Iwe done an importance-performance map of my ECSI model which iwe used the total effects and latent index values.
If i want to compute an importance-performance map for each of my latent variables (showing the importance and performance for the manifest questions), which values do i then use? Average of each manifest question and outer weights or measurement model ? (impact on loyalty which is the ultimate variable in the ECSI model)
Thank you very much in advance
Best regards
Kasper
Manifest variables performance
-
bergsorensen
- PLS User
- Posts: 13
- Joined: Wed Jun 25, 2008 10:40 am
- Real name and title:
-
Diogenes
- PLS Super-Expert
- Posts: 899
- Joined: Sat Oct 15, 2005 5:13 pm
- Real name and title:
- Location: São Paulo - BRAZIL
- Contact:
Use the outer weights, they are standardized weights and are easier to interpret (mainly in a map).
The "measurement model" is the untandardized weight (like relative weights, sum = 1 - or weights in a weighted mean) and they are used to have the unstandardized LV scores in the same scale as the MV.
Best regards.
Bido
The "measurement model" is the untandardized weight (like relative weights, sum = 1 - or weights in a weighted mean) and they are used to have the unstandardized LV scores in the same scale as the MV.
Best regards.
Bido