S4E24 Longitudinal Measurement Invariance
Quantitude
The Problem With Comparing Customer Satisfaction Scores
In order to make a meaningful comparison between those two things, in other words, in order for the mean difference to be reflective of some underlying difference in true latent customer satisfaction, a lot of things have to hold. The problem is that when I am comparing scores from time one to time two, when there are issues associated with those underlying parameters that we can't see, it can really mess things up. For example, if someone wanted to do something as simple as compare the mean at time one with themean at time two, like a little repeated measure design or a paired samples t test, they've got the mean of the one to 10 scale score at time one and at times two.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
