Consensus among preference rankings: a new weighted correlation coefficient for linear and weak orderings

Preference data are a particular type of ranking data where some subjects (voters, judges,...) express their preferences over a set of alternatives (items). In most real life cases, some items receive the same preference by a judge, thus giving rise to a ranking with ties. An important issue involving rankings concerns the aggregation of the preferences into a “consensus”. The purpose of this paper is to investigate the consensus between rankings with ties, taking into account the importance of swapping elements belonging to the top (or to the bottom) of the ordering (position weights). By combining the structure of $$\tau _x$$ τ x proposed by Emond and Mason (J Multi-Criteria Decis Anal 11(1):17–28, 2002) with the class of weighted Kemeny-Snell distances, a position weighted rank correlation coefficient is proposed for comparing rankings with ties. The one-to-one correspondence between the weighted distance and the rank correlation coefficient is proved, analytically speaking, using both equal and decreasing weights.

343 A benefit-risk assessment of daridorexant for the treatment of insomnia using patient preference data from two phase 3 trials

Introduction The efficacy and safety of daridorexant, a dual orexin receptor antagonist intended to treat insomnia, was demonstrated in two placebo-controlled phase III trials. Both pivotal trials included instruments for eliciting treatment preferences of enrolled patients, to interpret the trial findings from their perspective using a patient-centered benefit-risk assessment (pBRA). Methods Digital ethnographies and qualitative interviews with insomnia patients informed the design of a discrete choice experiment (DCE). The DCE was pre-tested in qualitative and quantitative pilots before inclusion in the trials. Within the DCE, patients were asked to make trade-offs between seven outcomes (“time to fall asleep,” “total time asleep,” “daytime functioning,” “likelihood of daytime dizziness/grogginess,” “likelihood of abnormal thoughts and behavioural changes,” “likelihood of falls in the night,” and “treatment withdrawal”). The preference data were analysed using a mixed logit (MXL) model that accounted for preference heterogeneity. Relative attribute importance (RAI) and maximum acceptable risk (MAR) of abnormal thoughts and behavioral changes were obtained from the MXL. A pBRA combined elicited preferences with collected clinical trial data to predict preferences for daridorexant over placebo. Sensitivity analysis accounted for uncertainty in both clinical outcomes and preferences. Results Patients valued all seven outcomes (p < 0.05), but considered improving daytime functioning (RAI = 33.7%) and avoiding treatment withdrawal (RAI = 27.5%) as most important. Patients were also willing to accept an additional 18.8% risk (p-value < 0.001) of abnormal thoughts and behavioral changes for an improvement in daytime functioning from difficulty functioning to restricted functioning. The pBRA suggested that both daridorexant 50 mg and 25 mg were significantly preferred (p-value < 0.001) over placebo, and 50 mg was significantly preferred (p-value < 0.001) over 25 mg, even after accounting for uncertainty in clinical outcomes and preferences. Conclusion All seven outcomes included in the DCE were valued by patients, but improving daytime functioning and avoiding severe treatment withdrawal was considered as most important. Daridorexant 50 mg and 25 mg were found to be significantly preferred over placebo, suggesting a positive benefit-risk balance of both doses. Overall, the preference data allowed for an innovative interpretation of the trial data from patients’ perspective. Support (if any):

Study on Premium Rent of Refurbished Apartments Based on Bayesian Modeling Using Stated Preference Data of the Tenants

In this study, we evaluated the premium rent of refurbished apartment houses in Greater Tokyo. We found that as a residential building’s age increased, the premium rent decreased. Male tenants in the age group of 20–30 years showed the highest willingness to pay (WTP). In addition, a high degree of residential satisfaction and the sense of expense toward rent had negative effects on the WTP toward premium rent.