Journal of Behavioral Data Science, 2025, 5 (2), 1–27.

DOI: [Link]

A Guide to Specifying Effects in Latent Change

Score Models with Moderated Mediation

Holly P. O’Rourke1[0000−0002−2927−0333] and Chanler D.

Hilley2[0000−0003−4766−9513]
1
Department of Psychology, University of California at Riverside
[Link]@[Link]
2
Department of Psychological Science, Kennesaw State University
chilley2@[Link]

Abstract. Latent change score (LCS) models are discrete-time longi-

tudinal models that concurrently investigate growth over time and dy-
namic (lagged) relations among variables. Bivariate LCS models can be
extended to multivariate scenarios with mediators and moderators, and
mediation paths can be constrained or freely estimated across time. We
provide a decision-making guide for model specification based on vari-
able scale of measurement and hypothesized change processes. We then
simulate two examples to illustrate how LCS models can be specified to
estimate moderated mediation effects where the indirect effect from me-
diation is conditional upon values of the time-invariant moderator. We
provide simulated data and annotated Mplus and R lavaan code.

Keywords: Latent Change · Mediation · Moderation · Moderated Medi-

ation · Conditional Indirect Effects

1 Introduction
Many applied researchers conduct longitudinal studies with repeated measure-
ments over time in order to refine their substantive theories with hypotheses
about change processes. There are numerous available methods for longitudi-
nal data analysis, and choosing the correct method for one’s research question
requires understanding the specific questions about change that a particular sta-
tistical model can answer. Methodological developments of latent change score
(LCS) models (Cáncer & Estrada, 2023; Grimm, 2007; Grimm, An, McAr-
dle, Zonderman, & Resnick, 2012; McArdle, 2009; McArdle & Grimm, 2010;
O’Rourke, Fine, Grimm, & MacKinnon, 2022; Serang, Grimm, & Zhang, 2019;
Usami, Hayes, & McArdle, 2016) have led to a recent wider adoption of ap-
plications of LCS models. Whereas latent growth curve (LGC) models answer
questions about static change (i.e., one characterization of change over the entire
course of the study), LCS models (the focus of this paper) answer questions about
2 H. O’Rourke & C. Hilley

dynamic change (i.e., lagged relations characterizing time-dependent changes

over a study period) where future effects depend on past effects (Baltagi, 2021;
Hsiao, 2014).
Much of the research on (and most of the applications of) LCS models to
date have focused either on univariate models of change or on bivariate models
with dynamic relations among two repeatedly measured variables. These models
can be extended beyond the bivariate to incorporate additional variables which
allow researchers to expand their causal theories of change. Recent work has
examined the inclusion of mediators into LCS models (Goldsmith et al., 2018;
Hilley & O’Rourke, 2022; Selig & Preacher, 2009; Simone & Lockhart, 2019), and
in particular has focused on how to parameterize these models with respect to the
traditional mediation literature stemming from the general linear model (Baron
& Kenny, 1986; Judd & Kenny, 1981; MacKinnon, 2008). Researchers have also
undertaken efforts to examine group differences of change in LCS models via
inclusion of moderators (Cáncer, Estrada, & Ferrer, 2023; Estrada, Bunge, &
Ferrer, 2023; Könen & Karbach, 2021; McArdle & Grimm, 2010; McArdle &
Prindle, 2008).
Moderator and mediator variables can be related in several ways; one com-
monly specified relation is moderated mediation, where the indirect effect from
mediation is conditional upon values of a moderator. Moderated mediation is
indexed via a conditional indirect effect (CIE) (Hayes, 2018, 2022; Preacher,
Rucker, & Hayes, 2007). To date, no work has been undertaken on model speci-
fication and interpretation of results from LCS models with both moderators and
mediators. This paper uses illustrative examples to provide a guide to specifying
CIEs in LCS models with variables that change dynamically over time, tying to-
gether prior simpler LCS model specifications to examine models that contains
LCSs, mediators, and moderators (LCSMM models). We begin by providing
definitions of moderators and mediators with details relevant to the ultimate
LCSMM model of interest as well as an introduction to the LCS model. Next,
we discuss some of the technical and practical details that must be considered
when introducing CIEs into the LCS framework. We demonstrate the proposed
methods with two simulated examples, each of which illustrates a different re-
search question and corresponding parameterization of the LCSMM model.

1.1 Moderators
In modern behavioral research, group differences in bivariate relations are often
of interest. Such relations can be examined via a moderator (Z) also known as an
interaction effect, where Z influences the relation from X to Y. Interaction effects
investigate whether the strength of the X to Y relation differs across varying
levels of Z. Moderators, like any other predictor of Y, can take on any scale of
measurement (though this paper focuses only on the use of binary moderators).
A binary moderator can be added to a simple bivariate linear regression as shown
in the following equations.

Y = i + d1 X + e (1)
 Latent Change Score Models with Moderated Mediation 3

Y = i + d1 X + d2 Z + d3 XZ + e (2)
Equation 1 illustrates a bivariate regression equation where a predictor X
is related to an outcome Y by a regression estimate d1 . In Equation 2, the
moderator Z also predicts Y via a regression estimate d2 . The interaction XZ,
which is the product of the predictors X and Z, also predicts Y in the model
by way of the estimate d3 (this estimate is the interaction effect). Re-arranging
Equation 2 gives us an interaction term that can be used to predict how the
relation of X to Y varies at values of Z, as shown in Equation 3:

Y = i + d2 Z + (d1 X + d3 Z)X + e (3)

When Z is binary (e.g., coded 0 or 1), values of Z can be plugged in to
Equation 3 to determine the effect of X on Y at different values of Z. For example,
if Z = 0 the effect of X on Y would reduce to just d1 . If Z = 1, the effect of X
on Y would be d1 + d3 .
In research involving longitudinal change, moderators can be time-varying
or time-invariant. A time-invariant moderator is a variable that does not change
across time for individuals (e.g., random assignment to a treatment group),
whereas a time-varying moderator is a Z variable that can vary across time
for individuals (e.g., compliance with treatment protocol). Importantly, time
invariance does not inherently imply that the effect of time-invariant Z on the
X-Y relation cannot vary over the course of a study, only that values of the
variable itself cannot vary over study duration.

1.2 Mediators
Mediators are another type of variable that can influence the relation of X to Y.
In behavioral research, mediators represent theoretical mechanisms of change in
terms of how X influences Y. Specifically, mediation analysis investigates whether
the influence of X on Y is transmitted indirectly through an intervening variable
(or mediator), M. Mediation makes the assumption that X temporally precedes
M which in turn temporally precedes Y. For example, intervention researchers
studying the effects of an intervention on a behavior may include a priori media-
tion theories about a mediator (or set of mediators) that the intervention (X) is
designed to influence to ultimately lead to behavior change (Y); e.g., a smoking
intervention (X) influences negative attitudes about smoking (M) which ulti-
mately reduces smoking behaviors (Y). The equations below demonstrate the
series of linear regression equations that capture these relations for a single me-
diator model (MacKinnon, 2008).

Y = i1 + bM + c′ X + e1 (4)
M = i2 + aX + e2 (5)
In mediation analysis, the a path represents the influence of X on M in a
regression equation predicting M. The b path represents the influence of M on Y
in a separate regression equation predicting Y. The c′ path refers to the influence
4 H. O’Rourke & C. Hilley

of X on Y while controlling for M, and is known as the direct effect. A single

estimate of mediation can be quantified by taking the product of the a and b
paths ab, known as the indirect effect, which represents the extent to which X
influences Y through M (Alwin & Hauser, 1975).
Several formal statistical tests have been developed to assess the presence of
mediation. The joint significance test (MacKinnon, Lockwood, Hoffman, West,
& Sheets, 2002) is an offshoot of the causal steps approach (Baron & Kenny,
1986), which simultaneously assesses the significance of the a and b estimates
to determine whether mediation is present. The joint significance test has been
found to have the best balance of power and Type I error relative to other
causal steps tests of mediation (MacKinnon et al., 2002). However, the joint
significance test does not provide a test of significance for the overall estimate
of the indirect effect, which is often preferred as it provides a single measure of
mediation magnitude. The indirect effect ab can also be tested for significance
by calculating a z test using a derived standard error (Sobel, 1982), or with
asymmetric Monte Carlo bootstrapped confidence intervals of ab (MacKinnon,
Fritz, Williams, & Lockwood, 2007; MacKinnon, Lockwood, & Williams, 2004).
As these methods of assessing significance for mediation can be utilized for the
different parameterizations of a and b in the LCS framework, both the joint
significance test and bootstrapped confidence intervals of ab are used to assess
significance of mediation throughout this paper.

Causal Assumptions of Mediation There are several assumptions about

causality that are made in statistical mediation models, as causality is the defin-
ing feature that separates a mediation model from other models that are math-
ematically equivalent (for example, confounder models). The first assumption is
temporal precedence, which is the assumption that X occurs temporally before
M and M occurs temporally before Y within a given mediation model. Even if
a mediation model contains only cross-sectional variables, temporal precedence
assumes that at least a (very) small amount of time has elapsed between mea-
surements of each subsequent variable in the mediational chain. This assumption
is made in part to satisfy the second assumption described below.
Causal order is the second and related assumption, which relates to spec-
ification of the causal process among variables in a mediation model. Causal
order assumes that the variables in the mediation model are ordered properly
such that the causal process is correctly specified with X causing M, and M then
causing Y. This second assumption clarifies the need for the first assumption;
temporal precedence is a necessary but not sufficient requirement for establish-
ing causality. Furthermore, an implication of this assumption is that there is no
misspecification of causality. This encompasses a wide range of possible misspec-
ifications such as no unmeasured confounders, no measurement error misspecifi-
cation, and no backward causality (i.e., no reciprocal relations or reversed arrows
in the mediation path model). In particular, handling the assumption of no un-
measured confounders often requires careful consideration of model specification
and variable selection. When possible, the assumption of no unmeasured con-
 Latent Change Score Models with Moderated Mediation 5

founders is partially addressed by randomizing X (as in an intervention study),

which addresses the assumption for the a path. However, this assumption of no
unmeasured confounders typically cannot be not met for the b path, as M is char-
acteristically a variable that cannot be randomized. The assumptions of causality
can create unique challenges when adapting mediation models to frameworks be-
yond linear regression. These assumptions also have important implications for
mediation models that specify CIEs, and each assumption has particularities
to consider when conducting mediation analysis with longitudinal data (see the
discussion section of this paper for a more in-depth treatment of these issues).

1.3 Conditional Indirect Effects

The condition under which mediation effects may differ for different groups (i.e.,
at different levels of a moderator) is sometimes referred to as “moderated media-
tion” (Hayes, 2015, 2018; Preacher et al., 2007). When the mediation a or b path
is moderated such that the indirect effect is 1) not consistent across all individ-
uals in a study and 2) systematically differs across subgroups in a sample, CIEs
can be estimated to quantify the differences in mediation effects. Moderators
can produce several different types of variations in the relations in a mediation
model. A moderator Z can influence the a path such that the estimate of a (the
effect of X on M) differs across levels of Z, which is referred to as first stage
moderated mediation (Hayes, 2018). Alternatively, the moderator Z could influ-
ence the b path such that the estimate of b (the effect of M on Y) differs across
levels of Z, a condition referred to as second stage moderated mediation (Hayes,
2018). First stage moderated mediation, which is the interaction relation utilized
in our examples, is estimated in a linear regression framework with the following
equations.

Y = i1 + bM + c′ X + e1 (6)

M = i2 + aX X + aZ Z + aXZ XZ + e2 (7)
Using this framework and building on the moderation equations above, CIEs
can be calculated to provide group-specific indirect effects for a binary mod-
erator Z. These group-specific CIEs are calculated using both the traditional
mediation a path (denoted here as aX ) and the interaction term that quantifies
the magnitude of variation in the relation of X to M at different values of Z
(denoted here as aXZ ), along with the b path from the equation predicting Y.
The CIEs are calculated as follows:

(aX + aXZ Z)b = aX b + aXZ bZ (8)

For binary Z, values of Z can be entered into Equation 8 to calculate multiple
CIEs that demonstrate group differences. For example, when Z = 0 the CIE
would reduce to just aX b as in traditional mediation. When Z = 1, the CIE
would be aX b + aXZ b.
6 H. O’Rourke & C. Hilley

In moderated mediation models, it is important to distinguish between aux-

iliary variables (i.e., Z) that moderate one or more of the mediation paths com-
pared with interactions of the variables involved in the mediation processes; the
distinction between the two is non-trivial. This paper focuses on cases where
an auxiliary variable Z moderates the mediation a path. Traditional approaches
to mediation have established the assumption that there is no XM interaction
present, but it is possible that researchers could be interested in empirically test-
ing whether X and M interact in their influence on Y (Valeri & VanderWeele,
2013).
The types of moderated mediation described above can be extended beyond
linear regression to models with latent variables (Cheung, Cooper-Thomas, Lau,
& Wang, 2021; Sardeshmukh & Vandenberg, 2017) or longitudinal models using
a structural equation modeling (SEM) framework (Zhu, Sagherian, Wang, Nahm,
& Friedmann, 2021). Much of the work in this space has focused on interactions
among latent variables or moderators of static change (i.e., growth). In order to
examine moderators of dynamic change over time in conjunction with mediation
hypotheses, we now present details of the LCS framework.

1.4 LCS Models

LCS models are discrete-time longitudinal models that allow for investigation of
both intraindividual change over two or more measurement occasions as well as
interindividual differences in such change (Hamagami & McArdle, 2001; McAr-
dle, 2001). LCS models capture measures of both static and dynamic (i.e., lagged)
change over time. These models are fit using a SEM framework and are illus-
trated throughout the paper with path diagrams that utilize SEM path model
notation.
The LCS framework was initially developed to overcome measurement error
issues inherent in analyses with change scores of observed variables (Cronbach
& Furby, 1970; Raykov, 1999). Using LCSs requires addressing the possibility of
measurement error in a manner consistent with classical test theory such that
for an observed variable y, the observed score for individual i at time t can be
decomposed into a latent (true) score lyti and an error score eti :

yti = lyti + eti (9)

The LCS framework defines latent scores as having fixed-unit autoregressive
relations within a given variable over time, expressed as follows (Hamagami &
McArdle, 2001; McArdle, 2001):

lyti = lyt−1i + ∆lyti (10)

where a latent score for y at a given timepoint (lyti ) is the sum of the latent
score for y at the prior timepoint (lyt−1i ) and the change between latent scores
for y from t − 1 to t (∆lyti ). A univariate system of LCSs measuring change in
a variable y over time includes two types of change, constant change and pro-
portional change. Constant or static change where yai is the additive (that is,
 Latent Change Score Models with Moderated Mediation 7

constant) change component for an individual i is functionally equivalent to the

slope in a LGC model with no self-effect (Serang et al., 2019), and following no-
tation from Cáncer, Estrada, Ollero, and Ferrer (2021) has a mean µya , variance
σy2a , and covariance with the initial level σy0 ,ya and is referred to as an additive
component throughout this paper.
The additive component models interindividual rates of change while main-
taining a constant rate of intraindividual change. Proportional change βy relates
prior latent level at t − 1 to later latent change between t–1 and t. In LCS
models, proportional change allows prior latent levels to influence later latent
change in a given variable. These change parameters can be combined into a
single dual change model, which includes both additive and proportional change
components.

∆lyti = yai + βy lyt−1i (11)

Together, the additive and proportional change components describe an ex-
ponential trajectory in the dual change model. The dual change model described
here is not the only possible specification of univariate models for latent change.
One could include only the additive component, which would result in a static
model equivalent to a LGC model that is defined in terms of latent change, or
only the proportional change βy as a model of self-effect. This univariate LCS
system can also be extended to study longitudinal bivariate relations. The re-
lation between two longitudinal variables in the LCS framework is most often
measured using coupling, the influence of prior latent levels of one variable on
later latent change in another. The interpretation of the coupling parameter γyx
resembles the proportional change described earlier. However, coupling is a time-
dependent effect that provides an estimate of the extent to which the preceding
measurement’s level of one variable impacts the trajectory of change in another
variable at a subsequent measurement occasion. Specifically, significant coupling
from a variable x to a second variable y means that x is a leading indicator of
scores on y. We can introduce a coupling parameter into the dual change model
such that x is a leading indicator of y:

∆lyti = yai + βy lyt−1i + γyx lxt−1i (12)

We build on this bivariate equation by adding mediators and moderators in
the coming sections.

1.5 Conditional Indirect Effects in LCS Models

To date, there has been no methodological treatment of first stage moderated
mediation in LCS models. Much of the methodological literature on mediation
in the LCS framework only examines latent change between two timepoints for
any given variable (Goldsmith et al., 2018; Selig & Preacher, 2009; Simone &
Lockhart, 2019). More recent work has examined how to specify LCS models
to include either cross-sectional or longitudinal mediators with more than two
timepoints (Hilley & O’Rourke, 2022). With respect to research on moderators or
8 H. O’Rourke & C. Hilley

group differences in change in the LCS framework, moderators have typically not
been the primary focus of methodological investigations and examinations have
been limited to moderators of univariate change (i.e., univariate cohort effects)
(Cáncer et al., 2023; Estrada et al., 2023; Könen & Karbach, 2021); applied
demonstrations of moderation in bivariate LCS models exist but are rare (see
McArdle & Grimm, 2010). However, despite the lack of methodological guidance,
several applied studies have included time-invariant binary moderators in LCS
models (Gradinger, Yanagida, Strohmeier, & Spiel, 2015; Griffiths, Kievit, &
Norbury, 2022; Zaccoletti et al., 2020). Given the obvious interest in applications
of group differences in change in the LCS framework, it is natural to extend the
framework to examine group differences in change with respect to mediation
paths.
In this paper, we present two models that illustrate different ways to specify
CIEs for first stage moderated mediation in the LCS framework. We begin by
defining a general LCSMM model with a time-invariant binary moderator. From
this general model, we then combine the information regarding CIEs and LCSs
that is provided in the introduction to demonstrate multiple ways to specify
CIEs in LCSMM models. All computer code and supplementary material for this
tutorial can be found on GitHub at [Link] LCS.

2 Example Model Setup

To demonstrate the different specifications of CIEs in LCSMM models, we begin

with a keystone LCS model. In this model, X1 (X at t = 1) is a continuous
variable that is measured at a single timepoint and is assumed to occur first
temporally in the model. M and Y are continuous variables that are measured
repeatedly at five timepoints, each with a univariate dual change structure. The
a path for mediation is specified such that X predicts the additive component
of M. This is a more parsimonious way of specifying a, in contrast to a model
where X has multiple constrained paths predicting latent change in M (Hilley
& O’Rourke, 2022). The mediation b path is specified by a coupling relation
from M to Y, where prior latent level of M influences later latent change in Y.
Coupling paths are lagged such that latent levels of M at t–1 predict later latent
change in Y (between t–1 and t) to meet the mediation assumption of temporal
precedence. A measurement schedule that begins at the timepoint directly after
measurement of X is assumed for both M and Y. X also predicts the additive
component of Y (akin to a mediation c′ direct effect). The moderator Z is a
binary variable that is time-invariant (i.e., the onset of the group difference is
assumed to occur before the measurement of all other variables in the model
and to persist without change for the duration of the study). The moderator in
the keystone model influences the a path such that there are group differences
across Z in the influence of X on the additive component of M (i.e., a first stage
moderated mediation model).
This paper demonstrates estimating CIEs when the moderator Z and the
product of X and Z are included as time-invariant covariates. The time-invariant
 Latent Change Score Models with Moderated Mediation 9

covariate method uses an extension of the moderator equations described in the

introduction and incorporates the moderator directly into the statistical model.
In this approach, an interaction term is estimated as a parameter relating the
product of X and Z to the additive component of M (i.e., the interaction is first
stage moderated mediation) and is included in the equation of each indirect
effect. Values of Z are substituted into the resultant equation to calculate CIEs
at each value of Z. We provide code in Mplus and R to estimate these models
and calculate the resultant CIEs at values of binary Z.
These models may also be estimated using an equivalent multiple group ap-
proach. The multiple group approach was developed to investigate group dif-
ferences in change (McArdle & Hamagami, 1996) and was originally utilized
as a way of examining group differences for factor structures (Jöreskog, 1971).
With this approach, an invariance method is used where each parameter in the
model is explicitly specified to be either constrained to be equal across groups
or to vary across groups. This approach allows researchers to examine group
differences in any parameter of the model while defaulting to constraining all
other parameters that are not explicitly freed to vary across groups. When a
moderator is binary and time-invariant, the multiple group approach to fitting a
LCSMM model produces two sets of model estimates, one for each group on the
moderator. The a and b paths can be freely estimated across groups, with two
CIEs calculated individually as a(Z=0) b and a(Z=1) b using the MODEL CON-
STRAINT command in Mplus. A Wald χ2 test can then used to assess whether
the two CIEs significantly differ from one another, which would indicate that
the a path of X to M (and therefore the entire indirect effect ab) was moderated
by Z. Although not discussed in detail in this article, code for this approach is
also provided on our GitHub.
Given that most models in methodological work on LCS models present con-
strained coupling paths, it is correspondingly rare to find applications where LCS
models are fit with freely estimated coupling paths in empirical studies. However,
varying the typical constraints on coupling may be necessary for certain research
questions about change, and doing so has implications for how CIEs are calcu-
lated in LCSMM models (as we will see in the examples). The traditional use
of a coupling path that is constrained across time resulting in a single estimate
would result in only one CIE per value of the moderator. However, specifying a
LCSMM model with coupling paths that are freely estimated across time results
in multiple estimates of b, and thus requires that for each value of the moderator
we calculate multiple CIEs (one per estimate of b). Therefore, we present two
examples in this paper: one example with the most common specification where
b is a coupling parameter constrained to be equal across time, and one example
where there are multiple b paths that are coupling parameters freely estimated
at each wave.

2.1 Data Generation and Analysis

For each example, an illustrative data set was simulated in R (R Core Team,
2020) using the keystone model as a baseline and varying constraints on the b
10 H. O’Rourke & C. Hilley

path. Parameter values were selected to produce data trajectories typically seen
in longitudinal behavioral research, and were varied such that the a paths were
equal in magnitude but had opposing signs across groups on Z. When data were
simulated with a b path that varied across time, the b path magnitude decreased
at each successive wave. Our rationale for using this pattern of variation for
the magnitudes comes from the mediation literature (O’Rourke & MacKinnon,
2015, 2018), where Y outcomes that are more distal (i.e., farther away in time
of measurement) typically have weaker relations to the mediator than outcomes
that are more proximal (i.e., closer in time of measurement). Correlations among
latent initial score and additive change component means were fixed to .5 (large)
based on correlations commonly observed in applications of LCS models (Grimm,
2007). Population parameters used to simulate the data are shown in Table 1.
In both of the following examples, estimates from the models that were fit to
the simulated data were generally unbiased.

Table 1. Parameter Population Values for Simulated Examples

Constrained Freely Estimated

Parameter Example 1 Example 2
µX 0 0
2
σX 1 1
Univariate M
µm0 6 6
µma 0.9 0.9
βm -0.05 -0.05
2
σm0 0.49 0.49
2
σma 0.01 0.01
2
σe(m) 0.025 0.025
Univariate Y
µy0 7 7
µya -0.5 -0.5
βy 0.1 0.1
2
σy0 0.36 0.36
2
σya 0.04 0.04
2
σe(y) 0.101 0.101
Mediation/Moderation
aX1 -0.4 -0.4
aZ 0 0
aX1 Z 0.8 0.8
b -0.13 -
b3 - -0.23
b4 - -0.18
b5 - -0.13
b6 - -0.08
c′ 0.1 0.1
 Latent Change Score Models with Moderated Mediation 11

After data simulation, models were then fit to the data using Mplus (Muthén
& Muthén, 2017) and the lavaan package in R (R Core Team, 2020; Rosseel,
2012). Data generation code (R), analytic code (Mplus and R), and simulated
datasets for each example can be found on GitHub.

2.2 Power Analyses

For the datasets in each example, a sample size of 520 (n = 260 per moderator
group) was chosen based on recent simulation work recommending minimum
sample sizes for mediation with LCSs (Simone & Lockhart, 2019). Although
in the traditional regression framework, including moderators often results in
lower power to detect effects, the sample sizes provided in Simone and Lockhart
(2019) allowed for detection of significant indirect effects at magnitudes that
would reasonably be seen in empirical research. Beyond this simulation study,
there is little empirical work on sample size and power for mediation in the LCS
framework. For readers interested in conducting power analyses for the models
described in this paper, we have provided the code for a user-friendly method to
conduct power analyses for both models described below. Because LCS models
in general have complex model specifications that require several parameters to
be fixed to 0 or 1, Monte Carlo simulations are not straightforward in many
existing R packages; instead, we are using a 2-step process to conducting power
in Mplus (Muthén & Muthén, 2017).
First, we conducted the LCSMM analyses described in this paper and used
the SAVEDATA: ESTIMATES = function in Mplus to save the parameter esti-
mates as a data file to be used as population parameters in the next step. This
first step requires the use of a “real” data file; we used the data we simulated in
R in this step. Additionally, MODEL CONSTRAINT statements to compute the
CIEs are not included in the code for the first step, as they are not relevant for
generating the data file containing population parameters. In the second step, we
conducted a power analysis using the Monte Carlo procedure in Mplus. Unlike
typical Mplus Monte Carlo power analyses in which the population parameters
are set in the MODEL POPULATION statement, the population values come
from the data file saved in the first step. In the second step, a MODEL CON-
STRAINT statement was used to compute the CIEs. Using this process, power
was examined for all estimates in the LCSMM models, including the CIEs.

3 Example 1: Constrained Dynamic Paths

In example 1, we demonstrate how to specify and estimate CIEs for a LCSMM
model with constrained coupling for the b path1 .
1
In Figures 1 and 2, paths sharing labels are constrained to be equal. Unlabeled paths
are constrained to be 1, except the paths marked by an asterisk which are freely
estimated. Variances and covariances are represented with double-headed arrows.
Variances and covariances not shown are constrained to be 0, except covariances
among the residuals for observed M and Y which are excluded from this path model
for visual parsimony.
12 H. O’Rourke & C. Hilley

M2 M3 M4 M5 M6

X1
lm2 lm3 lm4 lm5 lm6

m m m m

m3
m4
m5
m6

ax1
c'
Z m0
az

ma
b b b b

ya
m0
axz ma

X1Z ya y0

y0

y
y3 y
y4 y
y5 y
y6

ly2 ly3 ly4 ly5 ly6

1

Y2 Y3 Y4 Y5 Y6

Figure 1. LCSMM Model with Constrained Coupling for b

The following equations express this LCSMM model and correspond to the
path diagram in Figure 1.

∆lmti = mai + βm lmt−1i (13)

mai = aX1 X1 + aZ Z + aX1 Z X1 Z (14)

∆lyti = yai + βy lyt−1i + blmt−1i (15)

yai = c′ X1 (16)
In Equation 14, the mediation a path is distinguished from the other pa-
rameters in the equation with a subscript, aX1 , to denote that it is the path
relating X1 to the additive component of M. An interaction is formed by tak-
ing the product of X1 and Z, and this product is included in the equation as a
third predictor of the additive component of M by way of the parameter aX1 Z
(the interaction term). The main effect of Z predicting M is also included, as
represented by the parameter aZ .
The CIEs are estimated using the following equation.

abCIE = (aX1 b) + (aX1 Z b)Z (17)

 Latent Change Score Models with Moderated Mediation 13

This equation is quite similar to the CIEs introduced in Equation 8 from a

regression framework, although in this example b is a longitudinally constrained
coupling parameter rather than a linear regression path. To calculate CIEs from
model estimates, Equation 17 is programmed directly into the analysis script in
Mplus and R using MODEL CONSTRAINT statements. We use Wald tests of
significance (Wald, 1943) to assess the difference in the CIEs, therefore provid-
ing evidence of significant, stage one moderated mediation. The Wald test null
hypothesis was specified as

a(Z=0) b − a(Z=1) b = 0 (18)

Bootstrapping was also conducted to generate bootstrapped confidence in-
tervals of the respective CIEs and to determine their significance in terms of
inclusion of 01 .

3.1 Conditional Indirect Effect Interpretations

Table 2 contains results from the simulated example for which we provide in-
terpretation of the relevant estimates used in calculating CIEs. The mediation
a path was negative and significant (aX1 = −0.373), indicating that for a one-
unit increase in X1 , the additive component of M decreased by .373 units. The
coupling b path was also negative and significant (b = −0.146), indicating that
higher values of M were a leading predictor of lower values on Y. Using the joint
significance test, significance of the a and b paths resulted in a conclusion that
overall mediation was present (without consideration of the moderator), such
that higher values of X predicted a more negative additive component of M and
higher prior values of M predicted smaller changes in Y at each subsequent wave.

abCIE = (−0.373 ∗ −0.146) + (0.768 ∗ −0.146)Z = −.054 − 0.112Z (19)

The equation above resulted in CIE estimates of a(Z=0) b = 0.054 and a(Z=1) b =
−0.057. Bootstrapped confidence intervals of the CIE estimates did not include
zero, indicating that mediation was present at both values of the moderator.
The Wald test of equality supported results with respect to significance of
the moderation estimate, (χ2 (1, N = 520) = 106.830, p < .001), providing ev-
idence that moderation of the a path across values of Z resulted in significant
group differences in the CIEs. Considering all results from this model, we can
conclude that mediation was significant for both groups, and that the impact
of X on the additive component of M differed between the groups, resulting in
mediation CIEs that were both significant but with opposite signs (and signif-
icantly different from one another). Additionally, the power analyses described
previously demonstrated power approaching 1 for both CIEs.
1
The MODEL TEST command in Mplus cannot be used in conjunction with boot-
strapping, so if bootstrapped confidence intervals of the CIEs are desired, the Wald
test needs to be conducted in a separate Mplus script.
14 H. O’Rourke & C. Hilley

Table 2. Unstandardized Estimates from LCSMM Model, Constrained Coupling

Parameter Estimate (SE) Lower 95% CI Upper 95% CI

Univariate M
µm0 6.017 (0.04)*** 5.937 6.097
µma 0.833 (0.037)*** 0.761 0.904
βm -0.039 (0.005)*** -0.050 -0.029
2
σm0 0.466 (0.031)*** 0.404 0.527
2
σma 0.009 (0.001)*** 0.008 0.011
2
σe(m) 0.025 (0.001)*** 0.023 0.027
Univariate Y
µy0 6.964 (0.046)*** 6.874 7.055
µya -0.346 (0.175)* -0.683 0.002
βy 0.094 (0.015)*** 0.065 0.123
2
σy0 0.401 (0.028)*** 0.344 0.455
2
σya 0.045 (0.007)*** 0.033 0.059
2
σe(y) 0.105 (0.004)*** 0.097 0.112
Mediation/Moderation
c′ 0.115 (0.012)*** 0.092 0.138
aX1 -0.373 (0.008)*** -0.389 -0.357
aZ -0.006 (0.008) -0.022 0.011
aX1 Z 0.768 (0.011)*** 0.748 0.789
b -0.146 (0.015)*** -0.175 -0.117
aZ=0 b 0.054 (0.005)*** 0.044 0.065
aZ=1 b -0.057 (0.006)*** -0.069 -0.047
*p < .05, **p < .01, ***p < .001.

4 Example 2: Freely Estimated Dynamic Paths

In our second example, the b coupling paths were freely estimated across time.
The path model for this example is shown in Figure 2. The equation predicting
the LCSs for Y demonstrates how the model in this example differs from the
model in example 1:

∆lyti = yai + βy lyt−1i + bt lmt−1i (20)

In this equation, the b path is now time-dependent as denoted by the subscript
t such that coupling is freely estimated across timepoints. The estimation of
multiple b paths necessitated the calculation of multiple CIEs for a given value
of Z, as there were four LCSs and thus four corresponding b paths. With two
values of Z, eight CIEs were calculated, four each for aZ=0 bt and aZ=1 bt . Four
equalities of CIEs were specified in the Wald Test such that the CIEs were equal
with time held constant, resulting in the following null hypothesis for the Wald
test.

a(Z=0) bt − a(Z=1) bt = 0 (21)

Although four equalities were specified for the Wald test (one for each time-
point), only one χ2 estimate was provided for all of the tests. Therefore, in this
 Latent Change Score Models with Moderated Mediation 15

example the Wald test provided information on whether at least one of the sets
of CIEs differed between groups, considering all timepoints. Bootstrapping was
also conducted to produce confidence intervals of the individual estimates as well
as the eight CIEs.

M2 M3 M4 M5 M6

X1
lm2 lm3 lm4 lm5 lm6

m m m m

m3
m4
m5
m6

ax1
c'
Z m0
az

ma
b3 b4 b5 b6

ya
m0
axz ma

X1Z ya y0

y0

y
y3 y
y4 y
y5 y
y6

ly2 ly3 ly4 ly5 ly6

1

Y2 Y3 Y4 Y5 Y6

Figure 2. LCSMM Model with Freely Estimated Coupling for b

4.1 Conditional Indirect Effect Interpretations

Table 3 shows model results from this example’s estimation. As with example
1, the mediation a path was negative and significant (aX1 = −0.396) such that
a one-unit increase in X1 resulted in a 0.396-unit decrease in the additive com-
ponent of M. All b path estimates were negative and significant (b3 = −0.230,
b4 = −0.174, b5 = −0.127, and b6 = −0.072) where with each subsequent wave,
the magnitude of b weakened. As indicated by the trend toward zero in the b
paths, higher prior levels of M were associated with smaller subsequent changes
in Y, however this relation weakened over the course of the study. Both thea path
and all freely estimated b paths were statistically significant, supporting evidence
that mediation was present across all waves in accordance with the joint signifi-
cance test. The conclusions from these results can be interpreted such that higher
values of X predicted lower values of M over time, and subsequently higher prior
values of M predicted smaller changes in Y, with the prediction of M on change
in Y weakening over time.
16 H. O’Rourke & C. Hilley

Table 3. Unstandardized Estimates from LCSMM Model, Freely Estimated Coupling

Parameter Estimate (SE) Lower 95% CI Upper 95% CI

Univariate M
µm0 5.966 (0.04)*** 5.886 6.044
µma 0.905 (0.037)*** 0.831 0.977
βm -0.051 (0.005)*** -0.061 -0.041
2
σm0 0.465 (0.03)*** 0.404 0.522
2
σma 0.009 (0.001)*** 0.007 0.011
2
σe(m) 0.024 (0.001)*** 0.022 0.026
Univariate Y
µy0 6.95 (0.042)*** 6.869 7.032
µya -0.614 (0.201)** -1.019 -0.231
βy 0.116 (0.035)** 0.051 0.187
2
σy0 0.381 (0.027)*** 0.326 0.432
2
σya 0.034 (0.007)*** 0.022 0.05
2
σe(y) 0.101 (0.004)*** 0.094 0.108
Mediation/Moderation
c′ 0.105 (0.011)*** 0.085 0.127
aX1 -0.396 (0.007)*** -0.41 -0.382
aZ 0.004 (0.009) -0.013 0.022
aX1 Z 0.799 (0.011)*** 0.777 0.82
b3 -0.23 (0.019)*** -0.267 -0.192
b4 -0.174 (0.015)*** -0.204 -0.145
b5 -0.127 (0.013)*** -0.154 -0.101
b6 -0.072 (0.014)*** -0.1 -0.046
aZ=0 b3 0.091 (0.007)*** 0.076 0.106
aZ=0 b4 0.069 (0.006)*** 0.058 0.08
aZ=0 b5 0.05 (0.005)*** 0.04 0.061
aZ=0 b6 0.029 (0.005)*** 0.018 0.039
aZ=1 b3 -0.093 (0.008)*** -0.107 -0.078
aZ=1 b4 -0.07 (0.006)*** -0.082 -0.059
aZ=1 b5 -0.051 (0.005)*** -0.062 -0.041
aZ=1 b6 -0.029 (0.005)*** -0.04 -0.019
*p < .05, **p < .01, ***p < .001.

The interaction term representing the product of X and Z predicting the

additive component of M was positive and significant (aX1 Z = 0.799), indicating
that there were significant group differences on Z in the prediction of X on the
additive component of M. The influence of Z on the additive component of M
(main effect) was not significant. The CIEs were estimated by utilizing the model
estimates in the following equations:
abCIE3 = (−0.396 ∗ −0.230) + (0.799 ∗ −0.230)Z (22)
abCIE4 = (−0.396 ∗ −0.174) + (0.799 ∗ −0.174)Z (23)
abCIE5 = (−0.396 ∗ −0.127) + (0.799 ∗ −0.127)Z (24)
abCIE6 = (−0.396 ∗ −0.072) + (0.799 ∗ −0.072)Z (25)
 Latent Change Score Models with Moderated Mediation 17

Bootstrapped confidence intervals for the CIEs indicated that mediation was
significant at all timepoints for both values of the moderator, as each of the eight
confidence intervals did not include zero. With respect to group differences of
the CIEs, the Wald test was significant, χ2 (4, N = 520) = 200.045, p < .001,
indicating that at least one of the sets of CIEs at a given timepoint differed
between groups on the moderator. Additionally, Z moderated the influence of
X on M such that the aX1 path varied across values of Z which resulted in
intergroup CIEs of opposing signs, with at least one timepoint having statistically
significant group differences in indirect effects. As the Wald test does not give
us specific information on which of the pairs of CIEs differed significantly at
each time point, plotting the CIEs is a useful way to interpret the moderated
mediation effect from the LCSMM model. Figure 3 contains a plot of the CIEs
across values of b at each timepoint grouped at each value of Z for example 2.

Figure 3. Comparison of CIEs Across Groups for LCSMM Model with Freely Esti-
mated Coupling for b

This plot shows that as the estimate of b decreased over time, the difference
in the CIEs between values of Z also decreased such that at the final time point
the CIEs had the smallest difference. Code for reproducing this plot in R can
be found on GitHub. Additionally, power analyses demonstrated that power
approached 1 for all eight estimates of the CIEs.
18 H. O’Rourke & C. Hilley

5 Discussion

In this paper, we demonstrated an approach for specifying CIEs in LCSMM

models which can be used to address research questions about group differences
in mediation models of dynamic change over time. We illustrated two specifica-
tions of LCSMM models to show how binary group differences in indirect effects
can be examined within the LCS framework using a time invariant covariate
approach with a binary moderator when the mediation b paths are either freely
estimated or constrained to be equal across time. As the LCS framework con-
tinues to grow in popularity among applied researchers, the models described
in this paper will be useful for refining theories of behavior change, particularly
with respect to group differences in mechanisms of change.

5.1 Mediation Considerations

The models presented in this paper conceptualize the mediation paths as those
that predict additive components (in the case of the a path) and as coupling
parameters (in the case of the b and c′ paths), all of which involve a type of
change as the outcome. Although these specifications are in line with prior work
on LCS models with mediators (Hilley & O’Rourke, 2022), the mediation paths
could be specified differently with respect to change (e.g., a as the influence of X
on latent levels of M; b as the influence of prior latent levels of M on later latent
levels of Y; b as the influence of prior latent change in M on later latent change in
Y; etc.). Additionally, by specifying the a path as X → Ma , the models we have
presented are also more parsimonious than other options, like X → ∆mt . The
alternative specification may be more appropriate for certain research scenarios,
such as if the research question hypothesized that X would predict change in M
differentially over time (i.e., when the influence of X on change in M differs over
time).
Additionally, for each example the X variable was assumed to be a continuous
normally distributed variable. Quite often, researchers conducting studies with
hypothesized mediators measure X as a categorical randomized variable in an
attempt to address the no unmeasured confounders assumption of mediation
for the a path. The models presented here could easily be extended to include
interaction terms between categorical X and Z; for example, if X and Z are
binary, the product XZ could be coded as a 4-category variable. Goldsmith et
al. (2018) describe a modified LCS mediation model with a randomized, 4-group
variable for X (although CIEs were not specified for these models).

Causality Considerations As described in the introduction, the causality

assumptions inherent to mediation are what separate mediation from other types
of three-variable models, and this is true for mediation in any framework. We
now address several considerations that are specific to causality for mediation in
the LCS framework.
 Latent Change Score Models with Moderated Mediation 19

Temporal Precedence. The LCS framework provides both opportunities and chal-
lenges for examining mediators. To begin with the benefits, mediation in LCS
models can allow researchers to examine effects that are known to be lagged
and therefore temporal precedence is known to be met (e.g., X1 → ∆m2 −m3 →
∆y3 −y4 ), or a corresponding coupling specification). This is an advantage over
mediation models with cross-sectional data where X, M, and Y are all measured
at the same time (e.g., X1 → M1 → Y1 ). However, researchers must be de-
liberate in how they specify their indirect effects to match theories of change,
as specifying change-change paths for mediation can result in measurements of
contemporaneous change (e.g., ∆m2 −m3 → ∆y2 −y3 ) that do not satisfy the tem-
poral precedence assumption. Circumstances do exist where it is appropriate to
specify contemporaneous change paths, such as if variables are measured at the
same timepoint but prior research indicates an underlying causal process that
occurs at a faster rate than the measurement timeline can capture (Goldsmith et
al., 2018; Hilley & O’Rourke, 2022). The theory of change should always be con-
sidered when determining the specification of change for longitudinal mediation
models.

Potential Confounders of Mediation. The assumption of no potential confound-

ing influences with respect to establishing causality in mediation is often both
the most problematic in terms of influencing model results when the assumption
is violated, and the most difficult to address. When X is not randomized (and
as we have mentioned previously, M is very often not randomized), bias is intro-
duced into the estimates of each of the mediation paths where M and Y are being
influenced by unmeasured confounders. Some longitudinal mediation frameworks
(including the LCS framework) can partially address the issue of unmeasured
confounders influencing M and Y by including correlated measurement errors
between M and Y across timepoints, and the current recommendation is to use
contemporaneous residual covariances among M and Y at each measurement of
t (Goldsmith et al., 2018). Although they are not shown in our path diagrams,
we have utilized this method to address potential confounding in our examples;
all of the LCSMM models presented here include correlations between residuals
for M and Y at each timepoint. This method addresses the assumption of no
unmeasured confounders for the b path, but unless X is randomized, the assump-
tion is not met for the a path. When X is a cross-sectional observed variable in
a LCSMM model, it is recommended to use methods for dealing with potential
confounders that were developed for mediation models in the linear regression
framework (Hilley & O’Rourke, 2022; MacKinnon & Pirlott, 2015).

5.2 Moderation Considerations

We now turn to some considerations for the moderation portion of the LCSMM
model and calculations of the CIEs. In LCS models, coupling represents the ex-
tent to which prior levels of one variable influence later change in another. Thus,
with the specification utilized in this paper, the mediation b path is represented
by coupling between M and Y. In both examples, the moderator was a binary,
20 H. O’Rourke & C. Hilley

time-invariant variable influencing the mediation a path. However, as described

below, the LCSMM models presented in this paper can be extended to capture
moderation of the b path or moderators that are time-varying or continuous,
although additional methodological research is needed in these areas.

Continuous vs. Binary Moderators In this paper we demonstrated ap-

proaches for calculating CIEs in LCSMM models using only binary, time-invariant
moderators. It is important to note that if the moderator was continuous and
time-invariant, the covariate and multiple group approaches to estimation would
not give equivalent CIEs due to the adjustments that would have to be made
to the calculations for each approach. In the multiple group approach, prior to
estimation synthetic categorical groups would have to be created by categoriz-
ing the continuous Z variable. Assuming Z is normally distributed, this would
typically be done by using a “high/medium/low” binning schema separating
the data into thirds and then running a multiple group analysis for the binned
groups. However, this approach is not recommended in practice due to the loss
of variability stemming from binning a continuous variable (Altman & Royston,
2006).
In contrast, for the time-invariant covariate approach, the product XZ could
be computed and included in analysis in the same manner as it was in the
examples presented here. Researchers would then choose “high/medium/low”
values of Z for which to calculate CIEs (typically −1SD/M/ + 1SD when Z is
normally distributed). The time-invariant approach thus would retain all of the
original variability from the continuous moderator by including it in the model
as a product with X. By contrast, the multiple group approach estimates would
come from “groups” that are in reality just separated groups of the same sam-
ple. Thus, calculating CIEs from mediation estimates using the multiple group
approach would result in different CIE estimates as compared to using the co-
variate approach. This difference in estimates would be even more pronounced if
the continuous time-invariant moderator was not perfectly normally distributed.

XM Interactions in LCSMM Models In the introduction of this paper we

described two types of interactions involving mediation, first and second stage
moderated mediation. Each of these types of moderation involves interaction
with the predictor X and a moderator Z, and our examples throughout the paper
used only first stage moderated mediation models. However, a single mediator
model can be extended to include interactions between X and the mediator
M, with no additional auxiliary variables in the model (i.e., XM interactions).
The models we described here could be extended to include XM interactions as
well. Methods have recently been developed for estimating XM interactions with
latent variables using a causal (rather than traditional regression) framework
(Gonzalez & Valente, 2023), but the causal effects can easily be converted to
traditional CIEs for XM interactions (MacKinnon, Valente, & Gonzalez, 2020).
 Latent Change Score Models with Moderated Mediation 21

5.3 Constraint Considerations

Next, we describe a more conceptual consideration, which is how to choose

whether to constrain vs. freely estimate the b path (or other dynamic change
paths) in LCSMM models. The choice should ultimately depend on the re-
searcher’s hypotheses about change over time. Given a single research question,
it may sometimes make sense to either constrain or freely estimate dynamic
change paths based on the given timeline of a research study. As an example,
suppose we have a developmental theory where we expect to observe coupling
between social preference and antisocial behavior in adolescence such that social
preference is a negative leading predictor of adolescent antisocial behavior (Buil,
Van Lier, Brendgen, Koot, & Vitaro, 2017). A study that occurs over a one-year
period during adolescence might hypothesize that coupling between social pref-
erence and antisocial behavior is consistent over multiple measurements in that
relatively short study period, and thus constraining the coupling parameter to
be equal across timepoints will both result in best model fit and be consistent
with the theory. However, if the same study were conducted over a longer pe-
riod starting in early adolescence and across the transition to adulthood (when
salience of social preference theoretically increases), the best representation of
the developmental theory would be to freely estimate the coupling paths such
that they are allowed to strengthen over time.
Although the selection of framework for longitudinal data analysis should be
driven by the research question at hand, the examples provided in this paper
highlight some of the benefits and challenges of each type of model. For example,
when the coupling paths are freely estimated, researchers will obtain CIEs for
each of the estimated paths and each group of the moderator (e.g., in our ex-
amples where two levels of the moderator and four coupling paths from M to Y
resulted in eight CIE estimates). When these coupling paths do truly differ over
time, models that constrain them to be equal would be misspecified. However,
interpretation of the CIEs may be more cumbersome for models with additional
CIE estimates. The multiple group approach to estimation may present similar
challenges (i.e., difficulty interpreting estimates if the dynamic change paths are
freely varied across groups with many groups and many time points), but they
also allow further freeing of constraints that may be appropriate in a given re-
search scenario but that are not presented here (e.g., differences in initial level
or additive components).

5.4 Limitations and Future Directions

There are several important limitations to consider regarding our work on the
LCSMM models presented here. First, there has been limited methodological
research regarding LCS models with mediators and even less research regard-
ing LCSMM models specifically. Additionally, methodological research on LCS
models is also extremely limited in its consideration of studies with imperfect
data or methods (i.e., missingness, attrition, model misspecification, etc.) that
are likely to occur in real world research, and the discussions around these topics
22 H. O’Rourke & C. Hilley

are mainly limited to univariate LCS models. There is also a lack of established
effect sizes for comparing CIEs with respect to both intra-study magnitude (i.e.,
comparing CIEs within a given study) and comparisons of CIEs across stud-
ies for mediation models in the LCS framework; it is unknown whether estab-
lished effect sizes for mediation in the regression framework (Miočević, O’Rourke,
MacKinnon, & Brown, 2018) translate to the LCS framework as well.
In terms of future research directions, an important future direction will in-
volve consideration of moderators with various measurements in LCSMM mod-
els: Continuous moderators, time-varying moderators, and moderators of medi-
ation paths when X, M, and Y are all longitudinal and therefore each has uni-
variate dual change structures. The same consideration of calculation of CIEs
should be given to these different specifications of LCSMM models. Furthermore,
future methodological research should give consideration to how model misspec-
ification impacts statistical power and bias in estimates of CIEs when the theory
of change for the b path is misspecified (constrained vs. freely estimated) and
when the assumptions of mediation are not met.

5.5 Conclusion

There are many model specification choices to be made that influence the esti-
mation and interpretation of results from models fit within the LCS framework.
Some choices are universal to multivariate LCS models, and other choices are
specific to inclusion of moderators and mediators into LCS models. Some of the
general choices that influence model estimation and interpretation are: measure-
ment of variables (all variables measured longitudinally, or one cross-sectional
predictor predicting a longitudinal outcome); specification of longitudinal bivari-
ate relations (coupling, prior level predicting later level, or prior change predict-
ing later change); and both univariate and bivariate dynamic change parameter
constraints (proportional change and/or coupling specified to be equal across
time, or parameters freely estimated across time). The estimation and subse-
quent calculation and interpretation of CIEs in LCSMM models varies depend-
ing on each of the individual choices made during model specification. Often
many of these choices are pre-determined for us with respect to the structure of
our data, but several of the choices depend on either the theories about change
underlying a research question or the technical propriety of a particular option.
The present paper provides examples that demonstrate obtaining these CIEs
in LCSMM models under two different conditions for coupling from M to Y. We
also highlight some important considerations related to different components
of estimation of CIEs when both moderators and mediators are present in a
LCS model. LCSMM models provide researchers with the opportunity to exam-
ine more refined theories of mechanisms of change over time, particularly when
that change is dynamic and when there are group differences in mechanisms of
dynamic change.
 Latent Change Score Models with Moderated Mediation 23

References
Altman, D. G., & Royston, P. (2006). The cost of dichotomis-
ing continuous variables. BMJ , 332 (7549), 1080.1. doi:
[Link]
Alwin, D. F., & Hauser, R. M. (1975). The decomposition of effects
in path analysis. American Sociological Review , 40 (1), 37. doi:
[Link]
Baltagi, B. H. (2021). Econometric Analysis of Panel Data. Cham: Springer
International Publishing. doi: [Link]
Baron, R. M., & Kenny, D. A. (1986). The moderator–mediator variable distinc-
tion in social psychological research: Conceptual, strategic, and statistical
considerations. Journal of Personality and Social Psychology, 51 (6), 1173–
1182. doi: [Link]
Buil, J. M., Van Lier, P. A. C., Brendgen, M. R., Koot, H. M., & Vitaro, F.
(2017). Developmental pathways linking childhood temperament with anti-
social behavior and substance use in adolescence: Explanatory mechanisms
in the peer environment. Journal of Personality and Social Psychology,
112 (6), 948–966. doi: [Link]
Cheung, G. W., Cooper-Thomas, H. D., Lau, R. S., & Wang, L. C. (2021).
Testing moderation in business and psychological studies with latent mod-
erated structural equations. Journal of Business and Psychology, 36 (6),
1009–1033. doi: [Link]
Cronbach, L. J., & Furby, L. (1970). How we should measure
“change”: Or should we? Psychological Bulletin, 74 (1), 68–80. doi:
[Link]
Cáncer, P. F., & Estrada, E. (2023). Effectiveness of the deterministic and
stochastic bivariate latent change score models for longitudinal research.
Structural Equation Modeling: A Multidisciplinary Journal , 30 (4), 618–
632. doi: [Link]
Cáncer, P. F., Estrada, E., & Ferrer, E. (2023). A dynamic approach to control
for cohort differences in maturation speed using accelerated longitudinal
designs. Structural Equation Modeling: A Multidisciplinary Journal , 30 ,
761–777. doi: [Link]
Cáncer, P. F., Estrada, E., Ollero, M. J. F., & Ferrer, E. (2021).
Dynamical properties and conceptual interpretation of latent
change score models. Frontiers in Psychology, 12 , 696419. doi:
[Link]
Estrada, E., Bunge, S. A., & Ferrer, E. (2023). Controlling for cohort ef-
fects in accelerated longitudinal designs using continuous- and discrete-
time dynamic models. Psychological Methods, 28 (2), 359–378. doi:
[Link]
Goldsmith, K. A., MacKinnon, D. P., Chalder, T., White, P. D., Sharpe, M.,
& Pickles, A. (2018). Tutorial: The practical application of longitudi-
nal structural equation mediation models in clinical trials. Psychological
Methods, 23 (2), 191–207. doi: [Link]
24 H. O’Rourke & C. Hilley

Gonzalez, O., & Valente, M. J. (2023). Accommodating a latent XM interaction

in statistical mediation analysis. Multivariate Behavioral Research, 58 (4),
659–674. doi: [Link]
Gradinger, P., Yanagida, T., Strohmeier, D., & Spiel, C. (2015). Prevention
of cyberbullying and cyber victimization: Evaluation of the ViSC social
competence program. Journal of School Violence, 14 (1), 87–110. doi:
[Link]
Griffiths, S., Kievit, R. A., & Norbury, C. (2022). Mutualistic coupling
of vocabulary and non-verbal reasoning in children with and with-
out language disorder. Developmental Science, 25 (3), e13208. doi:
[Link]
Grimm, K. J. (2007). Multivariate longitudinal methods for studying de-
velopmental relationships between depression and academic achievement.
International Journal of Behavioral Development, 31 (4), 328–339. doi:
[Link]
Grimm, K. J., An, Y., McArdle, J. J., Zonderman, A. B., & Resnick,
S. M. (2012). Recent changes leading to subsequent changes: Ex-
tensions of multivariate latent difference score models. Structural
Equation Modeling: A Multidisciplinary Journal , 19 (2), 268–292. doi:
[Link]
Hamagami, F., & McArdle, J. J. (2001). Advanced studies of individual differ-
ences linear dynamic models for longitudinal data analysis. In G. A. Mar-
coulides & R. E. Schumacker (Eds.), New Developments and Techniques
in Structural Equation Modeling (pp. 223–266). Psychology Press. doi:
[Link]
Hayes, A. F. (2015). An index and test of linear moderated me-
diation. Multivariate Behavioral Research, 50 (1), 1–22. doi:
[Link]
Hayes, A. F. (2018). Partial, conditional, and moderated moderated media-
tion: Quantification, inference, and interpretation. Communication Mono-
graphs, 85 (1), 4–40. doi: [Link]
Hayes, A. F. (2022). Introduction to mediation, moderation, and conditional pro-
cess analysis: A regression-based approach (3rd ed.). New York ; London:
The Guilford Press.
Hilley, C. D., & O’Rourke, H. P. (2022). Dynamic change meets mechanisms
of change: Examining mediators in the latent change score framework.
International Journal of Behavioral Development, 46 (2), 125–141. doi:
[Link]
Hsiao, C. (2014). Analysis of panel data (3rd ed.). New York, NY: Cambridge
University Press.
Judd, C. M., & Kenny, D. A. (1981). Process analysis: Estimating media-
tion in treatment evaluations. Evaluation Review , 5 (5), 602–619. doi:
[Link]
Jöreskog, K. G. (1971). Simultaneous factor analysis in several populations. Psy-
chometrika, 36 (4), 409–426. doi: [Link]
 Latent Change Score Models with Moderated Mediation 25

Könen, T., & Karbach, J. (2021). Individual differences in intervention-related

changes. Advances in Methods and Practices in Psychological Science,
4 (1), 251524592097917. doi: [Link]
MacKinnon, D. P. (2008). Introduction to statistical mediation analysis. Rout-
ledge.
MacKinnon, D. P., Fritz, M. S., Williams, J., & Lockwood, C. M. (2007).
Distribution of the product confidence limits for the indirect effect: Pro-
gram PRODCLIN. Behavior Research Methods, 39 (3), 384–389. doi:
[Link]
MacKinnon, D. P., Lockwood, C. M., Hoffman, J. M., West, S. G., & Sheets,
V. (2002). A comparison of methods to test mediation and other in-
tervening variable effects. Psychological Methods, 7 (1), 83–104. doi:
[Link]
MacKinnon, D. P., Lockwood, C. M., & Williams, J. (2004). Confidence
limits for the indirect effect: Distribution of the product and resam-
pling methods. Multivariate Behavioral Research, 39 (1), 99–128. doi:
[Link] 4
MacKinnon, D. P., & Pirlott, A. G. (2015). Statistical approaches for en-
hancing causal interpretation of the M to Y relation in mediation anal-
ysis. Personality and Social Psychology Review , 19 (1), 30–43. doi:
[Link]
MacKinnon, D. P., Valente, M. J., & Gonzalez, O. (2020). The correspondence
between causal and traditional mediation analysis: the link is the medi-
ator by treatment interaction. Prevention Science, 21 (2), 147–157. doi:
[Link]
McArdle, J. J. (2001). A latent difference score approach to longitudinal dynamic
structural analysis. In Structural Equation Modeling: Present and Future.
A Festschrift in Honor of Karl Joreskog (pp. 341–380). Lincolnwood, IL:
Scientific Software International.
McArdle, J. J. (2009). Latent variable modeling of differences and changes with
longitudinal data. Annual Review of Psychology, 60 (1), 577–605. doi:
[Link]
McArdle, J. J., & Grimm, K. J. (2010). Five steps in latent curve and la-
tent change score modeling with longitudinal data. In K. Van Montfort,
J. H. Oud, & A. Satorra (Eds.), Longitudinal Research with Latent Vari-
ables (pp. 245–273). Berlin, Heidelberg: Springer Berlin Heidelberg. doi:
[Link] 8
McArdle, J. J., & Hamagami, F. (1996). Multilevel models from a multiple group
structural equation perspective. In Advanced structural equation modeling:
Issues and techniques (pp. 89–124). Psychology Press.
McArdle, J. J., & Prindle, J. J. (2008). A latent change score analysis of
a randomized clinical trial in reasoning training. Psychology and Aging,
23 (4), 702–719. doi: [Link]
Miočević, M., O’Rourke, H. P., MacKinnon, D. P., & Brown, H. C. (2018). Statis-
tical properties of four effect-size measures for mediation models. Behavior
26 H. O’Rourke & C. Hilley

Research Methods, 50 (1), 285–301. doi: [Link]

017-0870-1
Muthén, L. K., & Muthén, B. O. (2017). Mplus. Los Angeles, CA: Muthén &
Muthén.
O’Rourke, H. P., Fine, K. L., Grimm, K. J., & MacKinnon, D. P. (2022). The
importance of time metric precision when implementing bivariate latent
change score models. Multivariate Behavioral Research, 57 (4), 561–580.
doi: [Link]
O’Rourke, H. P., & MacKinnon, D. P. (2015). When the test of mediation is
more powerful than the test of the total effect. Behavior Research Methods,
47 (2), 424–442. doi: [Link]
O’Rourke, H. P., & MacKinnon, D. P. (2018). Reasons for testing mediation in
the absence of an intervention effect: A research imperative in prevention
and intervention research. Journal of Studies on Alcohol and Drugs, 79 (2),
171–181. doi: [Link]
Preacher, K. J., Rucker, D. D., & Hayes, A. F. (2007). Address-
ing moderated mediation hypotheses: Theory, methods, and prescrip-
tions. Multivariate Behavioral Research, 42 (1), 185–227. doi:
[Link]
R Core Team. (2020). R: A language and environment for statistical computing.
R Foundation for Statistical Computing, Vienna, Austria.
Raykov, T. (1999). Are simple change scores obsolete? an approach to studying
correlates and predictors of change. Applied Psychological Measurement,
23 (2), 120–126. doi: [Link]
Rosseel, Y. (2012). lavaan : An R package for structural equa-
tion modeling. Journal of Statistical Software, 48 (2). doi:
[Link]
Sardeshmukh, S. R., & Vandenberg, R. J. (2017). Integrating
moderation and mediation: A structural equation modeling ap-
proach. Organizational Research Methods, 20 (4), 721–745. doi:
[Link]
Selig, J. P., & Preacher, K. J. (2009). Mediation models for longitudinal data
in developmental research. Research in Human Development, 6 (2-3), 144–
164. doi: [Link]
Serang, S., Grimm, K. J., & Zhang, Z. (2019). On the correspondence be-
tween the latent growth curve and latent change score models. Struc-
tural Equation Modeling: A Multidisciplinary Journal , 26 (4), 623–635. doi:
[Link]
Simone, M., & Lockhart, G. (2019). Empirical sample size guide-
lines for use of latent difference score mediation. Structural Equa-
tion Modeling: A Multidisciplinary Journal , 26 (4), 636–645. doi:
[Link]
Sobel, M. E. (1982). Asymptotic confidence intervals for indirect effects
in structural equation models. Sociological Methodology, 13 , 290. doi:
[Link]
 Latent Change Score Models with Moderated Mediation 27

Usami, S., Hayes, T., & McArdle, J. J. (2016). Inferring longitudi-

nal relationships between variables: Model selection between the latent
change score and autoregressive cross-lagged factor models. Structural
Equation Modeling: A Multidisciplinary Journal , 23 (3), 331–342. doi:
[Link]
Valeri, L., & VanderWeele, T. J. (2013). Mediation analysis allowing for expo-
sure–mediator interactions and causal interpretation: Theoretical assump-
tions and implementation with SAS and SPSS macros. Psychological Meth-
ods, 18 (2), 137–150. doi: [Link]
Wald, A. (1943). Tests of statistical hypotheses concerning several
parameters when the number of observations is large. Transac-
tions of the American Mathematical Society, 54 (3), 426–482. doi:
[Link]
Zaccoletti, S., Camacho, A., Correia, N., Aguiar, C., Mason, L., Alves, R. A., &
Daniel, J. R. (2020). Parents’ perceptions of student academic motivation
during the COVID-19 lockdown: A cross-country comparison. Frontiers in
Psychology, 11 , 592670. doi: [Link]
Zhu, S., Sagherian, K., Wang, Y., Nahm, E.-S., & Friedmann, E. (2021). Lon-
gitudinal moderated mediation analysis in parallel process latent growth
curve modeling in intervention studies. Nursing Research, 70 (3), 184–192.
doi: [Link]