Application of Item Response Theory to the Assessment of Coping in an Environmental Risk Situation: Perspectives and Limits.

Abstract

Classical test theory does not have a clear superiority over the item response theory (IRT) framework, as these approaches are meant to address different kinds of objectives. However, the use of the IRT framework makes it possible to take into account two different parameters in the assessment of coping willingness: the extent to which individuals declare that they use the different strategies and the level of difficulty of these strategies. Also, the IRT framework is strong enough to cope with inconsistent behaviors or missing data and can take into account the social, legal, and cultural influences on the ability to cope of respondents. The data set used in this study was obtained from different areas at risk from coastal flooding located in France. The sample was composed of 315 adult participants (mean age = 47; standard deviation = 15). In the present case, it appeared that just 10 items from an initial pool of 23 were sufficient to assess active and passive coping willingness because these had a good discriminatory power. Also, it appeared that the estimation of participants' level of coping willingness was linked to their risk perception and anxiety toward the risk. This result has several implications. Firstly, if the IRT calibration is well performed, IRT can be used to compare scores across assessments with different properties and difficulties/locations. Also, the maximum likelihood estimate of participants' level of active and passive coping willingness using an IRT model makes it possible to study the links between coping willingness and other factors of interest.