Dear colleagues,
Is there any literature on how to assess the differences in means for one construct across two (independent) groups when using PLS? There are recent publications on how to compare beta values across multiple groups (e.g. Sarstedt et al, 2011) but relatively little can be found on comparing means.
Best regards
Tibert Verhagen
multigroup analysis: how to compare means?
-
tibertverhagen
- PLS Junior User
- Posts: 5
- Joined: Thu Jul 12, 2007 8:04 pm
- Real name and title:
- Location: Amsterdam
multigroup analysis: how to compare means?
Dr. Tibert Verhagen
associate professor E-business
VU University Amsterdam
dep. of IS
De Boelelaan 1085, room 3a-22
1081HV Amsterdam
associate professor E-business
VU University Amsterdam
dep. of IS
De Boelelaan 1085, room 3a-22
1081HV Amsterdam
-
tibertverhagen
- PLS Junior User
- Posts: 5
- Joined: Thu Jul 12, 2007 8:04 pm
- Real name and title:
- Location: Amsterdam
compare inter-item correlations and factor loadings
Thank you Bido, a very useful suggestion.
An additional question: do you know if there are any scholars who applied this mean-testing PLS procedure (with Mann-whitney) in published papers before? Or is there any statistical work that elucidates these steps in combination with PLS? As we want to use it for a paper that is in the 2nd round of an academic journal, we would like to add some references to underpin the steps we took here (towards the reviewers).
A final question: could the same (Mann-whitney) procedure be applied when the goal would be to compare inter-item correlations and factor loadings across multiple (independent) samples?
thank you for your valuable input,
Best regards
Tibert Verhagen
Has this procedure been applied by
An additional question: do you know if there are any scholars who applied this mean-testing PLS procedure (with Mann-whitney) in published papers before? Or is there any statistical work that elucidates these steps in combination with PLS? As we want to use it for a paper that is in the 2nd round of an academic journal, we would like to add some references to underpin the steps we took here (towards the reviewers).
A final question: could the same (Mann-whitney) procedure be applied when the goal would be to compare inter-item correlations and factor loadings across multiple (independent) samples?
thank you for your valuable input,
Best regards
Tibert Verhagen
Has this procedure been applied by
-
Diogenes
- PLS Super-Expert
- Posts: 899
- Joined: Sat Oct 15, 2005 5:13 pm
- Real name and title:
- Location: São Paulo - BRAZIL
- Contact:
Mann Whitney is a test used when the normality of the distribution of the data is not met, for more details, see:
SIEGEL, S.; CASTELLAN N J, J. Nonparametrical statistics for the behavioural sciences. 2nd edition. McGrawHill International Edicions New York, p. 399 pp, 1988.
To compare factor loadings across multiple (independent) samples use the procedure and spreadsheet by Henseler et al.
HENSELER, J. RINGLE, C. M.; SINKOVICS, R. R. The use of partial least squares path modeling in international marketing. Advances in International Marketing, v. 20, p. 277-319, 2009.
Or try XLSTAT-PLSPM (free for 30 day trial). It has a procedure to compare groups easier than SmartPLS at this moment.
Best regards,
Bido
SIEGEL, S.; CASTELLAN N J, J. Nonparametrical statistics for the behavioural sciences. 2nd edition. McGrawHill International Edicions New York, p. 399 pp, 1988.
To compare factor loadings across multiple (independent) samples use the procedure and spreadsheet by Henseler et al.
HENSELER, J. RINGLE, C. M.; SINKOVICS, R. R. The use of partial least squares path modeling in international marketing. Advances in International Marketing, v. 20, p. 277-319, 2009.
Or try XLSTAT-PLSPM (free for 30 day trial). It has a procedure to compare groups easier than SmartPLS at this moment.
Best regards,
Bido
-
tibertverhagen
- PLS Junior User
- Posts: 5
- Joined: Thu Jul 12, 2007 8:04 pm
- Real name and title:
- Location: Amsterdam