Good morning,
I have the following problem.
In a second-dimension model, I have one correlation that is 0.979 - when I calculated the model using 1st orders constructs all HTMT fulfilled the criterion (<.80)
How can I fix this issue?
Thanks in advance,
HTMT
- cringle
- SmartPLS Developer
- Posts: 818
- Joined: Tue Sep 20, 2005 9:13 am
- Real name and title: Prof. Dr. Christian M. Ringle
- Location: Hamburg (Germany)
- Contact:
Re: HTMT
I usually do not use second-order constructs. However, this often happens between first and second order models. But do you expect discriminant validity between these construct? Can you establish discriminant validity between the second order construct and all other constructs in the model (except the first order constructs)?
In the HTMT paper, you find recommendation how to solve discriminant validity problems. You either need to increase the correlation of indicators within the construct or to reduce it across constructs.
Kind regards
Christian
In the HTMT paper, you find recommendation how to solve discriminant validity problems. You either need to increase the correlation of indicators within the construct or to reduce it across constructs.
Kind regards
Christian
Prof. Dr. Christian M. Ringle, Hamburg University of Technology (TUHH), SmartPLS
- Literature on PLS-SEM: https://www.smartpls.com/documentation
- Google Scholar: https://scholar.google.de/citations?use ... AAAJ&hl=de
- Literature on PLS-SEM: https://www.smartpls.com/documentation
- Google Scholar: https://scholar.google.de/citations?use ... AAAJ&hl=de
-
- PLS Junior User
- Posts: 9
- Joined: Tue Apr 14, 2015 8:43 am
- Real name and title: nuria recuero virto. PhD
Re: HTMT
Mr Ringle thank you for all your help.
The correlation that does not fit <0.90 is between two second order constructs
I have just realized that is because it does make sense that one of the first order constructs is included in the other second order construct. May I do a CFA? How can I justify this change when this second order constructs are already defined in literature (and contain the first order constructs)? I am in a revision process.
Thanks in advance
The correlation that does not fit <0.90 is between two second order constructs
I have just realized that is because it does make sense that one of the first order constructs is included in the other second order construct. May I do a CFA? How can I justify this change when this second order constructs are already defined in literature (and contain the first order constructs)? I am in a revision process.
Thanks in advance
- cringle
- SmartPLS Developer
- Posts: 818
- Joined: Tue Sep 20, 2005 9:13 am
- Real name and title: Prof. Dr. Christian M. Ringle
- Location: Hamburg (Germany)
- Contact:
Re: HTMT
Thanks. Could you merge the two second order constructs? Or would a third order construct make sense?
Prof. Dr. Christian M. Ringle, Hamburg University of Technology (TUHH), SmartPLS
- Literature on PLS-SEM: https://www.smartpls.com/documentation
- Google Scholar: https://scholar.google.de/citations?use ... AAAJ&hl=de
- Literature on PLS-SEM: https://www.smartpls.com/documentation
- Google Scholar: https://scholar.google.de/citations?use ... AAAJ&hl=de