Econometric policy evaluation: A critique

Motivational Interviewing: Preparing People for Change

We describe a two-step algorithm for estimating dynamic games under the assumption that behavior is consistent with Markov perfect equilibrium. In the first step, the policy functions and the law of motion for the state variables are estimated. In the second step, the remaining structural parameters are estimated using the optimality conditions for equilibrium. The second step estimator is a simple simulated minimum distance estimator. The algorithm applies to a broad class of models, including industry competition models with both discrete and continuous controls such as the Ericson and Pakes (1995) model. We test the algorithm on a class of dynamic discrete choice models with normally distributed errors and a class of dynamic oligopoly models similar to that of Pakes and McGuire (1994).

/pdf/estimating-dynamic-models-of-imperfect-competition-3ko56auuq6.pdf

Estimating Dynamic Models of Imperfect Competition

We describe a two-step algorithm for estimating dynamic games under the assumption that behavior is consistent with Markov perfect equilibrium. In the first step, the policy functions and the law of motion for the state variables are estimated. In the second step, the remaining structural parameters are estimated using the optimality conditions for equilibrium. The second step estimator is a simple simulated minimum distance estimator. The algorithm applies to a broad class of models, including industry competition models with both discrete and continuous controls such as the Ericson and Pakes (1995) model. We test the algorithm on a class of dynamic discrete choice models with normally distributed errors, and a class of dynamic oligopoly models similar to that of Pakes and McGuire (1994).

/pdf/estimating-dynamic-models-of-imperfect-competition-4fw5kfqjeo.pdf

The goal-gradient hypothesis denotes the classic finding from behaviorism that animals expend more effort as they approach a reward. Building on this hypothesis, the authors generate new propositions for the human psychology of rewards. They test these propositions using a field experiment, secondary customer data, paper-and-pencil problems, and Tobit and logit models. The key finding indicate that (1) participants in a real cafe reward program purchase coffee more frequently the closer they are to earning a free coffee; (2) Internet users who rate songs in return for reward certificates visit the rating Web site more often, rate more songs per visit, and persist longer in the rating effort as they approach the reward goal; (3) the illusion of progress toward the goal induces purchase acceleration (e.g., customers who receive a 12-stamp coffee card with 2 preexisting "bonus" stamps complete the 10 required purchases faster than customers who receive a "regular" 10-stamp card) and (4) a stronger tendency to accelerate toward the goal predicts greater retention and faster reengagement in the program. The conceptualization and empirical findings are captured by a parsimonious goal distance model, in which effort investment is a function of the proportion of original distance remaining to the goal. In addition, using statistical and experimental controls, the authors rule out alternative explanations for the observed goal gradients. They discuss the theoretical significance of their findings and the managerial implications for incentive systems, promotions, and customer retention.

The Goal-Gradient Hypothesis Resurrected: Purchase Acceleration, Illusionary Goal Progress, and Customer Retention

Card payments have been growing very rapidly. To continue the growth, payment card networks keep adding new merchants and card issuers try to stimulate their existing customers’ card usage by providing rewards. This paper seeks to analyze the effects of payment card rewards programs on consumer payment choice, by using consumer survey data. Specifically, we examine whether credit/debit reward receivers use credit/debit cards relatively more often than other consumers, if so how much more often, and which payment methods are replaced by reward card payments. Our results suggest that (i) consumers with credit card rewards use credit cards much more exclusively than those without credit card rewards; (ii) even among those who carry a credit card balance, consumers with credit card rewards use a credit card more often than those without rewards; (iii) among consumers who receive credit card rewards, those who receive credit card rewards as well as debit card rewards tend to use debit cards more often than those who receive credit card rewards only; and (iv) reward card transactions seem to replace not only paper-based transactions but also non-reward card transactions.

Payment card rewards programs and consumer payment choice

This paper investigates whether aggregate consumer learning together with consumer heterogeneity in price sensitivity could explain why (i) there is a slow diffusion of generic drugs into the market, and (ii) brand-name originators keep increasing their prices over time even after the number of generic entrants has become fixed. To examine these hypotheses, I estimate a structural demand model that incorporates consumer learning and heterogeneity in price sensitivity. By conducting a counterfactual experiment, which eliminates the uncertainty of generics, I find that learning plays a role in explaining the slow diffusion. By simulating the model, I find that the branded pricing pattern could be explained by: (a) the diffusion rate of generics for price-sensitive patients is faster than that for price-insensitive patients, causing the proportion of price-insensitive patients faced by brand-name firms to slowly increase over time; (b) the brand-name price elasticities of demand (evaluated at the observed prices) are often less than one and increase over time, suggesting that brand-name firms may set their prices lower than what they would do if they were myopic, in order to slow down the learning process for generic qualities. But such an incentive diminishes over time as the uncertainty slowly resolves.

Consumer Learning and Heterogeneity: Dynamics of Demand for Prescription Drugs after Patent Expiration

By using a unique data set that contains detailed information about consumer payment choice and consumers’ attitudes toward each payment method, we estimate the effects of payment card rewards on consumer choice of payment methods. Our approach allows us to control for consumer heterogeneity. We find the effects of rewards to be statistically significant across five retail types. Our policy experiments suggest that for the sub-population who hold both credit and debit cards, removing rewards would increase their share of paper-based payment methods (i.e., cash and checks), measured in terms of in-store transactions, by no more than 4 percentage points.

/pdf/payment-card-rewards-programs-and-consumer-payment-choice-2oyza8zatv.pdf

Payment Card Rewards Programs and Consumer Payment Choice

We propose a new methodology for structural estimation of infinite horizon dynamic discrete choice models. We combine the dynamic programming (DP) solution algorithm with the Bayesian Markov chain Monte Carlo algorithm into a single algorithm that solves the DP problem and estimates the parameters simultaneously. As a result, the computational burden of estimating a dynamic model becomes comparable to that of a static model. Another feature of our algorithm is that even though the number of grid points on the state variable is small per solution-estimation iteration, the number of effective grid points increases with the number of estimation iterations. This is how we help ease the “curse of dimensionality.” We simulate and estimate several versions of a simple model of entry and exit to illustrate our methodology. We also prove that under standard conditions, the parameters converge in probability to the true posterior distribution, regardless of the starting values.

/pdf/bayesian-estimation-of-dynamic-discrete-choice-models-3xc00rmrdu.pdf

Bayesian Estimation of Dynamic Discrete Choice Models

https://mpra.ub.uni-muenchen.de/7265/1/MPRA_paper_7265.pdf

Andrew T. Ching

Papers

Payment card rewards programs and consumer payment choice

Consumer Learning and Heterogeneity: Dynamics of Demand for Prescription Drugs after Patent Expiration

Payment Card Rewards Programs and Consumer Payment Choice

Bayesian Estimation of Dynamic Discrete Choice Models

Consumer learning and heterogeneity: Dynamics of demand for prescription drugs after patent expiration