Questions tagged [sem]

Structural Equation Modeling is a multivariate technique popular in social sciences. It is based on formulating a set of linear relations between variables, some of which may be latent, and estimating the whole system, typically by analyzing the covariance matrix of the observed variables.

Filter by
Sorted by
Tagged with
2
votes
1answer
56 views

When does it make sense to apply SEM to experimental designs?

I've often seen it mentioned that while SEM is generally used in relation to non-experimental designs it can be used in relation to experimental designs too. For example, Kline (2016) writes that ...
0
votes
1answer
28 views

Skewed outcome variable, sem model: is it a problem?

My outcome variable is really skewed, and I want to include it in a SEM model (I am using lavaan - R). It is measured with a 7-points Likert scale (agreement) and consists of 5 items. If the model ...
0
votes
0answers
13 views

Path Model with (endogenous) Treatment - which model?

I have collected data on the intention to create a new business of my students. I measured it before the course (t1) and after it (t2). I have data on their absenteeism in class and the time they ...
0
votes
0answers
11 views

Using least squares to estimate variance of latent variable

I am having trouble understanding why I can't use least squares to solve an overdetermined system of linear equations using $\bf{x} = (\bf{A}'\bf{A})^{-1} \bf{A}'\bf{b}$. The same model estimated ...
1
vote
0answers
24 views

Multi-leveled data, how to model?

I am designing biochemical analyses of human brain samples. In a nutshell, we believe levels of some things are related to levels of other things that relate to levels of other things that relate to ...
0
votes
0answers
4 views

heterotrait-monotrait analysis with PLSPM

I am using the PLSPM package in R and conducted discriminant analysis by applying the Fornell-Larcker criterion. I would also like to conduct heterotrait-monotrait (HTMT) analysis. Are there any tools ...
0
votes
1answer
27 views

How to assess the significance of r2 values across models

I want to know whether (and how) I can test whether the difference in r2 values across two SEM models is significantly different. I have conducted a study where participants completed one of two ...
2
votes
1answer
27 views

Do I estimate factor loadings in a confirmatory factor anlysis (CFA) aimed at verifying an exploratory factor analysis (EFA)?

I decided to use a questionnaire published by another researcher (paper and supplementary here). In the article they perform an EFA, find two factors, and report the resulting factor loadings (...
3
votes
1answer
53 views

Structural equation models in econometrics vs psychology, political science, etc

Can anyone tell me if the sort of the sort of simultaneous equation/structural equation modeling of economic relationships that that was championed and to some extent developed out of the Cowles ...
0
votes
1answer
18 views

Does a poorly fitting CFA preclude SEM?

Trying to help someone with a Masters dissertation. I've run CFA in Jamovi on her questionnaire responses based on the assumed item/factor relationships. I don't really understand the various ...
0
votes
1answer
17 views

Can I import dataset with latent variables calculated, or do I need to define them in the syntax? [closed]

Lavaan tells you that you need to define latent variables for the analyses, however, I have imported a dataset from SPSS where I already created the latent variables, as this is easier than doing it ...
1
vote
0answers
17 views

Endogenous selection bias / d-separation in SEM (Structural Equation Modeling)

I am a psychology student and currently working on a paper about omitted-variable bias in structural equation modelling (SEM). I am trying to tie endogenous selection bias to parametric SEM to ...
0
votes
1answer
26 views

SEM: Comparing models when removing paths

I'm developing an SEM model for a study I've recently run. Essentially, I have 6 factors that are shown from previous research to predict one's performance in a specific task. My data is the ...
0
votes
0answers
8 views

Can formative measures contribute to latent slope/intercept through a MIMIC model?

I am interested in examining the global trajectory of V over 3 time points (as shown in the figure). Latent V is specified by 4 indicators and 4 predictors/formative indicators. We fixed the ...
0
votes
0answers
16 views

Evaluating mediator effect, through SEM model selection with AIC [duplicate]

I am new to SEM and the lavaan R package, so perhaps this is a basic question. I have social media data with three variables: ...
2
votes
1answer
16 views

SEM Configural invariance multigroup: how to calculate statistical significance of coefficients between groups?

I would like to know your opinion about the following issue. I am estimating a multi-group SEM model on two groups (urban vs. extra-urban). The theory behind states that the factor loadings could ...
0
votes
1answer
24 views

Is it ok to use polynomial model to fit logarithmically transformed data?

Can we use polynomial regression using logarithmically transformed data. I transformed both y and x1 and x2 variables by natural log. After this, I used polynomial regression to fit. when using poly(...
0
votes
0answers
22 views

How to test nomological validity with lavaan?

in my understanding, I need to test nomological validity with SEM. But what exactly should I look at in e.g. summary(fit1, standardized=TRUE, fit.measures=TRUE)? Code for reference: ...
0
votes
1answer
18 views

PROCESS macro or SEM for mediation model with latent variables

I am conducting a survey to analyze the effect of a binary variable X on a latent variable Y. The effect is assumed to be mediated by another latent variable M. Moreover, the effect of X on M is ...
2
votes
0answers
20 views

How to get one composite score to represent a MIMIC factor (including both formative variables and reflective indicators)

I have a MIMIC model where the latent variable of interest has both formative causes and reflective indicators (as depicted in the figure). My question is: is there a way to get one composite score ...
0
votes
0answers
26 views

Standardizing variables in lavaan (cross-lagged panel model)

I am running cross-lagged panel models with lavaan (3 time points, with and without random intercepts, as shown here https://jflournoy.github.io/2017/10/20/riclpm-lavaan-demo/ ). I noticed that when I ...
0
votes
0answers
45 views

Fix latent variable endogenous variance (NOT residual variance) in Lavaan

I am fitting some models using lavaan. I have a number of latent variables (specifically I am fitting ACE behavioral genetics models with multiple phenotypes). For the model to be interpretable the ...
1
vote
3answers
84 views

lavaan WLSMV estimator: are results reliable when number of observations is too small to compute Gamma?

I run CFA (confirmatory factor analysis) with WLSMV estimator (since my data are ordinal) in lavaan and I get the following warning message: ...
0
votes
0answers
12 views

Interpretation of Nominal Scaling in PLSPM

I used nominal scaling in PLSPM in R and I am uncertain how to interpret the results. I made a minimal code example from the satisfaction data set and made up a nominal value for color (red, blue, ...
0
votes
1answer
27 views

How to interpret weights of a PLS SEM model

I made a PLS SEM model using smartPLS, consisting only of formative constructs. I managed to get weights out of the software, which all had excellent t values. The only thing is, I am not entirely ...
1
vote
1answer
30 views

SEM: issue with two correlated latent variables

I am fitting a SEM model that includes socio-economic status (SES) for a household and environmental conditions (env) surrounding this household (road condition, sanitation etc). My (obvious) ...
0
votes
0answers
7 views

Convergent & Discriminant Validity -Same construct (measured by different meaures) in two different samples

I don't know how to go about looking at the Convergent & Discriminant Validity of the same construct measured with two different scales in two different contexts. This is a cross-cultural ...
1
vote
1answer
26 views

What statistical analysis should I use for comparing multiple variables at different time frames? (psychology experiment)

I'm planning a longitudinal psychology experiment where I want to compare levels of different variables over the course of an 8-week treatment. i.e. I want to see any increase/decrease in variable A, ...
0
votes
0answers
22 views

How to interpret contradicting path coefficients and f² effect sizes in Structural Equation Models (SEM)?

In the evaluation of my structural equation model with the PLS-SEM approach I have path coefficients between two constructs that are significant (p-value < 0.000) but the effect size f² is small ...
0
votes
0answers
41 views

Standard error for difference between two independent gains

I've calculated an effect size for the difference between two standardized pre-post differences of two independent groups of subjects. That is: $[Mean_{dif_{group~1}}/SD_{dif_{group~1}}]-[Mean_{dif_{...
0
votes
1answer
60 views

Path Analysis with multiple mediators and predictors

I recently started studying SEMs and path analysis in particular to analyze a data set. I have the following model, and I want to make sure I specified it correctly with ...
0
votes
0answers
24 views

Is it reasonable to include both principal component analysis (PCA) and Structural Equation Modeling (SEM) into a single regression?

Seems a bit silly to do both. Using PCA cleans up the way the model looks, bu reducing number of variables, but it seems like you would suffer an (unnecessary) loss of information.
0
votes
1answer
26 views

SEM 4 questions - testing linearity, sum score, number of variables, independent variables

For my master thesis I'm making a structural equation model. However, I do not have much experience with this. So here are some different questions. I read that one of the assumptions important for ...
1
vote
1answer
38 views

Estimating common slope across two traits for a parallel growth curve model

I am using a parallel growth curve model with 5 waves longitudinal data to evaluate correlated change among 2 traits. For models that showed the effects of correlated change among traits, I'm ...
4
votes
1answer
54 views

Why is RMSEA typically reported with a 90% confidence interval, and not 95%?

Kline (2016) writes that [RMSEA] is usually reported in computer output with the 90% confidence interval $[\hat{\epsilon}_{L},\hat{\epsilon}_{U}]$ where $\hat{\epsilon}_{L}$ is the lower-bound ...
0
votes
0answers
15 views

How do I do what I think would be a simple SEM?

I have the following data sets: miRNA levels in brain (one miRNA) protein levels in brain (two proteins) Clinical measure. It is known that the miRNA regulates the two proteins' translation from ...
0
votes
1answer
15 views

Does adding more than 1 dependent variable to SEM have purpose other than to control for correlation between dependent variables?

I am pretty new to SEM, so when I first saw a SEM model with 2 DVs, I wanted to know the difference between having 2 DVs and running SEM process twice for each DV. From what I understand, having more ...
1
vote
0answers
30 views

Markov property of manifest variables in longitudinal ESM

I am working on a longitudinal ESM model were the indicators are (highly) autocorrelated. This means that the classic cross-lagged models of panel data analysis cannot be used directly. I have ...
1
vote
2answers
93 views

In CFA, does it matter which factor loading is set to 1?

I'd been previously taught that, aside from the fact that fixing a loading to 1 means you won't get a significance test on that loading, it was totally arbitrary which loading got fixed to 1. However,...
0
votes
0answers
25 views

Multi-group SEM: what steps in measurement invariance

Sorry for asking a stupid question but I had been struggling for quite a while now. I'm not sure what steps to talke to evaluate a moderating effect in a path analysis model. I now have a path ...
1
vote
0answers
30 views

Do I report the pvalue of the standardized or unstandardized factor loading in CFA/SEM?

Using lavaan, for a simple CFA or SEM with measurement tools, you can use parameterEstimates(fit, standardized=TRUE) to get the standardized factor loadings for the ...
0
votes
0answers
14 views

Non-collapsibility issue in OR and mediation analysis with binary DV, binary mediator and 3-category IV

I have been looking for theory and software implementation to solve for non-collapsibility issue in mediation analysis with categorical DV and mediator (and IV). In my case, the DV and mediator are ...
1
vote
1answer
20 views

EFA over time where changes in the factors are of interest

I am asking to find out if an idea that popped into my head is a real thing or just silly. EFA often presumes the data are static. I know there are forms of EFA that take time into account, but I ...
2
votes
0answers
44 views

Longitudinal CFA/SEM with autocorrelated/autoregressed indicators (in R, better with lavaan)

The problem is, I am trying to fit a multilevel factor model to highly autocorrelated (in fact, autoregressive) indicators. More specifically, I have multiple measurements (60-70) per person (5-10 ...
1
vote
1answer
68 views

Checking error covariances between indicator variables in sem/cfa

I'm learning SEM/CFA, and am currently following Beaujean's (2014) book on using lavaan. In the chapter where he talked about CFA and the number of indicator variables to have to ensure the model ...
0
votes
0answers
9 views

SEM resources from a linear model prospective

I'm starting a new project at work that requires theory and application of structural equation models, but my background is quite low in this area. I have a very good background in regression, linear ...
0
votes
0answers
529 views

Latent variable interaction: different number of indicators 4 vs 1

I am trying to calculate a latent variable interaction using the unconstrained product indicator approach (Marsh 2004) with double centering (Lin et al. 2010). My data: two latent predictor ...
2
votes
0answers
41 views

Why item discriminations are missing in IRT GRM, estimated as a part of the Structural Equation Model? [closed]

I have run a Structural Equation Model that has four latent constructs (FI, SC, EM and RB) in R. All of the factors are continuous. Meanwhile, indicators are all ordered categorical variables measured ...
1
vote
1answer
77 views

Help moving forward after modIndices() in lavaan

I’m running a model in SEM using lavaan. I’ve really run into a puzzle I can’t quite seem to solve and I would love to tap into everyone’s expertise to help provide some direction. Below I’ve added ...
0
votes
0answers
12 views

How does explained variance in within level variables influence across-level-relations in multilevel SEMs?

Firstofall: I am sorry I cannot provide a minimal example code. I am trying my best to generalize the problem, but yet I just couldn't recreate it with dummy data. I try to provide any information ...