Using stated preference and revealed preference modeling to evaluate prescribing decisions

Abstract

The use of stated preference analyses to evaluate choice of health care products has been growing in recent years. This paper shows how revealed preference data can be enriched with stated preference data and highlights the relative advantages of revealed and stated preference data. The techniques were applied to a study of determinants of physicians' prescriptions of alcoholism medications. Analyses were conducted on the relationship between physicians' perceptions of existing alcoholism medication attributes and their prescribing rates of those medications. Analyses were also conducted on physicians' decisions to prescribe hypothetical alcoholism medications with varying attributes such as efficacy, side effects, compliance, mode of action, and price. Finally, analyses were conducted on the combined stated and revealed preference data. Joint estimation suggests that parameters from the revealed and stated preference data are equal, up to scale. Joint analyses highlight how stated preference data can be used to estimate parameters for attributes that are not observed in the marketplace, that do not vary in the marketplace, or that are highly collinear with other attributes in actual markets.

Validity of discrete-choice experiments evidence for health risk reduction

“…with actual choice behavior. Mark and Swait (2004) come to the same conclusion with regard to physicians' evaluation of an alcohol medication and actual prescribing decisions.Still other studies cast doubt on the validity of the CV method (see, e.g., Hausman, 1993;Nocera et al, 2002) or suggest superiority of DCE over CV (Ryan, 2004) Outside health, the criterion validity of DCE has been tested on several occasions, causing Louviere (1988) to conclude that DCE constitute a valid instrument for explaining and predicting individual behavior on actual markets. More recently Carlsson and Martinsson (2001) observed that measured WTP for a public good did not differ much between a DCE with hypothetical payments and a subsequent DCE with real payments.…”

Discrete Choice Experiments: A Guide to Model Specification, Estimation and Software

“…We discussed the need to calibrate ASCs for market data where such data are available, particularly for welfare and forecasting analysis. A natural extension is more complete data fusion where stated preference data collected in a DCE can be combined with revealed preference data either from observed choices [68,69] or indeed from linking or embedding experiments in other data collection (cross sectional, panel, experimental, RCT) more generally to harness the advantages of the various data sources [70]. There are of course other interesting choice modeling extensions and we refer the interested reader to the Handbook of Choice modeling [71] for a recent survey of cutting edge choice models and estimation issues on the research frontier.…”

Effects coding in discrete choice experiments

“…We will also focus on how regression results should be interpreted when effects coding has been used. The advantages of effects coding have generally not been highlighted in the econometrics literature and has only briefly been explained in [8][9][10][11]. By presenting an illustrative example we hope to enlighten the reader and avoid future pitfalls.…”