forum.smartpls.com

Good day,

I have a few enquiries here.

1. What does it mean if there is negative outer loading? For your information, all the indicators that have negative loading in my reflective model are those with reverse question which I have recode them during data entry in SPSS or have negative relationship.

2. Someone said there is no negative loading in reflective model in SEM-PLS. Can anyone clarify on this matter?

3. Is it necessary to report R square? Besides, what should we report for pls algo, bootstrapping, mediation and MGA?

Thank you in advance.

You may want to take look at the books on PLS-SEM: www.pls-sem.com

@1: Outer loadings are the correlation between the indicator and the latent variable. The results can be negative but you may to not like this. In that case, you may consider recoding the indicator.

@2: see 1; sure, loadings can be negative but usually this is not desired in PLS-SEM

@3: Sure! Why don't you take a look at this article for a start: Hair, J. F., Sarstedt, M., Ringle, C. M., & Mena, J. A. (2012). An Assessment of the Use of Partial Least Squares Structural Equation Modeling in Marketing Research. Journal of the Academy of Marketing Science, 40(3), 414-433.

You find it here amongst other literature:
- List of articles in the PDF: http://info.smartpls.com/lit_list.pdf
- Endnote File with embedded PDFs: http://info.smartpls.com/lit_endnote.zip
- PDFs: http://info.smartpls.com/lit_pdf.zip

Best regards
Christian