Test Several Conditional Indirect Effects
Source:R/test_conditional_indirect_effects.R
test_cond_indirect_effects.RdTest several conditional
indirect effects
for a power4test object.
Usage
test_cond_indirect_effects(
fit = fit,
x = NULL,
m = NULL,
y = NULL,
wlevels = NULL,
mc_ci = TRUE,
mc_out = NULL,
boot_ci = FALSE,
boot_out = NULL,
check_post_check = TRUE,
...,
fit_name = "fit",
get_map_names = FALSE,
get_test_name = FALSE
)Arguments
- fit
The fit object, to be passed to
manymome::cond_indirect_effects().- x
The name of the
x-variable, the predictor.- m
A character vector of the name(s) of mediator(s). The path moves from the first mediator in the vector to the last mediator in the vector. Can be
NULLand the path is a direct path without mediator.- y
The name of the
y-variable, the outcome variable.- wlevels
The output of
manymome::merge_mod_levels(), or the moderator(s) to be passed tomanymome::mod_levels_list(). If all the moderators can be represented by one variable, that is, each moderator is (a) a numeric variable, (b) a dichotomous categorical variable, or (c) a factor or string variable used instats::lm()in fit, then it is a vector of the names of the moderators as appeared in the data frame. If at least one of the moderators is a categorical variable represented by more than one variable, such as user-created dummy variables used inlavaan::sem(), then it must be a list of the names of the moderators, with such moderators represented by a vector of names. For example:list("w1", c("gpgp2", "gpgp3"), the first moderatorw1and the second moderator a three-category variable represented bygpgp2andgpgp3. See the help page ofmanymome::cond_indirect_effects()for further details.- mc_ci
Logical. If
TRUE, the default, Monte Carlo confidence intervals will be formed. This argument andboot_cicannot be bothTRUE.- mc_out
The pre-generated Monte Carlo estimates generated by manymome::do_mc, stored in a
power4testobject. Users should not set this argument and should letpower4test()to set it automatically.- boot_ci
Logical. If
TRUE, the default, nonparametric bootstrap confidence intervals will be formed. This argument andmc_cicannot be bothTRUE.- boot_out
The pre-generated bootstrap estimates generated by manymome::do_boot, stored in a
power4testobject. Users should not set this argument and should letpower4test()to set it automatically.- check_post_check
Logical. If
TRUE, the default, and the model is fitted bylavaan, the test will be conducted only if the model passes thepost.checkconducted bylavaan::lavInspect()(withwhat = "post.check").- ...
Additional arguments to be passed to
manymome::cond_indirect_effects().- fit_name
The name of the model fit object to be extracted. Default is
"fit". Used only when more than one model is fitted in each replication. This should be the name of the model on which the test is to be conducted.- get_map_names
Logical. Used by
power4test()to determine how to extract stored information and assign them to this function. Users should not use this argument.- get_test_name
Logical. Used by
power4test()to get the default name of this test. Users should not use this argument.
Value
In its normal usage, it returns
the output returned by
manymome::cond_indirect_effects(),
with the following modifications:
est: The estimated conditional indirect effects.ciloandcihi: The lower and upper limits of the confidence interval (95% by default), respectively.sig: Whether a test by confidence interval is significant (1) or not significant (0).test_label: A column of labels generated to label the conditional effects.
Details
This function is to be used in
power4test() for testing several
conditional
indirect effects, by setting it
to the test_fun argument.
It uses manymome::cond_indirect_effects()
to do the test. It can be used on
models fitted by lavaan::sem()
or fitted by a sequence of calls
to stats::lm(), although only
nonparametric bootstrap confidence
interval is supported for models
fitted by regression using
stats::lm().
It can also be used to test
conditional effects on a direct path
with no mediator. Just omit m when
calling the function.
Examples
# Specify the model
model_simple_mod <-
"
m ~ x + w + x:w
y ~ m + x
"
# Specify the population values
model_simple_mod_es <-
"
y ~ m: l
y ~ x: n
m ~ x: m
m ~ w: n
m ~ x:w: l
"
# Simulate the data
# Set nrep to a larger value in real analysis, such as 400
sim_only <- power4test(nrep = 5,
model = model_simple_mod,
pop_es = model_simple_mod_es,
n = 100,
R = 100,
do_the_test = FALSE,
iseed = 1234)
#> Simulate the data:
#> Fit the model(s):
#> Generate Monte Carlo estimates:
# Do the tests in each replication
test_out <- power4test(object = sim_only,
test_fun = test_cond_indirect_effects,
test_args = list(x = "x",
m = "m",
y = "y",
wlevels = c("w"),
mc_ci = TRUE))
#> Do the test: test_cond_indirect_effects: x->m->y
print(test_out,
test_long = TRUE)
#>
#> ====================== Model Information ======================
#>
#> == Model on Factors/Variables ==
#>
#> m ~ x + w + x:w
#> y ~ m + x
#>
#> == Model on Variables/Indicators ==
#>
#> m ~ x + w + x:w
#> y ~ m + x
#>
#> ====== Population Values ======
#>
#> Regressions:
#> Population
#> m ~
#> x 0.300
#> w 0.000
#> x:w 0.150
#> y ~
#> m 0.500
#> x 0.000
#>
#> Covariances:
#> Population
#> x ~~
#> w 0.000
#> x:w 0.000
#> w ~~
#> x:w 0.000
#>
#> Variances:
#> Population
#> .m 0.887
#> .y 0.751
#> x 1.000
#> w 1.000
#> x:w 1.000
#>
#> (Computing indirect effects for 1 paths ...)
#>
#> (Computing conditional effects for 2 paths ...)
#>
#> == Population Conditional/Indirect Effect(s) ==
#>
#> == Effect(s) ==
#>
#> ind
#> x -> y 0
#>
#> - The 'ind' column shows the effect(s).
#>
#> == Conditional indirect effects ==
#>
#> Path: x -> m -> y
#> Conditional on moderator(s): w
#> Moderator(s) represented by: w
#>
#> [w] (w) ind m~x y~m
#> 1 M+1.0SD 1 0.225 0.450 0.500
#> 2 Mean 0 0.150 0.300 0.500
#> 3 M-1.0SD -1 0.075 0.150 0.500
#>
#> - The 'ind' column shows the conditional indirect effects.
#> - ‘m~x’,‘y~m’ is/are the path coefficient(s) along the path conditional
#> on the moderator(s).
#>
#>
#> == Conditional indirect effects ==
#>
#> Path: w -> m -> y
#> Conditional on moderator(s): x
#> Moderator(s) represented by: x
#>
#> [x] (x) ind m~w y~m
#> 1 M+1.0SD 1 0.075 0.150 0.500
#> 2 Mean 0 -0.000 -0.000 0.500
#> 3 M-1.0SD -1 -0.075 -0.150 0.500
#>
#> - The 'ind' column shows the conditional indirect effects.
#> - ‘m~w’,‘y~m’ is/are the path coefficient(s) along the path conditional
#> on the moderator(s).
#>
#>
#> ======================= Data Information =======================
#>
#> Number of Replications: 5
#> Sample Sizes: 100
#>
#> Call print with 'data_long = TRUE' for further information.
#>
#> ==================== Extra Element(s) Found ====================
#>
#> - fit
#> - mc_out
#>
#> === Element(s) of the First Dataset ===
#>
#> ============ <fit> ============
#>
#> lavaan 0.6-19 ended normally after 1 iteration
#>
#> Estimator ML
#> Optimization method NLMINB
#> Number of model parameters 7
#>
#> Number of observations 100
#>
#> Model Test User Model:
#>
#> Test statistic 4.530
#> Degrees of freedom 2
#> P-value (Chi-square) 0.104
#>
#> =========== <mc_out> ===========
#>
#>
#> == A 'mc_out' class object ==
#>
#> Number of Monte Carlo replications: 100
#>
#>
#> ======== <test_cond_indirect_effects: x->m->y> ========
#>
#> Mean(s) across replication:
#> test_label [w] (w) est cilo cihi sig m~x y~m
#> 1 x->m->y | w: M+1.0SD M+1.0SD 1.060 0.212 0.078 0.405 0.800 0.438 0.474
#> 2 x->m->y | w: Mean Mean 0.061 0.132 0.030 0.254 0.800 0.275 0.474
#> 3 x->m->y | w: M-1.0SD M-1.0SD -0.939 0.053 -0.092 0.189 0.000 0.112 0.474
#>
#> - The column 'sig' shows the rejection rates.
#> - If the null hypothesis is false, the rate is the power.
#> - Number of valid replications for rejection rate(s): 5
#> - Proportion of valid replications for rejection rate(s): 1.000