A comparison of regret-based and utility-based discrete choice modelling – an empirical illustration with hospital bed choice

Abstract

There is some concern that the unobserved preference heterogeneity in random utility maximization theory-based discrete choice experiment modelling is an important source of error variability. The randomness in utility is often interpreted as interpersonal preference heterogeneity but it can also be intrapersonal random variation in preferences. We compare utility maximization and regret minimization-based choice models' sensitivity to individual heterogeneity, examine differences between two consecrated models and validate with empirical illustrations. We use frequency of category (public, semi-private, and private) of bed chosen from Swiss cross-sectional datasets (2007)(2008)(2009)(2010)(2011)(2012) to compare two approaches -utility maximization and regret minimization by applying multinomial logit (MNL) models in regard to the variances in utility (regret) function, goodness-of-fit and predicted marginal effects (pseudo-elasticity) of additional payment. We find parameters with the same sign and estimates with almost same order of magnitude in both the approaches. The statistical significance of attribute effects is consistent in all variants of utility -based MNL models while effects of different attributes are significant only in heteroskedastic extreme value (HEV) variant of regret-based MNL models. This empirical illustration suggests that HEV variant of regret-based models perform better in capturing attribute effects in choice behaviour. KEYWORDSBehavioural paradigm; choice modelling; hospital bed choice; pseudo-elasticity and random regret JEL CLASSIFICATION C25; D12

Utility maximization versus regret minimization in health choice behavior: Evidence from four datasets

“…They also show that differences between models are fairly modest in both cases. Paul et al (2018) use revealed preference data on hospital choices to test RUM versus RRM. They find that for multinomial logit (MNL) models, RUM outperforms RRM.…”

“…We also used reference mining of studies that met our selection criteria. In total, our search yielded five studies that use RRM models in health (Biondi et al., 2019; Boeri et al., 2013; de Bekker‐Grob & Chorus, 2013; Paul et al., 2018; Ryan et al., 2018).…”

“…Paul et al. (2018) use revealed preference data on hospital choices to test RUM versus RRM. They find that for multinomial logit (MNL) models, RUM outperforms RRM.…”

Influence of the Corporate Image of Nursing Homes on the Loyalty of Residents’ Family Members

“…As ref. [ 83 ] stated, values between 0.2 and 0.4 indicate an excellent fit, which is still a generally accepted benchmark range [ 84 , 85 ]. Accordingly, our model shows the goodness of fit.…”

Dependência espacial sob a abordagem de minimização do arrependimento em modelos de escolha de modo de transporte.

“…Dessa forma, nos últimos dez anos, o número de trabalhos que fazem uso da abordagem RRM aumentou gradativamente, tanto na área de transportes onde foi inicialmente proposta, quanto em outras áreas do conhecimento, como saúde (PAUL et al, 2018) e economia de recursos naturais (THIENE; BOERI; CHORUS, 2012). Entre as análises desenvolvidas, a maioria dos estudos buscou comparar a modelagem RUM com sua contraparte, RRM, a fim de analisar seu desempenho.…”