# Questions tagged [structural-equation-modeling]

Structural Equation Modeling is a multivariate technique. 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.

1,034 questions
Filter by
Sorted by
Tagged with
11 views

### Building model for SEM: the problematic of highly correlated variables (SEM + Covariance)

I have recently come across articles suggesting we should avoid conducting SEM when variables are highly correlated. I have a model in which X1 and X2 predicts Y through M1 and M2. Which gives me the ...
• 1
1 vote
12 views

### Chi-Square Difference Test for Nested Models with a Continuous Outcome

Apologies if this is a very basic question - I'm still definitely a beginner when it comes to statistical tests. I understand that chi-square tests are conducted to determine the relationship between ...
• 11
3 views

### p value vs goodness of fit in sem

I analyzed data with the path model using SEM. There is no measurement model or latent variables in my analysis. My objective is to find the direct or indrect effects of some the independent variables....
16 views

### In lavaan, how do you allow all manifest indicators to covary?

When building and developing a model with lavaan, e.g., ...
• 101
39 views

### What are, really, structural equation models?

I can't really find a clear description of how SEMs work, or even whether they are a really unified thing or just a bunch of other methods that people refer to as a whole. The definitions one finds ...
10 views

### cross-lagged-model (sem) with moderators

I have longitudinal data and want to do structural equation modeling in form of a cross-lagged-analysis with three moderator variables. My variables are attractiveness (x_t), self-worth (y_t), age (A),...
13 views

### FIML in growth mixture modelling

I have a question about Full Information Maximum Likelihood (FIML). I’m fitting growth mixture models to outcome variables measured at three timepoints. Some individuals are missing outcome data at ...
39 views

### Chi square of 0.00, but acceptable (other) fit indices?

I am running a path analysis for a sample of 75 participants using RStudio. I am comparing two models and have to decide which one to use (I am in favor of Model A, but because of the Chi-square: 0, I ...
6 views

### What is a "method factor" in confirmatory factor analysis and structural equation modeling?

Researchers employing structural equation models and confirmatory factor analyses often choose to include a "method factor" in their models. My understanding is that this is intended to ...
• 318
9 views

### Questions for calculation power/sample size in (multi group) structural equation modeling

I will measure a certain characteristic in an intervention group and in a control group over four points in time. I want to construct a latent change score model to check if the groups develop ...
• 111
29 views

### Include manifest variable in SEM without association to any other variable?

I would like to know whether a model that assumes a correlation between my latent and my manifest variable has a better fit than a similar model without this correlation. I am using SEM for this in ...
• 93
14 views

### Attempting to recreate official Stata SEM example in the R-package lavaan [migrated]

I want to recreate this official Stata example with the R-package lavaan. I am using the same data and graphically it looks identical. My issue is that the ...
• 239
14 views

### SEM in Lavaan in favor of comparison

I am struggling with properly applying the lavaan package in R to estimate the latent variables and their relationships with the observed variables in my data ...
1 vote
71 views

### could not compute modification indices; information matrix is singular. error message, sem with formative dependant variable in Rstudio

I'm trying to build a covariance-based structural equation model, more precisely a mediation model, using both reflective and formative specifications of latent variables. The purpose of that ...
13 views

### Difference or similarity in latent variables or SEM models

There are five latent variables (three independent and two dependent) which constitute a PLS-SEM model. A single survey was conducted; however, the questions were asked twice to the same participants. ...
14 views

### Covariance based SEM and GOF indexes

I have some questions all related to SEM models. I am just estimating a SEM model in R using the function sem. The model looks like this: ...
• 57
24 views

### What is the difference of bootstrapped standard error and lavaan default output standard error?

I am doing sem with lavaan in R, and I found that even I don't input the bootstrap parameters, the output of ...
• 15
1 vote
19 views

### Required sample size of CFA using power analysis from semPower

I want to conduct a confirmatory factor analysis (CFA) for a model with 4 latent variables and 60 indicator variables (15 per factor, uncorrelated factors, hence 1,710 degrees of freedom, that is, ...
11 views

### For path analysis, how do I check if I've specified the model using the correct distributions?

I'm using the R package piecewiseSEM to test a path model. All of the refernces I've read so far appear to discuss using directed separation, Fisher's C statistic, and AIC to test the overall ...
• 293
54 views

### Which is the measurement invariance level necessary for a multiple regression analysis?

I am interested in running a multiple regression model to test the association between a predictor variable x and an outcome variable y and control by some confounders variables (e. g. gender, age). ...
1 vote
34 views

### Path analysis with missing data and dichotomous exogenous variables in lavaan

I am currently working on a path analysis in lavaan with many predictors, some of which are dichotomous. My sample size is 386 and I'm doing an exploratory study with many potential predictors ...
• 11
1 vote
32 views

### Can you statistically compare two indirect effects in metaSEM?

I'm conducting a meta-analytic structural equation model (MASEM) using the two-stage approach in metaSEM in R. I have fit a model with two indirect effects, and ...
• 13
1 vote
13 views

### Structural equation software can seemingly do factor analysis with more variables than observations

I have discovered that the function umxEFA in the R package umx can do a factor analysis with more variables than observations. A normal factor analysis cannot do this because the covariance matrix ...
• 133
9 views

### Does the Bollen-Stine procedure in AMOS affect fit indices?

My colleagues and I are working on a cross-cultural study and we attempt to obtain evidences of factorial validity by doing a measurement invariance analysis. Since our data failed to meet the ...
1 vote
36 views

### Latent moderated Regression / SEM in Lavaan

I am trying to build a SEM in lavaan to determine the stability of a personality trait across three measurement time points. As per the theory the stability of a trait is given by the standardized ...
• 11
8 views

### Regression: structural estimation

I have a question related to econometrics in corporate finance. My question is: Is structural estimation the same as structural equation modeling?
48 views

### When to add covariances of mediators [SEM]

I have just created my first mediation model using sem() with the lavaan package in R. I am using a bootstrapping with 5000 resamples and BCA to calculate the confidence intervals at a 0.9 level. Now, ...
23 views

### How do I put moderators into a latent change model? (structural equation modeling)

I want to compare a group with a traumatic life event to a group without such an event in regards to certain symptoms over time (variables S1, S2, S3). I expect the symptoms to increase much stronger ...
• 111
33 views

### Why don't I have metric measurement invariance even with very small differences between factor loadings across groups?

Background: I'm running a multi-group model in lavaan. It has two groups: One clinical sample (n = 160) and one healthy control sample (n = 248) that I chose to be comparable regarding age, gender and ...
• 37
29 views

### Struggling for simultaneous equation models

Recently, I have been reading the paper "Refinancing risk and cash holdings" by Jarrad Harford. This is a simple example of his model: $$y_1 = a_0 + a_1 y_2 + a_2 Z_1 + v$$ y_2 = b_0 + b_1 ...
31 views

### Lagged predictors in irregular-time / asynchronous / time-unconstrained data

In growth curve modeling or other approaches, when time is constrained/synchronous/regular (i.e. panel/wave data; all observations occur synchronously), lagged prediction is trivial - simply add t-1 ...
62 views

### Why do our devices fail?

I would like to figure out why some devices of my company fail. Therefore, I'm able to use a list in which around 300 devices are listed together with about 70 parameters while only half of it is ...
• 2,197
1 vote
33 views

### Reasons to prefer low bias with higher variance over the alternative (and vice versa)

I am trying to understand the bias-variance tradeoff in practice. I have read several related questions and answers, but still have a few questions: Assume we are estimating a structural equation ...
39 views

### Fit indices showing "na" in lavaan path analysis using DWLS

I am doing a path analysis using lavaan in R. I have two models of interest: Model 1. Model 2. As one of the variables in the model is ordinal, I specified the ordered="Y2" command when ...
• 55
1 vote
53 views

### Multi-Group SEM in R to compare latent covariances: Fix factor variances or factor loadings?

I am using Structural Equation Modeling (SEM) in R with the lavaan package. I would like to compare four groups of children regarding how strongly their processing speed (PS) and their working memory (...
• 37
13 views

### Interaction effects in latent variable models in OpenMx

I've been trying to figure out the best approach to model interaction effects between latent variables in OpenMx. Umbach et al (2017) and Cortina et al (2021) both provide an overview of the existing ...
• 133
86 views

### SEM: How to report latent factor relationships (covariance vs. correlation)?

I would like to report results from SEM I did in R using the lavaan package. I have gotten increasingly confused about how papers use different terms and units to describe latent factor relationships ...
• 37
1 vote
15 views

### How to compare nested multilevel path models

I have two multilevel path models, one is nested in the other and I want to compare the models to see whether I should prefer the full or nested model. The models have cross-level interactions and I ...
• 11
18 views

### R-square vs. NFI?

I ran a path model (no latent variables) in smartPLS3. It's not a complicated model. But after the analysis was computed, I checked the model fit measures. R-squares are small (all of them < .3), ...
• 77
82 views

### Estimated covariance matrix and sample covariance matrix of SEM

Normal Covariance I have tried looking high and low for an answer to this question, but I seem to never get a great answer on it. First, I think I'm knowledgeable about what a covariance matrix is. It ...
42 views

### Longitudinal Latent Change Score Modeling with Lavaan in R

I have the following data set: ...
• 239
25 views

### How analyze annual data with one IV and multiple DVs

I'm currently working with a data set that includes multiple variables associated with each of 10 years of data. The basic structure, with (example hypothetical) variables in caps, is from YEAR to ...
• 31
19 views

### what are the right or common steps to successfully build a structural equation model?

I have learned theories about structural equation modeling but don't have enough experience building a structural equation model. I have spent too much time struggling with building a good SEM. I have ...
1 vote
56 views

### How to convert SMART-PLS structural coefficients from standardized (correlation) to unstandardized?

I need use smartPLS but i also have prediction purpose (coefficients should also act like b-coefficients of regression). How to do this in smartPLS, since all coefficients are standardized?
• 77
1 vote
19 views

### How to report and interpret a parameter of a SEM model with categorical and continuous variables

I have conducted a SEM model in MPlus where X and Y are categorical and M is continuous. So the path from X to Y are log odds, the path from X to M are betas, and the path from M to Y are log odds. I ...
• 11
1 vote
19 views

### Manual Calculation of SEM Factor Scores

I am trying to re-create the factor scores computed by AMOS for a latent construct. However, I get a very different answer when using the "Estimates" for the variables than when AMOS ...
1 vote
147 views

### MLE on Structural VAR

I have a simple model that I wish to fit using data. The model is of the form below. \begin{gather} y_t = -\lambda r_t + \theta a_t + \varepsilon_1 \\ \\ \pi_t = \pi_{t-1} + w y_t + \varepsilon_2 \\ \\...
• 117
8 views

### Multilevel modelling weight

I want to use a nation-wide dataset which is associated with individual level weight to show the population in the US that is represented by the sample, and county-level sociodemographic census ...
• 1
81 views

### Potential Outcome (PO) vs Directed Acyclic Graph (DAG)

Recently I encountered this article of Prof. Imbens (https://arxiv.org/pdf/1907.07271.pdf). It address the capabilities of DAGs for causal inference in comparison with PO. I’m interested in opinions ...
• 4,064