Adoption of crop insurance in Ghana: an application of the complementary log-log truncated Poisson double-hurdle model

Purpose The aim of this paper is to identify the factors that influence rice farmers' decisions to adopt crop insurance and premium payments (willingness to pay [WTP] amounts). The paper also demonstrates the usefulness of the complementary log-log (cloglog) truncated Poisson double-hurdle model as an alternative hurdle model. Design/methodology/approach The study first investigated the nature of the dependent variable, which had non-normal residuals and was overdispersed. The probit truncated normal regression double-hurdle model was tried but it failed the normality and homoscedasticity tests; hence, the cloglog truncated Poisson double-hurdle model was employed in the study. Findings An estimated 61% of respondents would purchase crop insurance, despite farmers not having prior experience with this product. Amongst others, the factors that influence insurance adoption amongst rice farmers are the share of rice in total income, reliability perception of crop insurance schemes and the probability of failure to achieve target yields. The latter helps the authors to address adverse selection, a central issue to the viability of such an insurance programme. The determinants of farmers' WTP are also identified. Research limitations/implications Sampling was limited to farmers using irrigation and living in one region of Ghana, which may limit the study's wider applicability. Originality/value As far as the authors are aware, this study is the first to select the appropriate hurdle model based on established properties of the dependent variable on this topic - crop insurance decisions.