, & Muise, 2020)

Usage

data(DRES)

Format

A data frame with 121 rows and 28 variables:

PRQC_1.1

PRQC item 1 for partner 1

PRQC_2.1

PRQC item 2 for partner 1

PRQC_3.1

PRQC item 3 for partner 1

PRQC_4.1

PRQC item 4 for partner 1

PRQC_5.1

PRQC item 5 for partner 1

PRQC_6.1

PRQC item 6 for partner 1

PRQC_7.1

PRQC item 7 for partner 1

PRQC_8.1

PRQC item 8 for partner 1

PRQC_9.1

PRQC item 9 for partner 1

PRQC_1.2

PRQC item 1 for partner 2

PRQC_2.2

PRQC item 2 for partner 2

PRQC_3.2

PRQC item 3 for partner 2

PRQC_4.2

PRQC item 4 for partner 2

PRQC_5.2

PRQC item 5 for partner 2

PRQC_6.2

PRQC item 6 for partner 2

PRQC_7.2

PRQC item 7 for partner 2

PRQC_8.2

PRQC item 8 for partner 2

PRQC_9.2

PRQC item 9 for partner 2

sexsat1.1

sexual satisfaction item 1 for partner 1

sexsat2.1

sexual satisfaction item 2 for partner 1

sexsat3.1

sexual satisfaction item 3 for partner 1

sexsat4.1

sexual satisfaction item 4 for partner 1

sexsat5.1

sexual satisfaction item 5 for partner 1

sexsat1.2

sexual satisfaction item 1 for partner 2

sexsat2.2

sexual satisfaction item 2 for partner 2

sexsat3.2

sexual satisfaction item 3 for partner 2

sexsat4.2

sexual satisfaction item 4 for partner 2

sexsat5.2

sexual satisfaction item 5 for partner 2

References

Raposo, S., Impett, E. A., & Muise, A. (2020). Avoidantly Attached Individuals Are More Exchange‐Oriented and Less Communal in the Bedroom. Archives of Sexual Behavior, 49, 2863–2881. https://doi.org/10.1007/s10508-020-01813-9

Description

A function that performs a score test for relaxing each invariance equality constraint between partners in a given dyadic SEM model.

Usage

getConstraintTests(constrainFit, filterSig = FALSE)

Arguments

Value

a data frame with rows of equality constraints (now with readable param labels) and test statistic, df, and p for whether constraint worsens model fit

Examples

dvn <- scrapeVarCross(dat = commitmentM, x_order = "sip", x_stem = "sat.g",
x_delim2="_", distinguish_1="f", distinguish_2="m")

sat.resids.script <- scriptCor(dvn, lvname = "Sat",
constr_dy_meas = c("loadings", "intercepts", "residuals"),
constr_dy_struct = "none")

sat.resids.mod <- lavaan::cfa(sat.resids.script, data = commitmentM, std.lv = FALSE,
auto.fix.first= FALSE, meanstructure = TRUE)

getConstraintTests(sat.resids.mod)

Description

Calculates dmacs difference in expected indicator scores for between dyad members

Usage

getDydmacs(dat, dvn, fit, nodewidth = 0.01, lowerLV = -5, upperLV = 5)

Arguments

Value

For single LV models: a matrix with one column "dMACS" containing d_macs values. For multiple LV models: a named list of matrices, where each element corresponds to one LV and contains a matrix with one column "dMACS" containing d_macs values for that LV.

See Also

Other supplemental model calculators: getDyReliability(), getIndistFit()

Examples

dvn <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2")
sat.config.script <- scriptCor(dvn, lvname = "Sat",
constr_dy_meas = "none",
constr_dy_struct = "none")

sat.config.mod <- lavaan::cfa(sat.config.script, data = commitmentQ, std.lv = FALSE,
auto.fix.first= FALSE, meanstructure = TRUE)
getDydmacs(commitmentQ, dvn, sat.config.mod)

Description

This function takes the model from fitted scriptCor() scripts and returns omega total coefficients for each dyad member, adapted following Formula 2 in McNeish (2018).

Usage

getDyReliability(dvn, fit)

Arguments

Value

a tibble/data frame with calculated omega total coefficients for dyad Member 1 and Member 2

See Also

Other supplemental model calculators: getDydmacs(), getIndistFit()

Examples

dvn <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2")
sat.indist.script <-  scriptCor(dvn, lvname = "Sat")
sat.indist.mod <- lavaan::cfa(sat.indist.script, data = commitmentQ, std.lv = FALSE,
auto.fix.first= FALSE, meanstructure = TRUE)
getDyReliability(dvn, sat.indist.mod)

Description

This function takes the outputted model fit using scriptCor() with model = "indist", as well as scriptISAT(), and scriptINULL() and computes corrected model fit indexes according to the approach outlined by Olsen & Kenny (2006)

Usage

getIndistFit(indmodel, isatmod, inullmod)

Arguments

Value

A data frame of the original and corrected chi sq, df, p, rmsea, and tli

See Also

Other supplemental model calculators: getDyReliability(), getDydmacs()

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2"
)

sat.indist.script <- scriptCor(dvn, lvname = "Sat")
sat.indist.mod <- lavaan::cfa(sat.indist.script,
  data = commitmentQ, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = TRUE
)

sat.isat.script <- scriptISAT(dvn, lvxname = "Sat")
sat.isat.mod <- lavaan::cfa(sat.isat.script,
  data = commitmentQ, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = FALSE
)

sat.inull.script <- scriptINULL(dvn, lvxname = "Sat")
sat.inull.mod <- lavaan::cfa(sat.inull.script,
  data = commitmentQ, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = FALSE
)

getIndistFit(sat.indist.mod, sat.isat.mod, sat.inull.mod)

Description

Compare model fit of nested dyadic invariance models in order from most parsimonious (residual) to least parsimonious (configural)

Usage

getInvarCompTable(mods)

Arguments

Value

a data frame of model fit statistics for each model, as well as the difference in fit statistics between each model and the previous model

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi",
  x_stem = "sat.g", x_delim1 = ".", x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2"
)

sat.residual.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts", "residuals"), constr_dy_struct = "none"
)

sat.intercept.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts"), constr_dy_struct = "none"
)

sat.loading.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = c("loadings"), constr_dy_struct = "none"
)

sat.config.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = "none", constr_dy_struct = "none"
)

sat.residual.fit <- lavaan::cfa(sat.residual.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

sat.intercept.fit <- lavaan::cfa(sat.intercept.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

sat.loading.fit <- lavaan::cfa(sat.loading.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

sat.config.fit <- lavaan::cfa(sat.config.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

mods <- list(sat.residual.fit, sat.intercept.fit, sat.loading.fit, sat.config.fit)

getInvarCompTable(mods)

Description

A data set containing 5 ratings for each of (1) satisfaction, (2) quality of alternatives, (3) investment, and 4 (commitment) for each member of a mixed-sex romantic dyad. Measured using the Investment Model Scale subscales (Rusbult, Martz, & Agnew, 1998). Data are from Sakaluk, Fisher, and Kilshaw's (2021) study of dyadic invariance. Variable names have been re-coded to follow a stem-item-partner ("sip") order, with a delimiter ("_") between the item number and partner distinguishing character.

Usage

data(imsM)

Format

A data frame with 282 rows and 40 variables:

sat.g1_f

Satisfaction item 1 for female partner

sat.g2_f

Satisfaction item 2 for female partner

sat.g3_f

Satisfaction item 3 for female partner

sat.g4_f

Satisfaction item 4 for female partner

sat.g5_f

Satisfaction item 5 for female partner

qalt.g1_f

Quality of alternatives item 1 for female partner

qalt.g2_f

Quality of alternatives item 2 for female partner

qalt.g3_f

Quality of alternatives item 3 for female partner

qalt.g4_f

Quality of alternatives item 4 for female partner

qalt.g5_f

Quality of alternatives item 5 for female partner

invest.g1_f

Investment item 1 for female partner

invest.g2_f

Investment item 2 for female partner

invest.g3_f

Investment item 3 for female partner

invest.g4_f

Investment item 4 for female partner

invest.g5_f

Investment item 5 for female partner

com1_f

Commitment items item 1 for female partner

com2_f

Commitment items item 2 for female partner

com3_f

Commitment items item 3 for female partner

com4_f

Commitment items item 4 for female partner

com5_f

Commitment items item 5 for female partner

sat.g1_m

Satisfaction item 1 for male partner

sat.g2_m

Satisfaction item 2 for male partner

sat.g3_m

Satisfaction item 3 for male partner

sat.g4_m

Satisfaction item 4 for male partner

sat.g5_m

Satisfaction item 5 for male partner

qalt.g1_m

Quality of alternatives item 1 for male partner

qalt.g2_m

Quality of alternatives item 2 for male partner

qalt.g3_m

Quality of alternatives item 3 for male partner

qalt.g4_m

Quality of alternatives item 4 for male partner

qalt.g5_m

Quality of alternatives item 5 for male partner

invest.g1_m

Investment item 1 for male partner

invest.g2_m

Investment item 2 for male partner

invest.g3_m

Investment item 3 for male partner

invest.g4_m

Investment item 4 for male partner

invest.g5_m

Investment item 5 for male partner

com1_m

Commitment items item 1 for male partner

com2_m

Commitment items item 2 for male partner

com3_m

Commitment items item 3 for male partner

com4_m

Commitment items item 4 for male partner

com5_m

Commitment items item 5 for male partner

References

Sakaluk, J. K., Fisher, A. N., & Kilshaw, R. E.(2021). Dyadic measurement invariance and its importance for replicability in romantic relationship research. Personal Relationships, 28(1), 190-226. .

Description

Opens a Shiny application that guides researchers through selecting a dyadic model, configuring invariance constraints and variable naming patterns, previewing a path diagram, and generating the corresponding lavaan syntax.

Usage

launchScripter(launch.browser = TRUE)

Arguments

Details

The app supports uni-construct (unidimensional, correlated, hierarchical, bifactor), bi-construct (L-APIM, Common Fate, Mutual Influence, Two-Construct), and multi-construct (multiple correlated factors) models.

No data upload is required. The app constructs variable names from naming patterns you specify, generates lavaan syntax via dySEM scripters, and provides a path diagram preview, copy-to-clipboard, download, and reproducible R code.

Requires the shiny, bslib, and shinyjs packages (listed in Suggests).

Value

Called for its side effect (launching the app). Returns the value from runApp invisibly.

Examples

## Not run: 
launchScripter()

## End(Not run)

Description

outputConstraintTab() is used to perform a score test for relaxing each invariance equality constraint between partners in a given dyadic SEM model.

Usage

outputConstraintTab(
  constrainFit,
  filterSig = FALSE,
  gtTab = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Details

• If gtTab = TRUE and writeTo is specified, then output will simultaneously be saved as a .rtf file to the user's specified directory.

• If output file is successfully saved, a confirmation message will be printed to the console.

• If a file with the same name already exists in the user's chosen directory, it will be overwritten.

Value

A tibble::tibble() if gtTab = FALSE (default), or gt::gt() object if gtTab = TRUE, with rows of equality constraints (now with readable param labels) and test statistic, df, and p for whether constraint worsens model fit.

Examples

dvn <- scrapeVarCross(
  dat = commitmentM, x_order = "sip", x_stem = "sat.g",
  x_delim2 = "_", distinguish_1 = "f", distinguish_2 = "m"
)

sat.resids.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none"
)

sat.resids.mod <- lavaan::cfa(sat.resids.script,
  data = commitmentM, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = TRUE
)

outputConstraintTab(sat.resids.mod,
  filterSig = FALSE,
  gtTab = TRUE, writeTo = tempdir(), fileName = "dCFA_Residual"
)

Description

outputInvarCompTab() is used to compare the model fit of nested dyadic invariance models in order from most parsimonious (residual) to least parsimonious (configural)

Usage

outputInvarCompTab(
  mods,
  parsimonyFirst = FALSE,
  gtTab = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Details

• If gtTab = TRUE and writeTo is specified, then output will simultaneously be saved as a .rtf file to the user's specified directory.

• If output file is successfully saved, a confirmation message will be printed to the console.

• If a file with the same name already exists in the user's chosen directory, it will be overwritten.

Value

A tibble::tibble() if gtTab = FALSE (default), or gt::gt() object if gtTab = TRUE, of model fit statistics for each model, as well as the difference in fit statistics between each model and the previous model

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi",
  x_stem = "sat.g", x_delim1 = ".", x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2"
)

sat.residual.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts", "residuals"), constr_dy_struct = "none"
)

sat.intercept.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts"), constr_dy_struct = "none"
)

sat.loading.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = c("loadings"), constr_dy_struct = "none"
)

sat.config.script <- scriptCor(dvn,
  lvname = "Sat",
  constr_dy_meas = "none", constr_dy_struct = "none"
)

sat.residual.fit <- lavaan::cfa(sat.residual.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

sat.intercept.fit <- lavaan::cfa(sat.intercept.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

sat.loading.fit <- lavaan::cfa(sat.loading.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

sat.config.fit <- lavaan::cfa(sat.config.script,
  data = commitmentQ,
  std.lv = FALSE, auto.fix.first = FALSE, meanstructure = TRUE
)

mods <- list(sat.residual.fit, sat.intercept.fit, sat.loading.fit, sat.config.fit)

outputInvarCompTab(mods,
  parsimonyFirst = FALSE,
  gtTab = TRUE, writeTo = tempdir(), fileName = "dCFA_Invar_Standard"
)

mods <- list(sat.config.fit, sat.loading.fit, sat.intercept.fit, sat.residual.fit)

outputInvarCompTab(mods,
  parsimonyFirst = TRUE,
  gtTab = TRUE, writeTo = tempdir(), fileName = "dCFA_Invar_Reverse"
)

Description

outputInvarItem() generates a summary table showing which items exhibit noninvariance in loadings and/or intercepts based on a partial invariance model script, along with dMACS effect sizes for each item.

Usage

outputInvarItem(
  dvn,
  fit,
  partialScript,
  dat,
  nodewidth = 0.01,
  lowerLV = -5,
  upperLV = 5,
  gtTab = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Details

• The function parses the lavaan syntax to determine which loadings and intercepts are constrained to equality across partners (invariant) versus freed (noninvariant).

• LoadingNoninvariance = "Yes" indicates the loading was freed in the partial invariance model.

• InterceptNoninvariance = "Yes" indicates the intercept was freed in the partial invariance model.

• dMACS values are calculated using the getDydmacs() function.

• If gtTab = TRUE and writeTo is specified, then output will simultaneously be saved as a .rtf file to the user's specified directory.

• If output file is successfully saved, a confirmation message will be printed to the console.

• If a file with the same name already exists in the user's chosen directory, it will be overwritten.

Value

A tibble::tibble() if gtTab = FALSE (default), or gt::gt() object if gtTab = TRUE, with columns for Item, LoadingNoninvariance, InterceptNoninvariance, and dMACS. For multi-LV structures, an additional LV column is included; in gt tables, this is used as the row group label with Item names as row labels within each group.

Examples

## Not run: 
dvn <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
                      x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2")

# Create and fit a partial invariance model
partial.script <- scriptCor(dvn, lvname = "Sat",
                            constr_dy_meas = c("loadings", "intercepts"),
                            constr_dy_struct = "none")

partial.fit <- lavaan::cfa(partial.script, data = commitmentQ, std.lv = FALSE,
                           auto.fix.first = FALSE, meanstructure = TRUE)

outputInvarItem(dvn, partial.fit, partial.script, dat = commitmentQ,
                gtTab = TRUE, writeTo = tempdir(), fileName = "item_invar")

## End(Not run)

Description

This function takes the model from fitted dySEM() scripts and exports table(s) and/or a path diagram figure of expected output.

Usage

outputModel(
  dvn,
  model = NULL,
  fit,
  table = TRUE,
  tabletype = NULL,
  figure = TRUE,
  figtype = NULL,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Details

If a file with the same name already exists in the user's chosen directory, it will be overwritten.

Value

Ignore console (prints unnecessary semPlot::semPaths details). More importantly, prints word files for the table(s) and/or figure, outputted to the users working directory

Examples

dvnx <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2")

sat.config.script <- scriptCor(dvnx, lvname = "Sat", constr_dy_meas = "none",
constr_dy_struct = "none")

sat.config.mod <- lavaan::cfa(sat.config.script, data = commitmentQ, std.lv = FALSE,
auto.fix.first= FALSE, meanstructure = TRUE)

outputModel(dvnx, model = "cfa", fit = sat.config.mod, table = TRUE,
tabletype = "measurement", figure = "TRUE", figtype = "standardized",
writeTo = tempdir(), fileName = "dCFA_configural")
dvnxy <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2",
y_order="spi", y_stem="com", y_delim1 = ".", y_delim2="_")

apim.indist.script <-  scriptAPIM(dvnxy, lvxname = "Sat", lvyname = "Com", est_k = TRUE)

apim.indist.mod <- lavaan::cfa(apim.indist.script, data = commitmentQ, std.lv = FALSE,
auto.fix.first= FALSE, meanstructure = TRUE)

outputModel(dvnxy, model = "apim", fit = apim.indist.mod, table = TRUE,
tabletype = "measurement", figure = "TRUE", figtype = "standardized",
writeTo = tempdir(), fileName = "APIM_indist")

Description

This function takes the model from fitted dySEM scripts and exports .png path diagram figures of expected output.

Usage

outputParamFig(fit, figtype = NULL, writeTo = NULL, fileName = NULL)

Arguments

Details

• The function uses semPlot::semPaths() to create a qgraph object of the desired SEM path diagram.

• After execution, a semPlot::semPaths() message will be printed to the console confirming the directory path of the saved output file.

• If a file with the same name already exists in the user's chosen directory, it will be overwritten.

Value

A qgraph object of the desired SEM path diagram, which is simultaneously exported as a .png file to the specified directory.

Examples

dvnx <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2"
)

sat.config.script <- scriptCor(dvnx,
  lvname = "Sat", constr_dy_meas = "none",
  constr_dy_struct = "none"
)

sat.config.mod <- lavaan::cfa(sat.config.script,
  data = commitmentQ, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = TRUE
)

outputParamFig(sat.config.mod,
  figtype = "standardized",
  writeTo = tempdir(), fileName = "dCFA_configural"
)

dvnxy <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2",
  y_order = "spi", y_stem = "com", y_delim1 = ".", y_delim2 = "_"
)

apim.indist.script <- scriptAPIM(dvnxy, lvxname = "Sat", lvyname = "Com", est_k = TRUE)

apim.indist.mod <- lavaan::cfa(apim.indist.script,
  data = commitmentQ, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = TRUE
)

outputParamFig(apim.indist.mod,
  figtype = "standardized",
  writeTo = tempdir(), fileName = "APIM_indist"
)

Description

This function takes the model from fitted dySEM scripts and creates tables of expected output and/or exports them as .rtfs.

Usage

outputParamTab(
  dvn,
  model = NULL,
  fit,
  tabletype = NULL,
  gtTab = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Details

• If gtTab = TRUE and writeTo is specified, then output will simultaneously be saved as a .rtf file to the user's specified directory.

• If output file(s) is(are) successfully saved, a confirmation message will be printed to the console.

• If a file with the same name already exists in the user's chosen directory, it will be overwritten.

Value

A tibble::tibble() if gtTab = FALSE (default), or gt::gt() object if gtTab = TRUE, of specified model parameter estimates and corresponding statistical tests.

Examples

dvnx <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2"
)

sat.config.script <- scriptCor(dvnx,
  lvname = "Sat", constr_dy_meas = "none",
  constr_dy_struct = "none"
)

sat.config.mod <- lavaan::cfa(sat.config.script,
  data = commitmentQ, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = TRUE
)

outputParamTab(dvnx,
  model = "cfa", sat.config.mod, tabletype = "measurement",
  writeTo = tempdir(), fileName = "dCFA_configural"
)

dvnxy <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2",
  y_order = "spi", y_stem = "com", y_delim1 = ".", y_delim2 = "_"
)

apim.indist.script <- scriptAPIM(dvnxy, lvxname = "Sat", lvyname = "Com", est_k = TRUE)

apim.indist.mod <- lavaan::cfa(apim.indist.script,
  data = commitmentQ, std.lv = FALSE,
  auto.fix.first = FALSE, meanstructure = TRUE
)

outputParamTab(dvnxy,
  model = "cfa", sat.config.mod, tabletype = "measurement",
  writeTo = tempdir(), fileName = "APIM_indist"
)

Description

This function takes the outputted object from scrapeVarCross() along with the corresponding dataset and automatically tests competing uni-construct dyadic models for the latent variable under consideration. It inspects four possible model variants:

• Bifactor (scripted via dySEM::scriptBifac)

• Hierarchical (scripted via dySEM::scriptHier)

• Correlated Factors (scripted via dySEM::scriptCor)

• Unidimensional (scripted via dySEM::scriptUni)

Usage

outputUniConstructComp(
  dvn,
  dat,
  indexes = c("df", "chisq", "cfi", "rmsea", "bic", "GenTEFI"),
  ...,
  gtTab = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Details

• If "chisq" is included in indexes, the specific form of the applied chi-squared difference test (e.g., standard vs. robust) is determined automatically by lavaan::lavTestLRT(), based on the model estimation method used.

• If gtTab = TRUE and writeTo is specified, then output will simultaneously be saved as a .rtf file to the user's specified directory.

• If output file is successfully saved, a confirmation message will be printed to the console.

• If a file with the same name already exists in the user's chosen directory, it will be overwritten.

Value

A list containing up to two components:

• Indexes: A tibble::tibble() if gtTab = FALSE (default), or gt::gt() object if gtTab = TRUE, with the desired index(es) for each fitted model (requested via the indexes argument).

• GenTEFI: A tibble::tibble() of the GenTEFI (if "GenTEFI" is included in the indexes argument).

Examples

dvn <- scrapeVarCross(
commitmentM,
x_order = "sip",
x_stem = "sat.g",
x_delim1 = "",
x_delim2 = "_",
distinguish_1 = "f",
distinguish_2 = "m"
)

# Quick example for CRAN checks
outputUniConstructComp(
  dvn,
  commitmentM,
  indexes = c("df", "bic"),
  missing = "listwise"
)


# More comprehensive examples (slower due to FIML estimation)
outputUniConstructComp(
  dvn,
  commitmentM,
  missing = "fiml"
)

outputUniConstructComp(
  dvn,
  commitmentM,
  indexes = c("df", "bic"),
  missing = "fiml"
)

outputUniConstructComp(
  dvn,
  commitmentM,
  indexes = c("df", "bic"),
  estimator = "ml",
  missing = "fiml"
)

outputUniConstructComp(
  dvn,
  commitmentM,
  indexes = c("df", "bic"),
  missing = "fiml",
  gtTab = TRUE,
  writeTo = tempdir(),
  fileName = "uni-construct-dyad-models"
)

Description

A data set containing ratings on items (4 each) assessing romantic (1) satisfaction and (2) dissatisfaction for each member of a mixed-sex dyad . Positive-Negative Relationship Quality Scale (Rogge et al., 2017). Data are from Prine et al. (Under Review). Variable names follow a stem-item-partner ("sip") order, with a delimiter ("_") between the item number and distinguishing partner character.

Usage

data(pnrqM)

Format

A data frame with 219 rows and 16 variables. Participants responded–on a six-point scale (1 = "Not at all true", 6 = "Completely true")–to the prompt, "My relationship is...":

sat.pnrq1_w

Enjoyable for partner w

sat.pnrq2_w

Pleasant for partner w

sat.pnrq3_w

Strong for partner w

sat.pnrq4_w

Alive for partner w

dsat.pnrq1_w

Miserable for partner w

dsat.pnrq2_w

Bad for partner w

dsat.pnrq3_w

Empty for partner w

dsat.pnrq4_w

Lifeless for partner w

sat.pnrq1_m

Enjoyable for partner m

sat.pnrq2_m

Pleasant for partner m

sat.pnrq3_m

Strong for partner m

sat.pnrq4_m

Alive for partner m

dsat.pnrq1_m

Miserable for partner m

dsat.pnrq2_m

Bad for partner m

dsat.pnrq3_m

Empty for partner m

dsat.pnrq4_m

Lifeless for partner m

References

Prine, M., Sakaluk, J. K., Camanto, O. J., & Quinn-Nilas, C. (Under Review).

Description

A data set containing ratings on items (3 each) assessing romantic: (1) satisfaction, (2) commitment, (3) intimacy, (4) trust, (5) passion, and (6) love for each member of a dyad in which one or more members identify as LGBTQ+. Perceived Relationship Quality Components (PRQC) Inventory (Fletcher, Simpson, & Thomas, 2000). Data are from Sakaluk, Fisher, and Kilshaw (2021). Variable names follow a stem-partner-item ("spi") order, with a delimiter (".") between the stem and distinguishing partner character, and another delimiter ("_") between the distinguishing partner character and item number.

Usage

data(prqcQ)

Format

A data frame with 118 rows and 36 variables:

prqc.1_1

Satisfaction item 1 for partner 1

prqc.1_2

Satisfaction item 2 for partner 1

prqc.1_3

Satisfaction item 3 for partner 1

prqc.1_4

Commitment item 1 for partner 1

prqc.1_5

Commitment item 2 for partner 1

prqc.1_6

Commitment item 3 for partner 1

prqc.1_7

Intimacy item 1 for partner 1

prqc.1_8

Intimacy item 2 for partner 1

prqc.1_9

Intimacy item 3 for partner 1

prqc.1_10

Trust item 1 for partner 1

prqc.1_11

Trust item 2 for partner 1

prqc.1_12

Trust item 3 for partner 1

prqc.1_13

Passion item 1 for partner 1

prqc.1_14

Passion item 2 for partner 1

prqc.1_15

Passion item 3 for partner 1

prqc.1_16

Love item 1 for partner 1

prqc.1_17

Love item 2 for partner 1

prqc.1_18

Love item 3 for partner 1

prqc.2_1

Satisfaction item 1 for partner 2

prqc.2_2

Satisfaction item 2 for partner 2

prqc.2_3

Satisfaction item 3 for partner 2

prqc.2_4

Commitment item 1 for partner 2

prqc.2_5

Commitment item 2 for partner 2

prqc.2_6

Commitment item 3 for partner 2

prqc.2_7

Intimacy item 1 for partner 2

prqc.2_8

Intimacy item 2 for partner 2

prqc.2_9

Intimacy item 3 for partner 2

prqc.2_10

Trust item 1 for partner 2

prqc.2_11

Trust item 2 for partner 2

prqc.2_12

Trust item 3 for partner 2

prqc.2_13

Passion item 1 for partner 2

prqc.2_14

Passion item 2 for partner 2

prqc.2_15

Passion item 3 for partner 2

prqc.2_16

Love item 1 for partner 2

prqc.2_17

Love item 2 for partner 2

prqc.2_18

Love item 3 for partner 2

References

Sakaluk, J. K., Fisher, A. N., & Kilshaw, R. E.(2021). Dyadic measurement invariance and its importance for replicability in romantic relationship research. Personal Relationships, 28(1), 190-226. .#'

Description

This function scrapes the names of indicator variables in a wide-format data set used for dyadic analyses of two latent variables (LV; X and Y), and indexes which indicators correspond to which partner, for which LV. It is used primarily to guide the syntax-writing of the other dySEM functions.

Usage

scrapeVarCross(
  dat,
  x_order = "spi",
  x_stem,
  x_delim1 = NULL,
  x_delim2 = NULL,
  x_item_num = "\\d+",
  distinguish_1 = "1",
  distinguish_2 = "2",
  y_order = NULL,
  y_stem = NULL,
  y_delim1 = NULL,
  y_delim2 = NULL,
  y_item_num = "\\d+",
  var_list = NULL,
  var_list_order = NULL,
  var_list_item_num = "\\d+",
  group = NULL,
  covs_order = NULL,
  covs_stem = NULL,
  covs_delim1 = NULL,
  covs_delim2 = NULL,
  verbose = TRUE
)

Arguments

Value

a list, referred in short-hand as a "dvn" (dyad variable names list) containing variable names for p1, p2, # of items per LV, characters distinguishing partners, and total number of indicators

See Also

Other variable-scraping functions: build_dvn()

Examples

dvnx <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2"
)
dvnxy <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2",
  y_order = "spi", y_stem = "com", y_delim1 = ".", y_delim2 = "_"
)

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan() syntax for specifying Actor-Partner Interdependence Models (APIMs). Users can also invoke configural, loading, and/or intercept invariant measurement models, and particular types of structural comparisons.

Usage

scriptAPIM(
  dvn,
  scaleset = "FF",
  lvxname,
  lvyname,
  constr_dy_x_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_x_struct = c("variances", "means"),
  constr_dy_y_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_y_struct = c("variances", "means"),
  constr_dy_xy_struct = c("actors", "partners"),
  includeMeanStruct = FALSE,
  model = lifecycle::deprecated(),
  equate = lifecycle::deprecated(),
  est_k = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

character object of lavaan script that can be passed immediately to lavaan functions. Users will receive message if structural comparisons are specified when the recommended level of invariance is not also specified. If user supplies dvn with containing X or Y variables, they are alerted to respecify the dvn object.

See Also

scrapeVarCross which this function relies on

Other bi-construct script-writing functions: scriptBiDy(), scriptCFM(), scriptMIM(), scriptObsAPIM(), scriptTwoCross()

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
  x_delim2 = "_", distinguish_1 = "1", distinguish_2 = "2",
  y_order = "spi", y_stem = "com", y_delim1 = ".", y_delim2 = "_"
)
apim.script.indist <- scriptAPIM(dvn,
  lvxname = "Sat", lvyname = "Com", est_k = TRUE,
  writeTo = tempdir(),
  fileName = "latAPIM_indist"
)

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan() syntax for specifying dyadic configural, loading, and intercept invariant BiDy CFA (BiDy-C) or SEM (BiDy-S) Model. Currently only uses fixed-factor scale-setting

Usage

scriptBiDy(
  dvn,
  type = "CFA",
  lvxname,
  lvyname,
  constr_dy_x_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_x_struct = c("variances", "means"),
  constr_dy_y_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_y_struct = c("variances", "means"),
  constr_dy_xy_struct = c("actors"),
  model = lifecycle::deprecated(),
  equate = lifecycle::deprecated(),
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

character object of lavaan script that can be passed immediately to lavaan functions

See Also

Other bi-construct script-writing functions: scriptAPIM(), scriptCFM(), scriptMIM(), scriptObsAPIM(), scriptTwoCross()

Examples

dvn <- scrapeVarCross(DRES, x_order = "sip", x_stem = "sexsat",
x_delim2=".", distinguish_1="1", distinguish_2="2")

sexsat.bidyc.script <- scriptBiDy(dvn, lvxname = "SexSat", type = "CFA",
writeTo = tempdir(),
fileName = "BiDy_C")

dvn <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2",
y_order="spi", y_stem="com", y_delim1 = ".", y_delim2="_")

comsat.bidys.config.script <- scriptBiDy(dvn, lvxname = "Sat",
lvyname = "Com", type = "SEM",
writeTo = tempdir(),
fileName = "BiDy_S")

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan syntax for specifying dyadic configural, loading, intercept, and residual invariant bifactor models.

Usage

scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "X",
  lvar = "X",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = c("variances", "means"),
  constr_group_meas = NULL,
  constr_group_struct = NULL,
  writeTo = NULL,
  fileName = NULL,
  outputType = "lavaan script"
)

Arguments

Details

• By default, many ⁠dySEM::⁠ functions (including scriptBifac()) default to a fixed-factor method of scale-setting, whereby the latent variance of a given factor is constrained to 1 for both partners in the configurally invariant model, and then one of these variances is freely estimated in subsequent models of the invariance testing sequence. We have selected this default for two reasons: (1) the selection of a marker-variable is usually arbitrary, yet can have a large influence on the estimation and testing of of structural parameters (see https://stats.stackexchange.com/questions/402133/in-cfa-does-it-matter-which-factor-loading-is-set-to-1/402732#402732); and (2) the selection of a non-invariant marker-variable can have disastrous down-stream consequences for the identification of non-invariant measurement parameters, following a the rejection of an omnibus invariance constraint set (see Lee, Preacher, & Little, 2011).

Value

Character object of lavaan script that can be passed immediately to lavaan functions (when outputType = "lavaan script"), or a structured list of model components (when outputType = "syntax components").

See Also

scrapeVarCross which this function relies on.

Other uni-construct script-writing functions: scriptCor(), scriptHier(), scriptUni()

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ,
  x_order = "spi",
  x_stem = "sat.g",
  x_delim1 = ".",
  x_delim2 = "_",
  distinguish_1 = "1",
  distinguish_2 = "2"
)

sat.indist.script <- scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "Sat"
)

sat.lvars.script <- scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "loadings",
  constr_dy_struct = "variances"
)

sat.resids.script <- scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dBiFac_residual"
)

sat.ints.script <- scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dBiFac_intercept"
)

sat.loads.script <- scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dBiFac_loading"
)

sat.config.script <- scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "none",
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dBiFac_configural"
)

sat.source.script <- scriptBifac(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "loadings_source",
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dBiFac_source"
)

Description

This function takes the outputted object from scrapeVarCross() when the var_list argument has been used, and automatically writes, returns, and exports (.txt) lavaan() syntax for specifying dyadic configural, loading, and intercept invariant measurement models for either a group of latent variables (e.g., different sub-scales from a self-report measures).

scriptMultiCor() is a thin wrapper around scriptCFA() provided as a synonym for users who think of these models as dyadic multi-factor correlated-factor models. It takes the same arguments as scriptCFA() and returns the identical lavaan syntax.

Usage

scriptCFA(
  dvn,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = c("variances", "means"),
  writeTo = NULL,
  fileName = NULL
)

scriptMultiCor(
  dvn,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = c("variances", "means"),
  writeTo = NULL,
  fileName = NULL
)

Arguments

Details

By default, many dySEM:: functions (including scriptCFA() default to a fixed-factor method of scale-setting, whereby the latent variance of a given factor is constrained to 1 for both partners in the configurally invariant #model, and then one of these variances is freely estimated in subsequent #models of the invariance testing sequence. We have selected this default for two reasons: (1) the selection of a marker-variable is usually arbitrary, yet can have a large influence on the estimation and testing of of structural parameters (see https://stats.stackexchange.com/questions/402133/in-cfa-does-it-matter-which-factor-loading-is-set-to-1/402732#402732); and (2) the selection of a non-invariant marker-variable can have disastrous down-stream consequences for the identification of non-invariant measurement parameters, following a the rejection of an omnibus #invariance constraint set (see Lee, Preacher, & Little, 2011).

Value

character object of lavaan script that can be passed immediately to lavaan functions

character object of lavaan script that can be passed immediately to lavaan functions

See Also

scrapeVarCross which this function relies on

Other multi-construct script-writing functions: scriptDyEFA()

Examples

# When different factor use distinct stems:
imsList <- list(
  lvnames = c("Sat", "Q_Alt", "Invest", "Comm"),
  stem = c("sat.g", "qalt.g", "invest.g", "com"),
  delim1 = c("", "", "", ""),
  delim2 = c("_", "_", "_", "_")
)

dvnIMS <- scrapeVarCross(imsM,
  var_list = imsList,
  var_list_order = "sip",
  distinguish_1 = "f",
  distinguish_2 = "m"
)

script.ims.config <- scriptCFA(dvnIMS,
  scaleset = "FF",
  constr_dy_meas = "none",
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "ims_config"
)

script.ims.load <- scriptCFA(dvnIMS,
  scaleset = "FF",
  constr_dy_meas = c("loadings"),
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "ims_load"
)

script.ims.int <- scriptCFA(dvnIMS,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts"),
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "ims_int"
)

script.ims.res <- scriptCFA(dvnIMS,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "ims_res"
)

script.ims.indist <- scriptCFA(dvnIMS,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = c("variances", "means"), writeTo = tempdir(), fileName = "ims_indist"
)

# When different factor use the same stem and muse be detected through numeric position

prqcList <- list(
  lvnames = c("Sat", "Comm", "Intim", "Trust", "Pass", "Love"),
  stem = c("prqc", "prqc", "prqc", "prqc", "prqc", "prqc"),
  delim1 = c(".", ".", ".", ".", ".", "."),
  delim2 = c("_", "_", "_", "_", "_", "_"),
  min_num = c(1, 4, 7, 10, 13, 16),
  max_num = c(3, 6, 9, 12, 15, 18)
)

dvnPRQC <- scrapeVarCross(prqcQ,
  var_list = prqcList,
  var_list_order = "spi",
  distinguish_1 = "1",
  distinguish_2 = "2"
)

script.prqc.config <- scriptCFA(dvnPRQC,
  scaleset = "FF",
  constr_dy_meas = "none",
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "prqc_config"
)

script.prqc.load <- scriptCFA(dvnPRQC,
  scaleset = "FF",
  constr_dy_meas = c("loadings"),
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "prqc_load"
)

script.prqc.int <- scriptCFA(dvnPRQC,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts"),
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "prqc_int"
)

script.prqc.res <- scriptCFA(dvnPRQC,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none", writeTo = tempdir(), fileName = "prqc_res"
)

script.prqc.indist <- scriptCFA(dvnPRQC,
  scaleset = "FF",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = c("variances", "means"), writeTo = tempdir(), fileName = "prqc_indist"
)

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan() syntax for specifying Common Fate Models (CFMs). Users can also invoke configural, loading, and/or intercept invariant measurement models, and particular types of structural comparisons.

Usage

scriptCFM(
  dvn,
  scaleset = "FF",
  lvxname,
  lvyname,
  constr_dy_x_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_x_struct = c("variances", "means"),
  constr_dy_y_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_y_struct = c("variances", "means"),
  constr_dy_xy_struct = "none",
  model = lifecycle::deprecated(),
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

character object of lavaan script that can be passed immediately to lavaan functions. Users will receive message if structural comparisons are specified when the recommended level of invariance is not also specified. If user supplies dvn with containing X or Y variables, they are alerted to respecify the dvn object.

See Also

scrapeVarCross which this function relies on

Other bi-construct script-writing functions: scriptAPIM(), scriptBiDy(), scriptMIM(), scriptObsAPIM(), scriptTwoCross()

Examples

dvn <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2",
y_order="spi", y_stem="com", y_delim1 = ".", y_delim2="_")
cfm.script.indist <-  scriptCFM(dvn, lvxname = "Sat", lvyname = "Com",
writeTo = tempdir(),
fileName = "CFM_indist")

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan syntax for specifying dyadic configural, loading, intercept, and residual invariant two-factor models.

Usage

scriptCor(
  dvn,
  scaleset = "FF",
  lvname = "X",
  lvar = "X",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = c("variances", "means"),
  constr_group_meas = NULL,
  constr_group_struct = NULL,
  writeTo = NULL,
  fileName = NULL,
  outputType = "lavaan script"
)

Arguments

Details

• By default, many ⁠dySEM::⁠ functions (including scriptCor()) default to a fixed-factor method of scale-setting, whereby the latent variance of a given factor is constrained to 1 for both partners in the configurally invariant model, and then one of these variances is freely estimated in subsequent models of the invariance testing sequence. We have selected this default for two reasons: (1) the selection of a marker-variable is usually arbitrary, yet can have a large influence on the estimation and testing of of structural parameters (see https://stats.stackexchange.com/questions/402133/in-cfa-does-it-matter-which-factor-loading-is-set-to-1/402732#402732); and (2) the selection of a non-invariant marker-variable can have disastrous down-stream consequences for the identification of non-invariant measurement parameters, following a the rejection of an omnibus invariance constraint set (see Lee, Preacher, & Little, 2011).

Value

Character object of lavaan script that can be passed immediately to lavaan functions (when outputType = "lavaan script"), or a structured list of model components (when outputType = "syntax components").

See Also

scrapeVarCross which this function relies on.

Other uni-construct script-writing functions: scriptBifac(), scriptHier(), scriptUni()

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ,
  x_order = "spi",
  x_stem = "sat.g",
  x_delim1 = ".",
  x_delim2 = "_",
  distinguish_1 = "1",
  distinguish_2 = "2"
)

sat.indist.script <- scriptCor(
  dvn,
  scaleset = "FF",
  lvname = "Sat"
)

sat.lvars.script <- scriptCor(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "loadings",
  constr_dy_struct = "variances"
)

sat.resids.script <- scriptCor(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dCor_residual"
)

sat.ints.script <- scriptCor(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dCor_intercept"
)

sat.loads.script <- scriptCor(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dCor_loading"
)

sat.config.script <- scriptCor(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "none",
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dCor_configural"
)

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan() syntax for specifying a dyadic EFA model of a given number of exploratory factors.

Usage

scriptDyEFA(
  dvn,
  nFactor = 1,
  constr_dy_meas = "none",
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

character object of lavaan script that can be passed immediately to lavaan functions

See Also

scrapeVarCross which this function relies on

Other multi-construct script-writing functions: scriptCFA()

Examples

dvn <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2")

sat.defa1.script <- scriptDyEFA(dvn, nFactor = 1,
writeTo = tempdir(), fileName = "DEFA_1fac")

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan syntax for specifying dyadic configural, loading, intercept, and residual invariant hierarchical models.

Usage

scriptHier(
  dvn,
  scaleset = "FF",
  lvname = "X",
  lvar = "X",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = c("variances", "means"),
  constr_group_meas = NULL,
  constr_group_struct = NULL,
  writeTo = NULL,
  fileName = NULL,
  outputType = "lavaan script"
)

Arguments

Details

• By default, many ⁠dySEM::⁠ functions (including scriptHier()) default to a fixed-factor method of scale-setting, whereby the latent variance of a given factor is constrained to 1 for both partners in the configurally invariant model, and then one of these variances is freely estimated in subsequent models of the invariance testing sequence. We have selected this default for two reasons: (1) the selection of a marker-variable is usually arbitrary, yet can have a large influence on the estimation and testing of of structural parameters (see https://stats.stackexchange.com/questions/402133/in-cfa-does-it-matter-which-factor-loading-is-set-to-1/402732#402732); and (2) the selection of a non-invariant marker-variable can have disastrous down-stream consequences for the identification of non-invariant measurement parameters, following a the rejection of an omnibus invariance constraint set (see Lee, Preacher, & Little, 2011).

Value

Character object of lavaan script that can be passed immediately to lavaan functions (when outputType = "lavaan script"), or a structured list of model components (when outputType = "syntax components").

See Also

scrapeVarCross which this function relies on.

Other uni-construct script-writing functions: scriptBifac(), scriptCor(), scriptUni()

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ,
  x_order = "spi",
  x_stem = "sat.g",
  x_delim1 = ".",
  x_delim2="_",
  distinguish_1="1",
  distinguish_2="2"
  )

sat.indist.script <- scriptHier(
  dvn,
  scaleset = "FF",
  lvname = "Sat"
  )

sat.lvars.script <- scriptHier(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "loadings",
  constr_dy_struct = "variances"
  )

sat.resids.script <- scriptHier(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dHier_residual"
  )

sat.ints.script <- scriptHier(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dHier_intercept"
  )

sat.loads.script <- scriptHier(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dHier_loading"
  )

sat.config.script <- scriptHier(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "none",
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dHier_configural"
  )

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan() syntax for the I-NULL model described in Olsen & Kenny (2006)

Usage

scriptINULL(
  dvn,
  lvxname = "X",
  lvyname = NULL,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

character object of lavaan script that can be passed immediately to lavaan functions

See Also

scrapeVarCross which this function relies on

Other indistinguishable script-writing functions: scriptISAT()

Examples

dvn <- scrapeVarCross(dat = DRES, x_order = "sip", x_stem = "PRQC", x_delim1 = "_",
x_delim2=".", x_item_num="\\d+", distinguish_1="1", distinguish_2="2")
qual.inull.script <- scriptINULL(dvn, lvxname = "Qual",
writeTo = tempdir(),
fileName = "I-NULL_script")

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan() syntax for the I-SAT model described in Olsen & Kenny (2006)

Usage

scriptISAT(dvn, lvxname = "X", lvyname = NULL, writeTo = NULL, fileName = NULL)

Arguments

Value

character object of lavaan script that can be passed immediately to lavaan functions

See Also

scrapeVarCross which this function relies on

Other indistinguishable script-writing functions: scriptINULL()

Examples

dvn <- scrapeVarCross(dat = DRES, x_order = "sip", x_stem = "PRQC", x_delim1 = "_",
x_delim2=".", x_item_num="\\d+", distinguish_1="1", distinguish_2="2")

qual.isat.script <- scriptISAT(dvn, lvxname = "Qual",
writeTo = tempdir(),
fileName = "I-SAT_script")

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan() syntax for specifying Mutual Influence Models (MIMs). Users can also invoke configural, loading, and/or intercept invariant measurement models, and particular types of structural comparisons.

Usage

scriptMIM(
  dvn,
  scaleset = "FF",
  lvxname,
  lvyname,
  constr_dy_x_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_x_struct = c("variances", "means"),
  constr_dy_y_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_y_struct = c("variances", "means"),
  constr_dy_xy_struct = c("actors", "partners"),
  model = lifecycle::deprecated(),
  equate = lifecycle::deprecated(),
  est_k = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

character object of lavaan script that can be passed immediately to lavaan functions. Users will receive message if structural comparisons are specified when the recommended level of invariance is not also specified. If user supplies dvn with containing X or Y variables, they are alerted to respecify the dvn object.

See Also

scrapeVarCross which this function relies on

Other bi-construct script-writing functions: scriptAPIM(), scriptBiDy(), scriptCFM(), scriptObsAPIM(), scriptTwoCross()

Examples

dvn <- scrapeVarCross(dat = commitmentQ, x_order = "spi", x_stem = "sat.g", x_delim1 = ".",
x_delim2="_", distinguish_1="1", distinguish_2="2",
y_order="spi", y_stem="com", y_delim1 = ".", y_delim2="_")

mim.script.indist <- scriptMIM(dvn, lvxname = "Sat", lvyname = "Com", est_k = TRUE,
writeTo = tempdir(),
fileName = "MIM_indist")

Description

Writes lavaan syntax for an APIM with one observed (or composite) X and Y per partner. Structural constraints mirror scriptAPIM() (dyadic variances/means, actor/partner paths, optional orthogonal dyadic covariances).

Usage

scriptObsAPIM(
  X1 = NULL,
  Y1 = NULL,
  X2 = NULL,
  Y2 = NULL,
  constr_dy_x_struct = c("variances", "means"),
  constr_dy_y_struct = c("variances", "means"),
  constr_dy_xy_struct = c("actors", "partners"),
  includeMeanStruct = FALSE,
  equate = lifecycle::deprecated(),
  k = lifecycle::deprecated(),
  est_k = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

Character string of lavaan model syntax.

See Also

scriptAPIM()

Other bi-construct script-writing functions: scriptAPIM(), scriptBiDy(), scriptCFM(), scriptMIM(), scriptTwoCross()

Examples

scriptObsAPIM(
  X1 = "SexSatA", Y1 = "RelSatA",
  X2 = "SexSatB", Y2 = "RelSatB",
  constr_dy_xy_struct = "none",
  constr_dy_x_struct = "none",
  constr_dy_y_struct = "none",
  writeTo = tempdir(),
  fileName = "obsAPIM_script"
)

Description

Writes a fully specified population model with fixed numeric parameters for use with lavaan::simulateData(). Measurement blocks follow the same conventions as scriptPopCor() for each construct; structural paths use a single actor and partner coefficient on both partners' equations.

Usage

scriptPopAPIM(dvn, lvxname, lvyname, pop_values)

Arguments

Value

Single string of lavaan model syntax.

Population values

X measurement (lengths nx = dvn$xindper): x_loadings_p1, x_loadings_p2 (optional recycle), x_residuals_p1, x_residuals_p2, x_coresids, optional x_intercepts_p1 / x_intercepts_p2.

Y measurement (ny = dvn$yindper): y_loadings_p1, y_loadings_p2, y_residuals_p1, y_residuals_p2, y_coresids, optional ⁠y_intercepts_*⁠.

Latent X: x_lv_var (scalar or length 2, default c(1,1)), x_lv_cov (default 0), x_lv_means (optional, default c(0,0)).

Structural: actor, partner (numeric), y_lv_var (scalar or length 2, default c(0.5, 0.5)), y_lv_cov (default 0; covariance between latent Y residuals).

Vectors of length 1 are recycled to nx or ny for measurement slots.

See Also

Other population-scripting functions: scriptPopCor(), scriptPopUni()

Description

Produces lavaan syntax with fixed numeric values for data generation in Monte Carlo simulations. Used with lavaan::simulateData().

Usage

scriptPopCor(dvn, lvname = "X", pop_values, lvar = "X")

Arguments

Value

Character string of lavaan syntax

See Also

Other population-scripting functions: scriptPopAPIM(), scriptPopUni()

Examples

dvn <- dySEM::build_dvn(n_items_x = 3, x_stem = "x", x_delim1 = "", x_delim2 = "_",
  distinguish_1 = "A", distinguish_2 = "B")
scriptPopCor(dvn, "X", list(
  loadings_p1 = c(.75, .80, .55),
  loadings_p2 = c(.70, .85, .50),
  residuals_p1 = c(.44, .36, .70),
  residuals_p2 = c(.51, .28, .75),
  coresids = c(.10, .12, .08),
  lv_cov = 0.3
))

Description

Produces lavaan syntax with fixed numeric values for data generation in Monte Carlo simulations. Used with lavaan::simulateData().

Usage

scriptPopUni(dvn, lvname = "X", pop_values, lvar = "X")

Arguments

Value

Character string of lavaan syntax

See Also

Other population-scripting functions: scriptPopAPIM(), scriptPopCor()

Examples

dvn <- dySEM::build_dvn(n_items_x = 3, x_stem = "x", x_delim1 = "", x_delim2 = "_",
  distinguish_1 = "A", distinguish_2 = "B")
scriptPopUni(dvn, "X", list(
  loadings = c(.75, .80, .55),
  residuals = c(.44, .36, .70),
  coresids = c(.10, .12, .08)
))

Description

This function takes the outputted object from scrapeVarCross() with both X and Y indicators and automatically writes, returns, and exports (.txt) lavaan syntax for specifying a two-construct model where the measurement structure of X and Y can differ (e.g., X as correlated factors, Y as unidimensional).

Usage

scriptTwoCross(
  dvn,
  x_scaleset = "FF",
  y_scaleset = "FF",
  lvxname = "X",
  lvyname = "Y",
  x_model = "cor",
  y_model = "cor",
  constr_dy_x_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_x_struct = c("variances", "means"),
  constr_dy_y_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_y_struct = c("variances", "means"),
  constr_dy_xy_struct = "free",
  includeMeanStruct = FALSE,
  writeTo = NULL,
  fileName = NULL
)

Arguments

Value

Character object of lavaan script that can be passed immediately to lavaan functions.

See Also

scrapeVarCross which this function relies on; scriptUni, scriptCor, scriptHier, scriptBifac for the underlying scripters; scriptAPIM for a related two-construct function.

Other bi-construct script-writing functions: scriptAPIM(), scriptBiDy(), scriptCFM(), scriptMIM(), scriptObsAPIM()

Examples

dvn <- scrapeVarCross(
  dat = commitmentQ,
  x_order = "spi", x_stem = "sat.g", x_delim1 = ".", x_delim2 = "_",
  distinguish_1 = "1", distinguish_2 = "2",
  y_order = "spi", y_stem = "com", y_delim1 = ".", y_delim2 = "_"
)

# Correlated X, unidimensional Y
scriptTwoCross(dvn, lvxname = "Sat", lvyname = "Com",
  x_model = "cor", y_model = "uni")

# Both correlated
scriptTwoCross(dvn, lvxname = "Sat", lvyname = "Com",
  x_model = "cor", y_model = "cor",
  writeTo = tempdir(), fileName = "twoCross_cor_cor")

Description

This function takes the outputted object from scrapeVarCross() and automatically writes, returns, and exports (.txt) lavaan syntax for specifying dyadic configural, loading, intercept, and residual invariant one-factor models.

Usage

scriptUni(
  dvn,
  scaleset = "FF",
  lvname = "X",
  lvar = "X",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none",
  constr_group_meas = NULL,
  constr_group_struct = NULL,
  writeTo = NULL,
  fileName = NULL,
  outputType = "lavaan script"
)

Arguments

Details

• Users do not need to modify constr_dy_struct when using scriptUni().

• By default, many ⁠dySEM::⁠ functions (including scriptUni()) default to a fixed-factor method of scale-setting, whereby the latent variance of a given factor is constrained to 1 for both partners in the configurally invariant model, and then one of these variances is freely estimated in subsequent models of the invariance testing sequence. We have selected this default for two reasons: (1) the selection of a marker-variable is usually arbitrary, yet can have a large influence on the estimation and testing of of structural parameters (see https://stats.stackexchange.com/questions/402133/in-cfa-does-it-matter-which-factor-loading-is-set-to-1/402732#402732); and (2) the selection of a non-invariant marker-variable can have disastrous down-stream consequences for the identification of non-invariant measurement parameters, following a the rejection of an omnibus invariance constraint set (see Lee, Preacher, & Little, 2011).

Value

Character object of lavaan script that can be passed immediately to lavaan functions (when outputType = "lavaan script"), or a structured list of model components (when outputType = "syntax components").

See Also

scrapeVarCross which this function relies on.

Other uni-construct script-writing functions: scriptBifac(), scriptCor(), scriptHier()

Examples

dvn <- scrapeVarCross(
  commitmentQ,
  x_order = "spi",
  x_stem = "sat.g",
  x_delim1 = ".",
  x_delim2 = "_",
  distinguish_1 = "1",
  distinguish_2 = "2"
)

sat.resids.script <- scriptUni(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts", "residuals"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dUni_residual"
)

sat.ints.script <- scriptUni(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings", "intercepts"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dUni_intercept"
)

sat.loads.script <- scriptUni(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = c("loadings"),
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dUni_loading"
)

sat.config.script <- scriptUni(
  dvn,
  scaleset = "FF",
  lvname = "Sat",
  constr_dy_meas = "none",
  constr_dy_struct = "none",
  writeTo = tempdir(),
  fileName = "dUni_configural"
)