confirmatory factor analysis with smartpls?

Frequently Asked Questions about the SmartPLS software. Please refer to this section first, if you have problems with the software.
Post Reply
suyeon0223
PLS Junior User
Posts: 2
Joined: Sun Nov 10, 2013 1:28 am
Real name and title:

confirmatory factor analysis with smartpls?

Post by suyeon0223 » Fri Dec 06, 2013 8:04 am

Hello, I have a few questions regarding smartpls utilization.

1. Can I run confirmatory factor analysis with smartPLS?

2. If so, when drawing CFA diagram, can I include dependent variables and/or moderating variables as well? (I have three dependent variables) . If not feasible, does that mean I can only draw diagram with independent variables?

Any input will be much appreciated. Thanks in advance!

SY

huracan
PLS User
Posts: 20
Joined: Wed May 08, 2013 1:13 pm
Real name and title:

Post by huracan » Thu Dec 12, 2013 6:45 am

Hi.

Bido's explanation might be helpful.

Yes.

1) Connect all LV one with each other (take care to have not recursive arrows). Some LVwill send arrows and other will receive, but this doesn’t matter.
2) Use the “factor weighting scheme” in the PLS algorithm.
3) Assess the measurement model (outer loadings, crossloadings, AVE, reliability…), and the correlations between LVs (results of the CFA).
4) Don’t use the results of path coefficients (meaningfulness).

ozeryilmaz
PLS Junior User
Posts: 2
Joined: Fri Jun 07, 2013 9:57 pm
Real name and title:

is it true?

Post by ozeryilmaz » Sat Dec 14, 2013 1:36 am

hi there ı tried to do a cfa with recursive arrows and get error message but it is true that use only one way arrows? (second photo)
Image
Image

huracan
PLS User
Posts: 20
Joined: Wed May 08, 2013 1:13 pm
Real name and title:

Post by huracan » Sat Dec 14, 2013 8:28 am

Hello.

As i know, It is one of limitations in pls-sem.

That is to say, in PLS-SEM, it is not usually allowed to use non-recursive(or reciprocal) model which has feedback loop.

As you see in your first figure, they have connected with a bidirectional relationship (new1 and new2), which shows part of cycle with conflicted.
However, you can have a stable connected-model as your second figure since they have built in recursive with unidirectional arrows.

Regards.

ozeryilmaz
PLS Junior User
Posts: 2
Joined: Fri Jun 07, 2013 9:57 pm
Real name and title:

Post by ozeryilmaz » Sat Dec 14, 2013 12:38 pm

thanks for ur help.

yerliyabanci
PLS Junior User
Posts: 1
Joined: Sun May 29, 2016 1:53 am
Real name and title: Assoc. Prof. Nuri DOGAN, PhD

Re: confirmatory factor analysis with smartpls?

Post by yerliyabanci » Sun May 29, 2016 2:22 am

Hello,
I have the 30 replication data file, dichotomously. Each of them has two dimensional, same sample size, 50 items (each dimension has 25 items). I want to analyze these data files with comfirmatory factor analysis. My question is that can I also analyze these data files simultaneously by smartPLS?
Thank you your attention.

Nuri DOGAN, PhD.

Post Reply