Questions tagged [confirmatory-factor]
Confirmatory Factor Analysis (CFA) is a set of multivariate techniques aimed at validating the relations between the observed variables, or indicators, and underlying latent variables, or factors, and is typically used to test and describe the underlying structure of psychological scales and other social science measurements.
413
questions
1
vote
0
answers
13
views
Lavaan and semTools partial measurement invariance syntax
I am running measurement invariance in Lavaan using a 7 item ordinal scale. I have been using Lavaan and semTools, and specifically the measEq.syntax command, due to the fact it easily implements Wu ...
- 95
1
vote
1
answer
48
views
EFA strongly suggests to extract a single factor. CFA 1-factor model fits badly. Why?
N > 1000. Average correlation in the matrix is like 0.8.
Parallel analysis, Minimum Average Partial, Scree plot, and Kaiser's criterion all unanimously suggested the extraction of a single factor. ...
- 11
0
votes
1
answer
28
views
Measurement invariance: Model fit increases with increasing constraints
I have run into the same problem repeatedly, namely that model fit increases with increasing model restraints.
I want to compare measurement invariance on a three-factor model (based on previous CFAs ...
2
votes
1
answer
29
views
"The model is probably unidentified" in AMOS - how to fix this?
I am trying to fit a second-order factor in AMOS (where 'AA', 'AB', and 'AC' are thought to be facets of the higher-order factor 'AD'). I am getting the error message "Result (Measurement model)
...
- 21
0
votes
1
answer
39
views
R syntax of a second-order factor analysis. Does it work if one factor from the first order only consists of 2 items?
I tried the following syntax:
...
- 131
0
votes
0
answers
16
views
Factor Analysis in Deep Learning
I'm new to deep learning and currently trying to use it for my project. The goal is to predict ship charter prices based on various factors that we have identified theoretically. In this project, we ...
0
votes
1
answer
32
views
define latent variables and measurment model in SEM
Does a latent variable in SEM need to be defined by validated scale or can you "imagine" one?
For instance, I work on school participation (defined in research by attendance to school and ...
2
votes
3
answers
89
views
Why do matrices of simulation data generated in R create strongly related latent variables?
When creating examples of matrices for CFA in R for students, I still have a problem with getting data that looks realistic - specifically, that between latent variables I often have covariance path ...
- 141
1
vote
1
answer
20
views
Can I compare a parallel and congeneric model with lavaan::anova()?
I want to compare two 1-factor models: (a) a congeneric model where the loadings are optimally weighted; and (b) a parallel model where the loadings are fixed to 1 (equally weighted).
...
- 733
0
votes
0
answers
41
views
lavaan - sem with second order factor problem
I have a model in which I set relationships among different variables. One of them is a second-order factor.
However, I get the following problem when I try to run the analysis:
Warning messages:
1: ...
- 1
0
votes
0
answers
46
views
is a threshold model on ordinal data ~ a link function? SEM OpenMx
Are anyone familiar with OpenMx's capacity for handling ordinal data in SEM using a link function like ordered logit or probit (Stata gsem does this)?
Some folks have highlighted issues with feeding ...
- 145
0
votes
0
answers
40
views
What are considered "voodoo fit indices" and "true"/"fake" standard errors? SEM CFA
In a conversation about fitting CFA with clusters and sampling weights (inverse probability weights) for ordered/ordinal/categorical data in R Lavaan, fit indices (GoF) were referred to as "...
- 145
0
votes
0
answers
12
views
Principal component analysis with a limited sample size
Thanks in advance!
I am attempting to quantify hospital resources using database derived variables that are all believed based on theory to be important for surgical patients.
There are about 70 ...
0
votes
0
answers
37
views
Keep or remove insignificant covariance values when modifying CFA model?
I am working to improve goodness of fit in a CFA model and am wondering about if I should retain added covariance values that are insignificant. I am adding covariances that are indicated by ...
- 11
1
vote
1
answer
41
views
Lavaan modificiation indices are already in CFA model?
I am trying to improve the fit for my CFA model below.
...
- 11
0
votes
0
answers
22
views
How is allowing residual covariances related to changing total score of a scale?
For what reason should I think about changing the total score of a scale if I allowed residual covariances for similar sounding items?
If I still work with all of the items should I think about ...
- 1
1
vote
2
answers
38
views
Risk perception measurement using CFA - Items with different scale
I am working on my risk perception model using three measures- probability, affection, and severity. I have one item on a Likert scale (1-5) for each probability and affection. However, for the ...
0
votes
0
answers
15
views
Is an achieved model fit of a measurement model (SEM/CFA) "more important" than a minimum level of factor loadings (e.g.: > .4)?
I have a SEM model with three factors. One factor is measured with 5 items. Two factors with 35 and 10 respectively.
Since the two factors with the many items did not produce a good model under the ...
- 41
0
votes
0
answers
25
views
What does it mean if one factor describes four measures, another factor describes other four measures, but both don't describe the eight measures?
I have 8 measures: A_1, A_2, A_3, A_4, B_1, B_2, B_3, B_4. I know from the correlation matrix that they are all related. I would like to find the latent variable structure.
Using lavaan in R, I found ...
- 702
0
votes
0
answers
20
views
Good factor loadings in a one factor model, but poor loadings once model is added to full SEM (lavaan - RStudio)
So I have been trying to reproduce a logistic SEM with a binary outcome (not relevant to this question). The sample size after removing missing values is around 820. One of my predictor latent factors ...
- 1
1
vote
0
answers
83
views
Is it possible to use Bootstrap Bias-corrected confidence intervals when performing SEM?
As far as I know, Co-variance based SEM requires the normality assumption. To avoid violating this assumption, I am considering using Bootstrap Bias-corrected method intervals for hypothesis testing ...
1
vote
0
answers
19
views
CFA with lavaan: Standard errors not computable [duplicate]
I am not that much experiencend in R and I want to run a CFA. The code is as follows:
...
- 11
0
votes
1
answer
142
views
Comparing multigroup CFAs: Improved fit with more restrictions
I have conducted a CFA for a one-factor measurement model and then proceeded to do multigroup CFAs to test for measurement variance for gender and age (binary variable, median split). Testing for ...
- 63
0
votes
0
answers
51
views
Split Sample for EFA and CFA with Smaller Dataset
I have a dataset (n=290) that I need to run an EFA. I was hoping to also run a CFA but I'm unsure if I have enough data to do a split sample approach. Please advise.
1
vote
1
answer
25
views
Adding invariance restriction leads to eigenvalue close to zero - can invariance be stated, nevertheless?
I am testing invariance between two groups. Configural and metric invariance is given. When adding the restriction of equal intercepts, lavaan gives me the warning that the smallest eigenvalue is ...
- 63
0
votes
0
answers
15
views
Is confirmatory factor analysis a way to validate a scale?
I am doing a translation and validation of a scale. I do not have any other measures, so I cannot do convergent/discriminant validity assessments. Is CFA enough to validate a scale, and if not what ...
1
vote
1
answer
107
views
Robustification in lavaan: Difference between M, MV and MVS?
In lavaan, I am running a two-factor CFA on a questionnaire with 28 items, all of which are scored on a 6-point Likert scale. In total I have ~350 participants who completed the questionnaire.
Because ...
- 11
2
votes
1
answer
104
views
plotting congeneric lavaan model
I would like to produce this type of figure from the article "Thinking twice about sum scores".
Figure 3 shows the path diagram of a congeneric model for the same data used in Fig. 1. The ...
- 733
0
votes
0
answers
10
views
how to compare CFA models with correlated disturbances?
using lavaan in R, I am fitting a 4-factor models using confirmatory factor analysis (based on a "validated" scale). As the original authors did, I let 5 residual errors (disturbances) of ...
- 1
1
vote
0
answers
21
views
Exploratory factor analysis (EFA) for transcriptomic data
I am doing an EFA for transcriptomic data (n=202, p=190). I did log-transformed the data because of skewness.
My question is, do I have to do false discovery rate (FDR) analysis at all prior to my EFA....
- 11
1
vote
1
answer
83
views
CFA with R - small sample size - also different outcomes at different times
I have the following problem:
We have a model of 3 latent variables with 8 observed variables each.
Our sample size is 19, which can't be upped because it is a special subgroup of the population and ...
- 25
1
vote
1
answer
46
views
Can I use result (latent variables) from CFA as input to ANOVA (dependant variable)?
I am currently writing a paper. And I am not sure if I can use latent variable defined through CFA, as a dependent variable in ANOVA. Thank you for help!
1
vote
0
answers
44
views
How to use CFA in R to justify averiging of Likert scale and further calculation
I am currently writing a paper for school and currently have 3 sections of questionnaire questions based on the Likert scale, where each section has 4 questions that I need to group together. Further, ...
0
votes
0
answers
16
views
Can i have different scale of EFA and CFA? Can the scales remove from EFA reincluded in the CFA?
I am developing a questionnaire for social science. The preliminary questionnaire has 35 items with 6 domains. However, one of the domains was optional ( 5 items), where only those who had been ...
- 1
0
votes
0
answers
96
views
Lag variables on OLS after PCA (Principal Components Analysis)
I have about 60 macroeconomic and financial indicators; all of them stationary (logs and differencing), with monthly data for the last 25 years. I am trying to predict changes in a financial variable (...
1
vote
1
answer
106
views
What is the discrepancy function in structural equation modeling?
Excerpt from Book
I am currently trying to improve my knowledge of structural equation modeling, and have been reading through Structural Equation Modeling with Lavaan by Gana & Broc to do so. ...
- 6,011
0
votes
0
answers
32
views
Equation of model to predict latent and observed variables
I'm struggling to interpret my SEM results and extract the "regression equation" that generates yhat. Using lavaan in R, this is my model that I want to estimate.
...
- 41
0
votes
1
answer
54
views
How to free the first indicator in a CFA, and set equality constraint with other parameters?
I want to test Tau-Equivalence in a CFA model, under LAVAAN. If I don't free the first item in a factor, it will be automatically set to 1 (reference indicator), so I fixed the factor variance to 1, ...
1
vote
0
answers
70
views
Interpretation of SEM - prediction
I am trying to model a behavior using the Theory of Planned Behavior (TPB) as my main framework.
I have an active survey; currently with 110 answers. I'm using R with lavaan to run the following model....
- 41
0
votes
2
answers
145
views
Interpretation of covariance in CFA vs regression in SEM
I have conducted a confirmatory factor analysis in lavaan (in the context of a group comparison). Moving on to structural equation modelling I realised that my hypothesized structural model is ...
- 1
2
votes
1
answer
325
views
Perfect CFI, TLI, SRMR and RMSEA in CFA
I have a CFA result which is puzzling me and I am trying to determine why I am getting the results I am getting.
I have a dataset of 134 rows. I have a factor which I run a CFA on using ...
- 253
1
vote
1
answer
476
views
Combine results from many likert scales in order to get a single response variable - PCA? CFA?
I'm helping a friend design his research. He'll use a Google Forms questionnaire with several questions (from 0 to 5, Likert scale) to assess anxiety of students' ...
- 641
0
votes
1
answer
59
views
How to analyze factor structure for multiple stimuli with experimental manipulation?
I have a scale that I would like to validate using CFA. The scale measures different aspects of fear of any given stimulus. In my first study, I had participants create their own stimulus and then ...
- 63
1
vote
1
answer
47
views
Factor analysis between two measures with different age range
is it totally meaningless or impossible to do factor analysis between two measures with different age ranges? For example, I want to test if two personality measures are testing the same underlying ...
0
votes
0
answers
18
views
Bifactor model fit evaluation
Many analytic and simulation studies have looked at the appropriateness of confirmatory factor analysis (CFA) & structural equation modeling (SEM) fit indices (e.g., the CFI, TLI, SRMR, & ...
- 1,152
1
vote
1
answer
222
views
How does an item intercept in CFA relate to the difficulty parameter in IRT?
I am having difficulty clarifying in my mind how item intercepts in Confirmatory Factor Analysis or SEM manifest, and how they are graphically represented in an IRT ICC plot. I understand that multi-...
- 95
0
votes
0
answers
25
views
One CFA Per Scale - What correction to make for multiple test statistics
I have a question that is very similar to One CFA for each scale, or one CFA for all of the scales together?
I have data-set (111*120) which is very wide. When applying a CFA it fails to converge ...
- 253
0
votes
1
answer
218
views
Constrained model demonstrates slightly better fit than the unconstrained model (Measurment invariance). Explanation?
I am currently examining measurement invariance in lavaan. I create my unconstrained model. Then I apply constrains to loadings and loadings+intercepts. I use the WLSMV estimator. The following ...
1
vote
1
answer
50
views
Principal component vs. Exploratory Factor Analysis [duplicate]
Problem: Which method should I use to observe whether there is one common factor/component explaining six different measures (i.e., face and objects)?
Study: In this study, we have four measures of ...
- 13
0
votes
0
answers
89
views
Variance standardization vs. marker-variable method in measurement invariance analyses
I am conducting measurement invariance analyses on a 6 factor CFA Model (+ 1 "method" factor that is set to be orthogonal to the 6 "theoretical" factors) with 33 indicators in a ...
