Multigroup analysis in smartPLS again!

Frequently asked questions about PLS path modeling.
Post Reply
Hosam
PLS Junior User
Posts: 10
Joined: Thu Dec 13, 2012 8:43 am
Real name and title:

Multigroup analysis in smartPLS again!

Post by Hosam » Tue Jun 11, 2013 4:09 am

Hi All,
I am conducting Multigroup analysis in pls path modeling using smartPLS.

I have male and female groups. Therefore, I splitted the data to run two measurement models separately followed by the structural models.

Bootstrapping was performed and I have slight differences in path coefficient between groups.

I followed Sarstedt, Henseler, & Ringle (2011) to test weather these differences are significant or not by performing " t statistic test " shown here
Image

Sarstedt, Henseler, & Ringle (2011) posted in page 200 "The choice of test statistic depends on whether the parameter estimates’ standard deviations differ significantly across the groups"

My questions are:
1- Do the Parameters here refer to outer loadings only or something else?
2- They mention "Levene test" to check for invariance in Standard error while it is sensitive when data distribution is not normal. So how come?
3- am I following the correct procedures? please advice.

Sarstedt, M., Henseler, J., & Ringle, C. M. (2011). Multigroup analysis in partial least squares (PLS) path modeling: Alternative methods and empirical results. Advances in International Marketing, 22, 195-218.

Julen
PLS User
Posts: 17
Joined: Wed Apr 24, 2013 7:38 am
Real name and title:

Post by Julen » Tue Jun 11, 2013 9:37 am

Hi,
Not sure if this might help you:

http://warppls.blogspot.com.es/2013/06/ ... rppls.html

regards,
Julen

Hosam
PLS Junior User
Posts: 10
Joined: Thu Dec 13, 2012 8:43 am
Real name and title:

Post by Hosam » Wed Jun 12, 2013 2:15 am

Thanks Julen, it seems the link you posted require more digging.

regarding the two equations, I noticed that the difference is very small. and mostly the assumption of unequal Standard error is active.

Unequal std errors assumed----------------Equal assumed
2.540*-------------------------------------------2.544*
0.3-----------------------------------------------0.299
1.264--------------------------------------------1.262
0.421--------------------------------------------0.429
1.72----------------------------------------------1.703
1.128--------------------------------------------1.156
0.853--------------------------------------------0.842
0.082--------------------------------------------0.084
0.47----------------------------------------------0.472
1.041--------------------------------------------1.066
1.2-----------------------------------------------1.194

Julen
PLS User
Posts: 17
Joined: Wed Apr 24, 2013 7:38 am
Real name and title:

Post by Julen » Wed Jun 12, 2013 7:49 am

Hi,

I want to conduct a multigroup analysis also, but not yet, I have to study more about PLS...

This might help also (point 3.5):


Henseler, J., Ringle, C. M., & Sinkovics, R. R. (2009). The use of
partial least squares path modeling in international marketing.
Advances in international marketing, 20, 277–319.

User avatar
Hengkov
PLS Super-Expert
Posts: 1618
Joined: Sun Apr 24, 2011 10:13 am
Real name and title: Hengky Latan
Location: AMQ, Indonesia
Contact:

Post by Hengkov » Fri Jun 14, 2013 1:34 pm

Hi,

If your group model invariance used Smith-Satterwaite Test for one solution.

Regards,

Post Reply