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 describe the underlying structure of psychological scales and other social science measurements.
331
questions
0
votes
0answers
5 views
When to use k * (k+1)/2 (e.g. covariances and variances) vs. k * (k-1)/2 (e.g. variances only) for number of observed statistics in CFA/SEM?
Two formulas are often used for estimating the number of observed statistics in a CFA or SEM. Either:
k * (k+1)/2 for the lower triangle of covariances and variances
k * (k-1)/2 for the lower tiangle ...
0
votes
0answers
4 views
Is valid to conduct a CFA if p(CMIN) is significant
I conducted a CFA (confirmatory factor analysis).
My values are:
...
1
vote
0answers
9 views
What is “addition unique variance” in structural equation modeling?
I am studying confirmatory factor analysis and playing around with $\Omega\text{nyx}$. In the user guide, there is the following sentence:
By default, a double-headed loop is created with each ...
0
votes
0answers
26 views
Bifactor model - Factor variances
I am estimating a bifactor model, i.e., a model including a general factor (G) and 4 specific constructs/factors (S1-4), all orthogonal (see below). The fit for the model is surprisingly good (CFI/TLI ...
0
votes
0answers
7 views
If the factor has only two indicators in CFA, the errors of those two indicators cannot be correlated?
I have heard that if the factor has only two indicators in CFA, the errors of those two indicators cannot be correlated. Is it true? if so, I'm wondering if the issue is due to only identification or ...
1
vote
1answer
25 views
What does it mean to indicate correlation in lavaan CFA?
I am an undergraduate psychology student and I've been doing basic statistical analysis for professors, post-grad students, etc for their work. I use R for almost everything
I've recently faced myself ...
0
votes
0answers
9 views
Q: R, SEM with lavaan, problems specifying correlations between subscales. ERROR: Warning, could not compute standard errors
I am currently working on running a SEM analysis in Lavaan and I am running into a few problems. Before running the full sem, I intended to run a CFA to replicate the psychometric testing done with ...
0
votes
0answers
13 views
can I test for invariance if the base model has poor fit in CFA?
I am doing confirmatory factor analyses on a number of datasets where I want to confirm both factor structure and measurement invariance across groups, using lavaan in R. If the base model (before ...
0
votes
1answer
58 views
How to test a difference between two regression coefficients in SEM (CFA, Lavaan)
I have a simple CFA model, where there are 4 latent factors, each including 4 manifest variables, and there are covariation among all factors. The model is estimated on ~180 individuals.
...
0
votes
0answers
16 views
Invariance for CFA in multiple groups over time with lavaan in R
Essentially, I am having trouble testing for invariance for a CFA in multiple groups over time. I am trying to do this with the lavaan package in R.
I am following Little (2013) and attempting to do a ...
0
votes
0answers
25 views
Multi-group CFA analysis - two different outcomes
I have four first-order factors explained by one second-order factor. I am going to test the second-order factor across two different groups, one in Poland (group 1) and one in Spain (group 2). Also, ...
0
votes
1answer
19 views
CFA in AMOS vs. R: Different modification indices and standardized errors
I am doing a confirmatory fator analysis and I do obtain different results in SPSS AMOS vs. R/lavaan.
All parameter estimates, df and standard errors are the same. Yet, standardized residuals and ...
0
votes
0answers
24 views
Bifactor-model in Mplus - warning message: PSI is not positive-definite
This question is about: When does the warning massage appear?
I have a rather complicated model in Mplus that consists of three individual models. Each model consists of several manifest variables ...
0
votes
0answers
15 views
Defining single indicators for CFA and covariance in Lavaan (R)
I am struggling with performing my very first confirmatory factor analysis (CFA) and structural equation model and I am already stuck. For reference, I am using the Lavaan package in R. I am ...
0
votes
0answers
16 views
Correlation Analysis on a MICE Dataset
This question is similar to one that was asked almost 10 years ago but never got answered. I want to perform a CFA on a data set mainly consisting of categorical data. It also contains around 2-3 ...
0
votes
0answers
7 views
Exhaustive reading of Factor Analysis [duplicate]
I have learned EFA and CFA in SPSS/ AMOS and a basic understanding of why they work (but in a non-mathematical way, which makes me feel I might have some fundamental misconceptions, and hence this ...
1
vote
0answers
19 views
In confirmatory factor analysis, what is the notation for the modification index?
What symbol or abbreviation can we use to refer to the modification index? Say you were writing an article about a CFA that was performed and inside of the article you want to list several ...
0
votes
1answer
18 views
Could not compute standard errors in lavaan but why?
I am estimating a two-factor model in lavaan via sem(). I try and estimate this model in two different ways that should be equivalent (unless I am missing something) but one way gives an error ...
1
vote
1answer
20 views
Best practice for establishing configural invariance?
I was hoping for some perspectives on the best practices for establishing configural invariance using ordered indicators with WLSMV estimation. I have a 3-factor scale and I am assessing invariance ...
0
votes
0answers
26 views
What is the best approach to examine the dimensionality of related behaviours and to develop theory?
I’m preparing a study whose main goal it is to explore whether a set of related behaviours are best conceptualized as one-dimensional or two-dimensional. Traditionally, such questions have been ...
0
votes
0answers
23 views
DWLS applicable for 7-Likert scale CFA?
I am writing my undergrad business thesis and I am new to CFA. I did a CFA for 7-Likert Scale Data (Sample Size 210, 8 Factors, 36items) which resulted in poor model fit with the classic MLR estimator ...
1
vote
1answer
15 views
Structural equation modeling for habitat suitability
I am new to the concept of SEM. Yet, after reading about SEM it seems quite promising to give me a better understanding about how influential/important a set of measured variables (in respect to each ...
1
vote
0answers
142 views
Interpreting Omega coefficients (reliability) from EFA and CFA
I have a dataset with 5 variables and I would like to estimate the reliability of the scale score computed as the linear combination of all items (n = number of items), that is $O = \sum_{i=1}^{n}(X_i)...
1
vote
0answers
18 views
CFA, 1 latent variable, 3 observed, saturated, how to continue?
For a survey on work satisfaction and health containing multiple constructs (for stress, intrinsic motivation, anxiety, quality of life), I need to confirm the unidimensionality of each construct. ...
1
vote
1answer
77 views
SEM Instead of MANOVA
I do not have sufficient reputation to comment on a question, so I hope this post is acceptable.
Regarding the accepted answer to this question:
How to do Simple Confirmatory Factory Analysis/SEM in R?...
1
vote
0answers
43 views
How to interpret standardized coefficients for latent variable in CFA?
I am fitting a CFA model with the following syntax from lavaan package:
...
0
votes
0answers
8 views
If I have a second order model that runs great, do I need to run first order model to evaluated if I can use the small constructs?
I have already posted this question on https://groups.google.com/g/lavaan/c/CZAyEDBNUwk . However, as this is more theoretical, I think that more people will be happy to help here.
I have a survey ...
1
vote
0answers
96 views
Lavaan CFA with lots of cross-loadings solution not found
I am having some trouble getting my CFA to converge. There are lots of cross loadings and one factor with two indicators, both of which I think may be contributing to the error. Here is a reproducible ...
1
vote
0answers
21 views
What are the solutions for small sample in SEM?
is bootstrap a solution? I use Lisrel 8.8 (the student version) and bootstrap actually does not work in it. Bootstrap S has N/A values.
0
votes
0answers
21 views
How to calculate convergent and discriminant validity in SEM?
Using the average variance extract (AVE), the method is explained easily by doing some calculations on the factor loadings. I only found such procedure on CFA models, where we don't have an endogenous ...
0
votes
0answers
69 views
Comparing the means of latent variables in a CFA model measured at two different times in R
I have a CFA model with 7 latent variables and about 4 items per construct, I'm using R with lavaan for the CFA, $N\approx 3500$.
My model looks like this:
...
0
votes
0answers
34 views
Unrefined scores for confirmatory factor analysis
I have read the paper entitled "Understanding and Using Factor Scores: Considerations for the
Applied Researcher" by C. Distefano, M. Zhu, Diana Mîndrilă (2009), Practical Assessment, ...
1
vote
0answers
26 views
How to find degree of freedom in SEM-CFA model? [Inquiring Clarification]
I found a link that explains it.
http://reifman-sem.blogspot.com/2007/04/some-of-students-wanted-review-of.html
It is
$$Degree \;of\;Freedom (DF) = Total \;Elements - Total \;Free \;Parameters$$
[...
0
votes
1answer
165 views
How to interpret the negative variances
I had used the already published Likert scale for the survey. And the responses to the survey from 98 participants were collected. The survey likert scale was from <...
0
votes
0answers
21 views
Evaluating discriminant validity of a 2nd order reflective construct?
I am currently assessing my measurement model which includes-besides other constructs-a 2nd order reflective construct (consists of four 1st order constructs that are also reflective).
I noticed that ...
3
votes
1answer
39 views
Standard errors and p-values in exploratory factor analysis
I was wondering why there are no standard errors and p-values reported for the factor loadings in the exploratory factor analysis, instead the magnitude of the factor loadings are used to judge the ...
2
votes
1answer
63 views
Can you do confirmatory factor analysis on items with different response scale
Can one do a confirmatory factor analysis with items on different response scales.
let's say 50 items have a likert response scale from 1 to 4, and the second group of items have a likert response ...
2
votes
0answers
48 views
How to calculate confirmatory factor analysis by hand?
I am trying to learn how confirmatory factor analysis works and the way I learn is best by understanding how the calculations work by hand using a pen, paper, and a calculator, and then replicate this ...
0
votes
1answer
34 views
Factor loading calculated by factor_analyzer smaller than -1
I used factor_analyzer Python package for CFA, but matrix of factor loadings that I got contains value smaller than -1. Is a bug in the package, or maybe I ...
1
vote
1answer
147 views
CFA: should I remove highly correlated items?
I want to Run CFA model (N=400), but I have a question about the correlation between items. I know I should have high correlation between items that make up one factor (cor>.3). I have two factors ...
0
votes
0answers
35 views
SEM: Difference between standardized and non-standardized p-values?
I'm currently working on regressions of one latent factor on another latent factor with ``lavaan'`. More specifically, I want to examine if depression predicts procrastination behavior. However, I did ...
0
votes
0answers
46 views
What steps in data cleaning process I need to do before the CFA?
I wonder if you can help me find any sources of literature that describes what steps needs to be done to clean up the data before CFA?
I have done the following steps:
convert Likert type scale to ...
1
vote
0answers
18 views
Longitudinal CFA How to build configural model?
I have 12 survey questions (Qs) that were asked during pre- and post-term survey. So I want to do the longitudinal CFA to see whether there was a difference between factor models for pre/post-term ...
1
vote
1answer
23 views
In Structural Equation Modelling, what is the difference between Exploratory and Confirmatory Factor Analysis?
I am trying to understand the difference between Exploratory and Confirmatory Factory Analysis. I have usually only done CFAs because I would test existing models. Though I know EFA usually precedes ...
0
votes
0answers
140 views
Difference between CFA using WLSMV estimator and IRT
I am trying to understand the differences (or similarities) between conducting CFA on categorical data using the WLSMV estimator in SEM and item response theory analysis. I would appreciate any input. ...
2
votes
1answer
209 views
Multilevel SEM with three or more levels in OpenMx
I am trying to figure out how to conduct analyses using CFA and SEM models with three or more levels. Pritikin et al. (2017) investigates how to conduct a three-level and up to five-level SEM using ...
0
votes
0answers
9 views
How should low factor loadings affect interpretation of the factor's correlation with another variable?
In a research project I am working on for university, I used 18 items to measure 4 variables. This measurement instrument has been validated in previous literature. I ran a factor analysis with 4 ...
0
votes
0answers
26 views
CFA Model Saturated, fit perfect
I am running a CFA with three items and one latent factor. My sample size is 900. Each item loads onto the factor between .64 and .89. Why is it saying fit is perfect? I have tried in both STATA and ...
0
votes
1answer
73 views
Dealing with reversed items that are causing poor CFA fit model: residuals-related problem
I am running a CFA model (N=500) with a total of 5 factors: 3 of them include reverse items.
I first run a reliability test psych::alpha(df_cronbach) which showed ...
1
vote
0answers
74 views
Controlling variance manually for a latent factor w/ only one manifest indicator using lavaan in R
Using lavaan in R, I'm trying to reproduce a CFA/SEM model from a publication (cf. Figure 1 of https://onlinelibrary.wiley.com/doi/pdf/10.1111/desc.12202).
Below is the correlation table and std. dev....
