forum.smartpls.com

Hey all, I would like to use several indicators with different scales to form a latent variable.
Some of the indicators have a metric scale (e.g. revenue) while some have an ordinal scale (funding stage coded from 1 = pre-seed to 5 = Series C).
However, in smartPLS 4 I cannot combine these indicators in the same latent variable.

Is there any way to circumvent that, e.g. by re-coding the indicators?

In general, the PLS algorithm assumes metric or quasi metric data. If you do not have such data for all indicators, it does not make much sense to combine them into a construct, because the constructs will also have a metric representation. If you think that your ordinal scale satisfies quasi metric data (scale categories have equal distance) you can just select that the variable is metric in the data view and SmartPLS will allow you to combine it.
For example, most researchers assume that their ordinal Likert scale data is quasi metric.

Makes sense.
Thanks a lot!