Scores are commonly used in environmental valuation exercises. The two main procedures when testing for score differences are the within sample and the between sample approaches. Their conclusions do not always coincide. With a case study involving scores on difficulty of responding to two choice modeling variants -contingent ranking and contingent grouping-, the paper shows the strength of the within sample approach when relying on the coherent arbitrariness principle. Results suggest that the grouping is significantly less difficult to complete than the ranking task. The validity of these results is enhanced by the fact that they are independent of the exercise order, which is tested by randomizing the sequence order in which respondents face the two methods.
|Publication status||Published - 18 Jun 2010|