Confirmatory factor analysis (CFA) using JAMOVI software
HTML-код
- Опубликовано: 15 июл 2024
- In this video, I am demonstrating the process of running Confirmatory factor analysis (CFA) using JAMOVI software. The dataset is based on the following citation: Pattusamy, M., Jacob, J. A Test of Greenhaus and Allen (2011) Model on Work-Family Balance. Curr Psychol 36, 193-202 (2017). doi.org/10.1007/s12144-015-94...
I tried to drag my data for each factor creation. I am getting an error like " lavan Error: cound not compute modification indices, information matrix is singular." could you please tell me what it is
Dear Murugan, thank you for your videos using jamovi! I have four items or variables in my jamovi file and I want to summarize or combine them to one variable, for example: i have for items that ask about empathy, so i want to combine them into the variable empathy. I think that is called item parcelling. Do you know how this functions?
Yes, it is referred to as item parcelling. you can create a single column of information using the Mean or Sum function. There are other types of item parcelling approaches are available in the literature. For more details just look at the following citations: Little, T. D., Cunningham, W. A., Shahar, G., & Widaman, K. F. (2002). To parcel or not to parcel: Exploring the question, weighing the merits. Structural equation modeling, 9(2), 151-173.
Matsunaga, M. (2008). Item parceling in structural equation modeling: A primer. Communication Methods and Measures, 2(4), 260-293.
WU, Y., & WEN, Z. L. (2011). Item parceling strategies in structural equation modeling. Advances in Psychological Science, 19(12), 1859-1867.
for more references visit my personal webpage: sites.google.com/view/muruganpattusamy/resources?authuser=0
Many thanks, Mr Pattusamy!
@@muruganpattusamy4789 One more question: Im currently writing my master thesis, and I am absolutely nooby in statistics. I have continous data that is not normally distributed, when it comes to SEM, what estimation method (in JAMOVI) would you suggest? And have you some papers supporting your suggestion? I really looked in many papers but cant find the right estimation method, because my sample size is 150 and the most scholars only speak about a much bigger sample size when it comes to SEM.
@@normanschmitt6303 you can use adf estimation technique. Even in non normal condition you can estimate the parameter values. But your sample size may not be sufficient.
can u provide a free link to dataset??
Sir are we supposed to consider only independent variables for cfa or can we include even mediating and dependant variables also sir
Yes everything need to be included even control variables if it is a latent construct
@@muruganpattusamy4789
Sir if we are taking the variables/items from previous studies and modifying the statements are we supposed to conduct exploratory factor analysis
@@amitavenkatesh5946 you can do cfa