We adapt the Expectation-Maximization (EM) algorithm to incorporate unobserved heterogeneity into conditional choice probability (CCP) estimators of dynamic discrete choice problems. The unobserved heterogeneity can be time-invariant or follow a Markov chain. By developing a class of problems where difference in future value terms depend on few conditional choice probabilities, we extend the class of dynamic optimization problems where CCP estimators provide a computationally cheap alternative to full solution methods. For this class of problems, we establish partial identification results for cases where the environment is non-stationary and the sample period falls short of the decision-maker’s time horizon. Monte Carlo results confirm that our algorithms perform quite well, both in terms of computational time and in the precision of the parameter estimates.

We propose a likelihood based method that relies on sequential importance sampling to estimate dynamic discrete games of complete information with serially correlated unobserved state variables. Our method is applicable to similar games that have a Markovian representation of the latent dynamics and an algorithm to solve the game. We apply the method to a dynamic oligopolistic game of entry for the generic pharmaceutical industry in which the production costs of firms are the serially correlated unobserved state variable. Costs evolve dynamically and endogenously in response to past entry decisions, leading to heterogeneity among firms regardless of whether they are ex ante identical or heterogeneous. We find that there are significant spillovers of entry on costs. Each entry on average reduces costs by 7 % at the next market opportunity; the average annual cumulative reduction is 51%. Our results provide evidence on the dynamic spillover effects of industry experience on subsequent market performance. The dynamic evolution of production cost plays an important role in the equilibrium path of the structure of the generic pharmaceutical industry.

This paper extends the semi-parametric identification and estimation method for dynamic discrete choice models using Hotz and Miller’s (1993) conditional choice probability (CCP) approach to the setting where individuals may have hyperbolic discounting time preferences and may be naive about their time inconsistency. We implement the proposed estimation method to the decisions of undertaking mammography to evaluate the importance of present bias and naivety in the under-utilization of mammography. Preliminary results show evidence for both present bias and naivety.

of the Census Bureau for their competence and kindness. The research in this paper was conducted while I was Special

Very preliminary –Please do not cite without permission We look into the potential existence of a “state nobility”in top civil service in Spain. With that aim we exploit the surname information of 21,000 members and 85,000 candidates for positions in the eleven main Corps of the Spanish Administration. We use a two-component linear mixture model to estimate the probability that a candidate is a relative of a Corps member. We show that (1) relatives are on average about 44 times more likely to apply for these positions than nonrelatives, constituting 20 % of all candidates; (2) relatives are more likely to apply for exams including a practical test, as well as those containing more extensive study material; and (3) relatives perfom relatively better in oral tests than in anonymous multiple choice tests, but this di¤erence is only marginally signi…cant.

In markets for experience goods, consumers learn about the quality of available products through experimentation. In their decisions, they balance the desire to choose the good with the largest expected value against the incentive to try lesser-known but potentially superior options. I develop a dynamic framework for analyzing demand that interacts pricing and promotion with this learning process, and accommodates settings in which agents search over large choice sets. I employ this approach to study the antidepressant market, testing whether insurer policies can improve the quality of drug-patient matches and overall health. I find that tools that selectively promote only the most effective products for a patient outperform commonly-used tiered pharmaceutical policies. In addition, my estimates, built from a large pool of patient episodes, identify treatments that induce stronger adherence and thus faster recovery relative to alternatives recommended by clinical trial reviews. This result suggests that treatment protocols built from observed quit rates can improve physician decision-making and ultimately patient health.

games. In this paper I estimate a dynamic model of entry/exit in local markets for the US banking industry with heterogeneous firms: single-market and multimarket banks. The econometric model allows for differences between single-market and multimarket banks in competitive effects, sell-off values, and sunk costs of entry. I use the model to run counterfactual exercises addressing the future of the single-market business model in the industry. The contribution of the paper is twofold. First, discusses the coexistence of firms with such a different geographic scope in an industry. Second, provides evidence of the viability of single-market banks in the US banking industry. Results suggest that single-market banks have profit advantages over multimarket banks, but single-market banks pay a sunk cost of entry which is 25 % higher. These higher barriers to entry can be linked to start-up costs, advertisement, and hiring costs for management positions.

Beverage consumption occurs many times a day in response to a variety of needs that change throughout the day. In making their choices, consumers self-regulate their consumption by managing short run needs (e.g., hydration and mood pickup) with long-term goals (e.g., health). Using unique intra-day beverage consumption, activity and psychological needs data, we develop and estimate a model of high frequency consumption choices that accounts for both intra-day changes in short run needs and individual level unobserved heterogeneity in the degree of self-regulation. A novel feature of the model is that it allows for dynamics of consumption and stockpiling at the level of product attributes. The model is used to evaluate introduction of new products in the beverage category and gain insight into the linkage between selfregulation and excess consumption. Broadly, the modeling framework of balancing short run needs with long-term goals has wide ranging applications in choices where long term effects are gradual (e.g., nutrition, exercise, smoking and preventive health care).

Economists have recently argued that time inconsistency may play a central role in explaining intertemporal behavior, particularly among poor households. However, time-preference parameters are typically not identified in standard dynamic choice models and little is known about the fraction of inconsistent agents in the population. We formulate a dynamic discrete choice model in an unobservedly heterogeneous population of possibly time-inconsistent agents motivated by specifically collected information combined with a field intervention in rural India. We identify and estimate all time-preference parameters as well as the population fractions of time-consistent and “naïve ” and “sophisticated ” timeinconsistent agents. We estimate that time-inconsistent agents account for more than half of the population and that “sophisticated ” inconsistent agents are considerably more present-biased than their “naïve ” counterparts. We also examine whether there are other differences across types (e.g. in risk and cost preferences) and find that these differences are small relative to the differences in time preferences. JEL: I1,I3

The e ect of fertility on female labor supply has been a topic widely studied. Literature on treatment e ects have estimated the e ect of second and higher order births on female labor supply. Nevertheless, the e ect of the rst born child is still subject of interest. I propose to use the fact that couples fail in their intentions of having or preventing children as sources of variation. I develop and estimate a dynamic discrete choice structural model which jointly estimates labor force participation and contraception decisions. Preliminary results considering unobserved heterogeneity in tastes for leisure and children and in the fecundity level show that the e ect of the rst born child on female labor supply is about-16%. Finally, I compare the results with OLS and IV estimates. In doing this I provide information about the sources of unobserved heterogeneity in the reduced form estimations and explore what are the advantages and disadvantages of all the abovementioned approaches. JEL CODES: J13, J21