Dear all,
I have conducted an analysis of my CVA data (single concept input with radio buttons "1 - unattractive" to "5 - Attractive") using OLS. When having a look at the individual utilities of my respondents one data set comprises a negative value for the R-squared (-0,441) although in the CVA Tutorial and Example (https://sawtoothsoftware.com/help/lighthouse-studio/manual/hid_cva_tutorial.html) it says:
"R-squared is bounded by 0 and 1.0, with 1.0 indicating perfect fit (note that the reported R-squared is the fit after imposing any constraints on the data)."
Therefore, it seems to me that CVA OLS does not compute an adjusted R-squared and I don't know how to proceed with the described data set except for excluding it in my analysis.
Further explanations regarding this issue would be highly appreciated. Thanks in advance for your help and happy holidays.
Best regards
Natalie