RMSEA is an absolute fit index, in that it assesses how far a hypothesized model is from a perfect model. On another side, in PCLOSE, if the P parameter is greater than 0.5(i.e., not statistically significant), then it is concluded that the fit of the model is "close." If the p is less than 0.5, it is concluded that the model's fit is worse than close-fitting (i.e., the RMSEA is greater than 0.05).

Sandeep Singhai

There is considerable controversy over whether "approximate" or "closeness-of-fit" indices such as the RMSEA are at all useful to test SEM models above and beyond the chi-square test of exact model fit. Some argue that such indices aren't helpful at all. This issue has been discussed in great detail and for decades on the SEMNET listserv, where you can find pretty much all of the pro and con arguments for the RMSEA and other fit indices. The SEMNET archives can be found here:

https://listserv.ua.edu/cgi-bin/wa?REPORT=SEMNET&z=4&L=SEMNET&1=SEMNET

Christian Geiser Sir, Thank you for the inputs..However, I am unable to follow the link shared by you as it requires login information. Kindly guide me in this regard if possible or if you can share relevant snippets from the link.

regards

Sandeep Singhai

You can subscribe to the SEMNET listserv and register a password on the following websites (free of charge):

https://listserv.ua.edu/cgi-bin/wa?SUBED1=SEMNET&A=1

https://listserv.ua.edu/cgi-bin/wa?GETPW1

Once you register, you should also be able to log into and search the SEMNET archives.