A straightforward diagnostic tool to identify attribute non-attendance in discrete choice experiments

To distinguish between respondents that have attended to/ignored an attribute in discrete choice experiments (DCE), Hess and Hensher (HH) apply the coefficient of variation conditional distribution, setting a threshold 2 as conservative rule thumb. This paper develops analytical framework (piecewise regression analysis — PWRA) to refine HH approach, offering flexible method identify non-attendance (ANA) highly context-dependent DCE. It is empirically tested on dataset used value agricultural public goods. The results suggest identification goodness fit different random parameter logit models accommodate ANA are better when developed this research applied. When comparing welfare estimates from PWRA significant differences observed. Consequently, flexibility notably contributes revealing context-specific patterns can help provide more accurate measures therefore policy recommendations.