Search found 14 matches

by mronkko
Fri Mar 22, 2013 2:34 pm
Forum: FAQ (Methodology)
Topic: bias-corrected bootstrap confidence interval
Replies: 4
Views: 1898

semPLS R package can do bias corrected CIs
by mronkko
Fri Mar 08, 2013 7:04 am
Forum: PLS Related Literature
Topic: Article
Replies: 304
Views: 224767

author = Rönkkö, M., & Evermann, J. title = A Critical Examination of Common Beliefs About Partial Least Squares Path Modeling journal = Organizational Research Methods year = 2013 Rönkkö, M., & Evermann, J. (2013). A Critical Examination of Common Beliefs About Partial Least Squares Path Modeling. ...
by mronkko
Tue Feb 14, 2012 6:06 pm
Forum: FAQ (Methodology)
Topic: Problem with Multicollinearity in covariance based analysis
Replies: 1
Views: 766

Probably not. There is generally very little research showing that PLS would be able to reject false models and there is at least one study that shows that this is indeed the case http://aisel.aisnet.org/icis2010_submissions/21/ How exactly to treat multicollinearity depends on your data and researc...
by mronkko
Tue Feb 14, 2012 4:51 pm
Forum: FAQ (Methodology)
Topic: common method bias test
Replies: 2
Views: 1358

You can check my paper on the topic at http://aisel.aisnet.org/icis2011/procee ... methods/8/

If you cannot access that, you can probably find an earlier version with google scholar.
by mronkko
Thu Oct 13, 2011 1:37 pm
Forum: FAQ (Methodology)
Topic: Interaction effect: Othogonalizing (residual centering)
Replies: 3
Views: 1400

Smart PLS does not report residuals. (This is a severe shortcoming, because residual analysis is a standard post-estimation method for all regression analysis based approaches.) If you want to orthogonalize the indicators, you need to do that with some other statistical software (PASW, Stata, R, etc...
by mronkko
Thu Oct 13, 2011 12:22 pm
Forum: FAQ (Methodology)
Topic: Interaction effect: Othogonalizing (residual centering)
Replies: 3
Views: 1400

#3 is not orthogonalization. For orthogonalization, you need to first center (I prefer to standardize)the variables that form the interaction term, then regress the product of these two centered variables on the centered variables. Use the residual as the interaction term. If you have variables A an...
by mronkko
Thu Sep 15, 2011 11:09 am
Forum: FAQ (SmartPLS 2.0)
Topic: PLS and common method variance
Replies: 1
Views: 945

Check the last post in this thread for a link to a forthcoming conference paper on the issue.

viewtopic.php?t=1573
by mronkko
Sun Jul 17, 2011 1:18 pm
Forum: FAQ (SmartPLS 2.0)
Topic: common method variance
Replies: 8
Views: 4467

The latest version of our paper on method variance with PLS can be found now at http://dl.dropbox.com/u/694399/ICIS-method-variance.pdf The correct citation for this is Rönkkö, Mikko and Jukka Ylitalo (2011) "PLS marker variable approach to diagnosing and controlling for method variance". Forthcomin...
by mronkko
Tue Jul 05, 2011 6:03 pm
Forum: FAQ (SmartPLS 2.0)
Topic: common method variance
Replies: 8
Views: 4467

"Assimilation of enterprise systems: the effect of institutional pressures and the mediating role of top management Huigang Liang Nilesh Saraf Qing Hu Yajiong Xue MIS Quarterly Vol. 31 No. 1, pp. 59-87/March 2007 " This method does not really work at all. There is a paper forthcoming in MISQ that ac...
by mronkko
Tue Mar 08, 2011 6:10 am
Forum: FAQ (SmartPLS 2.0)
Topic: How to use the correlation matrix to run???
Replies: 3
Views: 2226

A couple of the Herman Wold's original papers argue that PLS model can be estimated with covariance matrix as the data. Also, the LVPLSC program in the LVPLS software package should be able to estimate such models. Unfortunately, LVPLS does not seem to be available anymore and the description of how...
by mronkko
Tue Mar 08, 2011 6:06 am
Forum: FAQ (Methodology)
Topic: Significance level for correlations coefficients
Replies: 5
Views: 2513

Actually, you cannot estimate the significance of correlations with SPSS no more than you can estimate the significance of the path coefficients by comparing these to the appropriate t-distribution. The correlation between PLS scores does not follow any known sampling distribution, so you would need...
by mronkko
Tue Dec 07, 2010 1:37 pm
Forum: FAQ (Methodology)
Topic: How to test for Common Method Variance in PLS?
Replies: 21
Views: 16659

This is bit of a bumping an old thread, by we have published a new version of our PLS CMV paper. Also analyzed the Liang et al method and found out that it does not work the way that the paper argues it does. See this thread and the links there.

viewtopic.php?t=1573
by mronkko
Tue Dec 07, 2010 1:35 pm
Forum: FAQ (Methodology)
Topic: COMMON METHOD BIAS
Replies: 5
Views: 1795

You should note that the Liang et al. does actually nothing to control for method variance. The reason for this is explained in detail in our paper that is cited in this thread. We also provide an alternative with simulation evidence supporting the method. http://forum.smartpls.com/viewtopic.php?t=1...
by mronkko
Tue Dec 07, 2010 1:30 pm
Forum: FAQ (SmartPLS 2.0)
Topic: common method variance
Replies: 8
Views: 4467

A more recent version of our PLS CMV paper can be found at

http://www.hut.fi/u/mronkko/PLSCMV.pdf

It contains a better explanation on how to use our method.

This paper will be presented in ICIS 2010 MISQ Workshop and then will be submitted to journal.