Experimental analysis of choice

Journal of the Economic Science Association, 2019

Until recently, research in experimental economics had largely ignored the choice process, focusing instead on choice outcomes. This is consistent with the traditional focus of the economics profession as a whole on the specific decisions themselves, but has also in part been due to the technological limitations of collecting process data. The equipment for measurement can be expensive and knowledge may be lacking in terms of data analysis best practices. Some recent developments have changed the landscape and brought process data to the forefront of experimental research. First, the measurement technology has improved substantially in quality, availability, and relevance in the marketplace. For example, as little as 15 years ago, eye-tracking involved subjects wearing equipment that was strapped to their heads, with tiny cameras sitting just centimeters below their eyes. Setups would cost many thousands of dollars and had limited temporal and spatial resolution. These days, eye-trackers are sold commercially (e.g., for videogaming) and can be purchased for as little as $100. Modern eye-tracking cameras can fit in your pocket and sit innocuously below the computer monitor. Moreover, with an ever-increasing fraction of economic transactions occurring online and most "smart" devices already built with backward facing cameras (and other biosensors), it is only a matter of time before these data are readily available alongside standard browsing and purchasing data. Second, as economists use behavioral insights and data to refine their theories of decision-making, a clear scientific role for process data has emerged. For example, the now prominent topic of rational inattention makes predictions that relate decision processes to outcomes (Caplin and Dean 2015). These predictions can be readily tested using established process-tracing tools. Third, field and online experiments have emerged in the last 15 years and made substantial impacts on experimental economics. To best complement work in the field and online, laboratory experimenters must leverage their comparative advantage, namely having subjects in a controlled laboratory setting. Process data, which are considerably more difficult to collect in the field, are conducive to laboratory methods. This comparative advantage buttresses the tendency for studies using process data to make up an increasing share of the laboratory experiments that are conducted. 3 Some types of choice-process data that have been studied There are many dimensions of the choice process that can be studied. These methods vary in their accessibility, their intrusiveness, and what they can reveal. They range from the readily observable and unidimensional, e.g., response times, to the complex and high-dimensional, e.g., brain activation patterns or verbal communication. Below, we briefly review the most common measures and highlight recent advances using these methods.

European Review of Agricultural Economics, 2022

Although choice experiments (CEs) have emerged as the most popular stated preference method in applied economics, the method is not free from biases related to order and presentation effects. This paper introduces a new preference elicitation method referred to as a calibrated CE (CCE), and we explore the ability of the new method to alleviate starting-point bias. The new approach utilises the distribution of preferences from a prior CE to provide real-time feedback to respondents about our best guess of their willingness-to-pay (WTP) for food attributes and allows respondents to adjust and calibrate their values. The analysis utilises data collected in 2017 in two US cities, Phoenix and Detroit, on consumer preferences for local and organic tomatoes sold through supermarkets, urban farms and farmers' markets to establish a prior preference distribution. We re-conducted the survey in May 2020 and implemented the CCE. Conventional analysis of the 2020 CE data shows that WTP is strongly influenced by a starting point: the higher the initial price respondents encountered, the higher the absolute value of their WTP. Despite this bias, we show that when respondents have the opportunity to update their WTP when presented with the best guess, the resulting calibrated WTP is much less influenced by the random starting point.

Journal of Marketing Research, 2006

To date, no attempt has been made to design efficient choice experiments by means of the G-and V-optimality criteria. These criteria are known to make precise response predictions, which is exactly what choice experiments aim to do. In this article, the authors elaborate on the G-and V-optimality criteria for the multinomial logit model and compare their prediction performances with those of the D-and A-optimality criteria. They make use of Bayesian design methods that integrate the optimality criteria over a prior distribution of likely parameter values. They employ a modified Fedorov algorithm to generate the optimal choice designs. They also discuss other aspects of the designs, such as level overlap, utility balance, estimation performance, and computational effectiveness.

Handbook of Experimental Economic Methodology, 2015

We outline experiments that improve our understanding of decision making by analyzing behavior in the period of contemplation that preceeds commitment to a …nal choice. The experiments are based on axiomatic models of the decision making process that relate closely to revealed preference logic. To test the models, we arti…cially incentivize particular choices to be made in the pre-decision period. We show how the resulting experiments can improve our understanding not only of the decision making process, but of the decision itself. Our broad method is to make aspects of search visible while retaining the disciplined approach to data that axiomatic modeling best provides.

Journal of Choice Modelling, 2008

We show how to combine statistically efficient ways to design discrete choice experiments based on random utility theory with new ways of collecting additional information that can be used to expand the amount of available choice information for modeling the choices of individual decision makers. Here we limit ourselves to problems involving generic choice options and linear and additive indirect utility functions, but the approach potentially can be extended to include choice problems with non-additive utility functions and non-generic/labeled options/attributes. The paper provides several simulated examples, a small empirical example to demonstrate proof of concept, and a larger empirical example based on many experimental conditions and large samples that demonstrates that the individual models capture virtually all the variance in aggregate first choices traditionally modeled in discrete choice experiments.

PharmacoEconomics, 2017

We provide a user guide on the analysis of data (including best-worst and best-best data) generated from discrete choice experiments (DCEs), comprising a theoretical review of the main choice models followed by practical advice on estimation and post estimation. We also provide a review of standard software. In providing this guide we endeavor not only to provide guidance on choice modeling, but to do so in a way that provides researchers to the practicalities of data analysis. We argue that choice of modeling approach depends on: the research questions; study design and constraints in terms of quality/quantity of data and that decisions made in relation to analysis of choice data are often interdependent rather than sequential. Given the core theory and estimation of choice models is common across settings, we expect the theoretical and practical content of this paper to be useful not only to researchers within but also beyond health economics.

2016

To potentially reduce bias in hypothetical choice experiments, many studies have incentivized respondents to reveal more truthful choices by randomly choosing a binding choice set and then asking them to pay the price indicated for the chosen product alternative in this binding choice set. This approach, however, does not separate the price the respondent indicated he/she is willing to pay for the chosen product alternative from the price that he/she will end up paying. Would the use of the Becker-DeGroot-Marshack (BDM) mechanism make non-hypothetical choice experiments more demand revealing? Our results using a conventional homegrown choice experiment and an induced value choice experiment suggest that it does not. Choice behavior is associated with the degree of understanding about the experimental procedures and the amount of time devoted to examine the choice set.

2009

Efficient experimental designs offer the potential to reduce confidence intervals for parameters of interest in choice models, or to reduce required sample sizes. C-efficiency recognizes the salience of willingness to pay estimates rather than utility function parameters. This study reports on a choice model application that incorporated updated statistical designs based on initial responses in order to maximize C-efficiency. The

Food quality and preference, 2019

Journal of Consumer Research, 2008

The discrete choice experiment is a widely used methodology in consumer studies. However, applying this method to investigate the market of products sold in a wide price range could present issues as to the quality of the estimate of preferences. In fact, for this `type of product, frequently consumers may have different behaviours when faced with different price levels. For example, some market segments may refrain from purchasing products below certain price thresholds, considering them of an unacceptable quality, while others choose only below certain prices. To work around this problem area, we propose a methodology in which each respondent declares his own price interval of reference and consequently participates in a choice experiment with a price vector coherent with his habits. In this manner, we are able to grasp and include in the estimations the heterogeneity of consumers with respect to price and thus obtain more accurate willingness to pay estimates. The method describes a procedure to bypass issues related to identifying the price vector in discrete choice experiments that involve products sold in a wide price range.