Links to specific topics

Monday, July 21, 2014

One-tailed or two-tailed P values in PLS-SEM?


Should P values associated with path coefficients, as well as with other coefficients such as weights and loadings, be one-tailed or two-tailed? This question is addressed through a publication recently released as a ScriptWarp Systems research report:

Kock, N. (2014). One-tailed or two-tailed P values in PLS-SEM? Laredo, TX: ScriptWarp Systems.

PDF file:

http://www.scriptwarp.com/warppls/pubs/Kock_2014_OneTwoTailedPLSSEM.pdf

Abstract:

Should P values associated with path coefficients, as well as with other coefficients such as weights and loadings, be one-tailed or two-tailed? This question is answered in the context of structural equation modeling employing the partial least squares method (PLS-SEM), based on an illustrative model of the effect of e-collaboration technology use on job performance. A one-tailed test is recommended if the coefficient is assumed to have a sign (positive or negative), which should be reflected in the hypothesis that refers to the corresponding association. If no assumptions are made about coefficient sign, a two-tailed test is recommended. These recommendations apply to many other statistical methods that employ P values; including path analyses in general, with or without latent variables, plus univariate and multivariate regression analyses.

7 comments:

S Sadeque said...

Hi Prof. Kock,

Is it possible to get t-values and CI associated with the path coefficients in WrapPls?

Many thanks.

Ned Kock said...

Yes, one can obtain T ratios and conduct confidence intervals tests in WarpPLS. These are explained in the publications below.

Kock, N. (2015). Hypothesis testing with confidence intervals and P values. Laredo, TX: ScriptWarp Systems.

http://cits.tamiu.edu/kock/pubs/Reports/2015_SWSReport_ConfIntervalsPvalues/Kock_2015_ConfIntervalsPvalues_SWSReport.pdf

Kock, N. (2015). One-tailed or two-tailed P values in PLS-SEM? International Journal of e-Collaboration, 11(2), 1-7.

https://drive.google.com/file/d/0B76EXfrQqs3ha255TkliQk1ONEE/view

S Sadeque said...

Thank you for your reply, Prof. Kock. I am still bit confused about where I can see the results of t-values and the CIs. I have run the analysis with PLS mode A, Linear and Stable3 options from general settings as suggested in the first article. But I am not sure where I can see the results. Which menu options needs to be clicked?

Another query is whether mean values of the latent variable can be obtained. I can find the median, max, etc. from the 'Latent variable coefficient' option but not the mean values.

Thanks again.

Ned Kock said...

Hi SS, again.

WarpPLS generates path coefficients and standard errors for each path. Let us call these quantities b and a. Using these, you can then calculate T ratios and confidence intervals as follows:

T = b/a.
CI = b–1.96*a, b+1.96*a.

The above are discussed in the report I mentioned to you, which is the first listed and linked below. For another publication including relevant WarpPLS screens, see the second one below.

Kock, N. (2015). Hypothesis testing with confidence intervals and P values. Laredo, TX: ScriptWarp Systems.

http://cits.tamiu.edu/kock/pubs/Reports/2015_SWSReport_ConfIntervalsPvalues/Kock_2015_ConfIntervalsPvalues_SWSReport.pdf

Kock, N. (2014). Advanced mediating effects tests, multi-group analyses, and measurement model assessments in PLS-based SEM. International Journal of e-Collaboration, 10(3), 1-13.

http://www.scriptwarp.com/warppls/pubs/Kock_2014_UseSEsESsLoadsWeightsSEM.pdf

Now to your other question regarding LV means. LVs are standardized; that is, their scores are. Therefore, each and all LVs have the same mean, namely zero.

S Sadeque said...

Thanks, Prof. Kock for the clarifications. Much appreciated.

zul said...

Hi Prof. Kock

I have question, how to set WarpPLS with one tailed or two tailed.

Thank you

Ned Kock said...

Hi zul. I hope that the link below can be of use in connection with this. See the 3rd paragraph on page 25.

User Manual (link to specific page):

http://www.scriptwarp.com/warppls/UserManual_v_5_0.pdf#page=25

The link above, as well as other links that may be relevant in this context, are available from:

http://warppls.com/