tspa: Two-Stage Path Analysis

In Gengrui-Zhang/R2spa: An R package for two-stage path analysis (2S-PA) to adjust for measurement errors

Two-Stage Path Analysis

Description

Fit a two-stage path analysis (2S-PA) model.

Usage

tspa(
  model,
  data,
  reliability = NULL,
  se = "standard",
  se_fs = NULL,
  fsT = NULL,
  fsL = NULL,
  fsb = NULL,
  ...
)

Arguments

model	A string variable describing the structural path model, in lavaan syntax.
data	A data frame containing factor scores.
reliability	A numeric vector representing the reliability indexes of each latent factor. Currently tspa() does not support the reliability argument. Please use se.
se	Deprecated to avoid conflict with the argument of the same name in lavaan::lavaan().
se_fs	A numeric vector representing the standard errors of each factor score variable for single-group 2S-PA. A list or data frame storing the standard errors of each group in each latent factor for multigroup 2S-PA.
fsT	An error variance-covariance matrix of the factor scores, which can be obtained from the output of get_fs() using attr() with the argument which = "fsT".
fsL	A matrix of loadings and cross-loadings from the latent variables to the factor scores fs, which can be obtained from the output of get_fs() using attr() with the argument which = "fsL". For details see the multiple-factors vignette: vignette("multiple-factors", package = "R2spa").
fsb	A vector of intercepts for the factor scores fs, which can be obtained from the output of get_fs() using attr() with the argument which = "fsb".
...	Additional arguments passed to sem. See lavOptions for a complete list.

Value

An object of class lavaan, with an attribute tspaModel that contains the model syntax.

Examples

library(lavaan)

# single-group, two-factor example, factor scores obtained separately
# get factor scores
fs_dat_ind60 <- get_fs(data = PoliticalDemocracy,
                       model = "ind60 =~ x1 + x2 + x3")
fs_dat_dem60 <- get_fs(data = PoliticalDemocracy,
                       model = "dem60 =~ y1 + y2 + y3 + y4")
fs_dat <- cbind(fs_dat_ind60, fs_dat_dem60)
# tspa model
tspa(model = "dem60 ~ ind60", data = fs_dat,
     se_fs = c(ind60 = fs_dat_ind60[1, "fs_ind60_se"],
               dem60 = fs_dat_dem60[1, "fs_dem60_se"]))

# single-group, three-factor example
mod2 <- "
  # latent variables
    ind60 =~ x1 + x2 + x3
    dem60 =~ y1 + y2 + y3 + y4
    dem65 =~ y5 + y6 + y7 + y8
"
fs_dat2 <- get_fs(PoliticalDemocracy, model = mod2, std.lv = TRUE)
tspa(model = "dem60 ~ ind60
              dem65 ~ ind60 + dem60",
     data = fs_dat2,
     fsT = attr(fs_dat2, "fsT"),
     fsL = attr(fs_dat2, "fsL"))

# multigroup, two-factor example
mod3 <- "
  # latent variables
    visual =~ x1 + x2 + x3
    speed =~ x7 + x8 + x9
"
fs_dat3 <- get_fs(HolzingerSwineford1939, model = mod3, std.lv = TRUE,
                  group = "school")
tspa(model = "visual ~ speed",
     data = fs_dat3,
     fsT = attr(fs_dat3, "fsT"),
     fsL = attr(fs_dat3, "fsL"),
     group = "school")

# multigroup, three-factor example
mod4 <- "
  # latent variables
    visual =~ x1 + x2 + x3
    textual =~ x4 + x5 + x6
    speed =~ x7 + x8 + x9
"
fs_dat4 <- get_fs(HolzingerSwineford1939, model = mod4, std.lv = TRUE,
                  group = "school")
tspa(model = "visual ~ speed
              textual ~ visual + speed",
     data = fs_dat4,
     fsT = attr(fs_dat4, "fsT"),
     fsL = attr(fs_dat4, "fsL"),
     group = "school")

# get factor scores
fs_dat_visual <- get_fs(data = HolzingerSwineford1939,
                        model = "visual =~ x1 + x2 + x3",
                        group = "school")
fs_dat_speed <- get_fs(data = HolzingerSwineford1939,
                       model = "speed =~ x7 + x8 + x9",
                       group = "school")
fs_hs <- cbind(do.call(rbind, fs_dat_visual),
               do.call(rbind, fs_dat_speed))

# tspa model
tspa(model = "visual ~ speed",
     data = fs_hs,
     se_fs = data.frame(visual = c(0.3391326, 0.311828),
                        speed = c(0.2786875, 0.2740507)),
     group = "school",
     group.equal = "regressions")

# manually adding equality constraints on the regression coefficients
tspa(model = "visual ~ c(b1, b1) * speed",
     data = fs_hs,
     se_fs = list(visual = c(0.3391326, 0.311828),
                  speed = c(0.2786875, 0.2740507)),
     group = "school")

Gengrui-Zhang/R2spa documentation built on Sept. 6, 2024, 5:01 p.m.