Optimal Social Design: Estimating a Social Welfare Function from Questionnaire Data

A social design x evokes a response y from a set of individuals. The value of the design is expressed in terms of a social welfare function which is derived from Arrow’s formulation of social choice. Making certain simplifying assumptions the social welfare function can be expressed in terms of individuals’ ideal designs. A method for estimating the social welfare function from quite limited empirical evidence is developed. The method is applied to an educational case study. There was considerable variation in individuals’ ideal designs. The components of the social welfare were estimated: the welfare ideal, the population sensitivity, the population variation, the deviation from the ideal and the welfare ceiling. Methodological problems are discussed.     

Product Differentiation and Mergers in the Carbonated Soft Drink Industry

I simulate the competitive impact of several soft drink mergers from the 1980s on equilibrium prices and quantities. An unusual feature of soft drink demand is that, at the individual purchase level, households regularly select a variety of soft drink products. Specifically, on a given trip households may select multiple soft drink products and multiple units of each. A concern is that using a standard discrete choice model that assumes single unit purchases may understate the price elasticity of demand. To model the sophisticated choice behavior generating this multiple discreteness , I use a household-level scanner data set. Market demand is then computed by aggregating the household estimates. Combining the aggregate demand estimates with a model of static oligopoly, I then run the merger simulations. Despite moderate price increases, I find substantial welfare losses from the proposed merger between Coca-Cola and Dr. Pepper. I also find large price increases and corresponding welfare losses from the proposed merger between Pepsi and 7 UP and, more notably, between Coca-Cola and Pepsi.     

Discrete choice models and the housing price and travel to work elasticities of location demand

Multinomial logit and nested logit models of mode choice in travel to work and housing location choice are estimated from 1970 U.S. census data aggregated to small zones of the Chicago SMSA. The estimated models are then used to derive the “housing rent,” “travel time,” and “travel cost” elasticities of location demand. The effects of sampling variation, sample size, attribute inclusion, model specification, and estimation method on the estimated elasticities are evaluated and found to be important. The elasticities are also compared and found to agree with those obtained from other discrete choice models and, in the case of “housing rent,” with estimates obtained from models based on other theoretical structure.     

The welfare cost of taxation in a labour market with unemployment and non-participation

The standard public economics analysis of the welfare cost of labour income taxation is based on the estimation of labour supply functions that treat unemployed individuals as non-participants. This paper applies econometric models of multinomial discrete choice to the labour market, explicitly allowing individuals to be in any of three possible states (employment, unemployment and non-participation). Based on these estimates, we present calculations of the dead-weight loss (DWL) of taxes, which turn out to be larger than those suggested by the literature.     

Endogenous censoring in the mixed proportional hazard model with an application to optimal unemployment insurance

We examine the sensitivity of estimates of the MPH model with respect to assumptions on the censoring mechanism in the context of an economic model of optimal unemployment insurance. We assume a parametric model for the duration of interest and leave the distribution of censoring unrestricted, allowing it to be correlated with observed and unobserved characteristics. We provide a practical characterization of the identified set with moment inequalities and suggest methods for estimating this set. We apply this approach to estimate the elasticity of unemployment exit rate with respect to unemployment benefit. Finally, we investigate welfare consequences of our estimates.     

ECONOMIC WELFARE ANALYSIS OF THE LEGALIZATION OF DRUGS: A CGE MICROSIMULATION MODEL FOR COLOMBIA

In this paper, a computable general equilibrium (CGE) microsimulation model is used to analyze the effects of an ex ante legalization of drugs on the Colombian economy. The model consists of 11 productive sectors, 3 different labor force categories with unemployment, and 20 households divided by income and location. Changes in wages and migration are estimated using a labor participation model, and a NIDS estimates the demands of the households. Changes in household economic welfare, measured by changes in income and prices (CV and EV measurements), are very sensitive to the reinvestments that the government makes in the economy. By analyzing six different scenarios with different assumptions about changes in drug prices, investments of the government, and the termination of the armed conflict, the results suggest that economic welfare improves when the government reinvests military expenditures in other productive sectors or when the ‘economy of war’ continues and the legalization does not end the armed conflict.     

THE THEORY AND ESTIMATION OF INDIVIDUAL AND SOCIAL WELFARE MEASURES

Abstract. The most widespread measure of individual welfare is consumer surplus ( cs ). If consumer surplus is to represent underlying preferences, very restrictive assumptions must be imposed and, worse, the resulting measures completely ignore distributional issues. Applied economists often argue that consumer surplus is a good approximation to the theoretically correct measures and the only feasible choice in practice. This is no longer true; recent advances in estimation techniques have made it possible to determine the approximate values of the correct measures quite satisfactorily. The theory and estimation of social welfare measures automatically involves ethical and distributional judgements. Often, these are difficult to incorporate in intuitive summary indicators that are easy to estimate. A range of money metric measures is presented that provide a more desirable, albeit still problematic alternative. Subject to severe data limitations, the theoretically correct welfare measures can be estimated for a wide range of modelling situations using parametric and nonparametric techniques.     

Heterogeneous treatment effects: Instrumental variables without monotonicity?

Imbens and Angrist (1994) were the first to exploit a monotonicity condition in order to identify a local average treatment effect parameter using instrumental variables. More recently, Heckman and Vytlacil (1999) suggested the estimation of a variety of treatment effect parameters using a local version of their approach. We investigate the sensitivity of the respective estimates to random departures from monotonicity. Approximations to the respective bias terms are derived. In an empirical application the bias is calculated and bias corrected estimates are obtained. The accuracy of the approximation is investigated in a Monte Carlo study.     

非线性定价下的移动通信需求行为

本文研究多产品移动通信业务以及非线性定价条件下的消费者需求理论,并利用话单层级的用户消费数据,建立离散选择结构计量模型,并对用户资费选择行为与个人属性、资费属性和换网行为之间的关系进行研究,最后利用估计出的需求结构参数,就资费优化对企业收入和用户资费选择概率的影响进行分析。     

Product diffusion,product differentiation and the timing of new product introduction the television and VCR market 1964-85

An econometric model of the demand and supply of color televisions, black and white televisions and video cassette recorders in the United States from 1964 to 1985 is developed and estimated. Supply and demand parameter estimates are obtained using a simultaneous equation system estimated by three-stage least squares. The model employed integrates theories of product diffusion from the marketing literature with those of the economic literature on discrete choice. Particular attention is paid to the relationship between product saturation and demand, as well as to supply decisions pertaining to product differentiation and the timing of new product introduction. The central hypothesis that product differentiation and new product introduction are more likely to occur as demands for established products slow at critical saturation levels is supported by the empirical results and actual market occurrences.     

On the need to compensate the compensating variation in CGE modeling

The message of this research is that in the standard calibrated setting of Computational General Equilibrium (CGE) models, the welfare measures typically used to compare benchmark with counterfactuals are numéraire dependent. This evaluation bias affects the compensating variation and the Konüs index of cost of living. We show that the equivalent variation is neutral regarding the choice of value units in calibrated models but would be affected as well in uncalibrated CGE models. We illustrate with a simple example and propose an even simpler theoretical solution to overcome these biases; all that is required to have correct welfare estimates is to compensate normalizing with a suitable price index. This type of correction is necessary to overcome the sometimes blind implementation of welfare measures in numerical general equilibrium analysis. We show that the induced quantitative errors may be substantial providing biased welfare estimates and misleading results.     

New methods for analyzing structural models of labor force dynamics

The economic theory of decision-making under uncertainty is used to produce three econometric models of dynamic discrete choice: (1) for a single spell of unemployment; (2) for an equilibrium two-state model of employment and non-employment; (3) for a general three-state model with a non-market sector. The paper provides a structural economic motivation for the continuous time Markov (or more generally ‘competing risks’) model widely used in longitudinal analysis in biostatistics and sociology, and it extends previous work on dynamic discrete choice to a continuous time setting. An important feature of identification analysis is separation of economic parameters that can only be identified by assuming arbitrary functional forms from economic parameters that can be identified by non-parametric procedures. The paper demonstrates that most econometric models for the analysis of truncated data are non-parametrically under-identified. It also demonstrates that structural estimators frequently violate standard regularity conditions. The standard asymptotic theory is modified to account for this essential feature of many structural models of labor force dynamics. Empirical estimates of an equilibrium two-state model of employment and non-employment are presented.     

Multicollinearity in regression: an efficiency comparison between L<Subscript>p</Subscript>-norm and least squares estimators

Multicollinearity is one of the most important issues in regression analysis, as it produces unstable coefficients’ estimates and makes the standard errors severely inflated. The regression theory is based on specific assumptions concerning the set of error random variables. In particular, when errors are uncorrelated and have a constant variance, the ordinary least squares estimator produces the best estimates among all linear estimators. If, as often happens in reality, these assumptions are not met, other methods might give more efficient estimates and their use is therefore recommendable. In this paper, after reviewing and briefly describing the salient features of the methods, proposed in the literature, to determine and address the multicollinearity problem, we introduce the L_pmin method, based on L_p-norm estimation, an adaptive robust procedure that is used when the residual distribution has deviated from normality. The major advantage of this approach is that it produces more efficient estimates of the model parameters, for different degrees of multicollinearity, than those generated by the ordinary least squares method. A simulation study and a real-data application are also presented, in order to show the better results provided by the L_pmin method in the presence of multicollinearity.     

Frequency Domain Tests for Residual Serial Correlation in Cointegration Regressions

This paper introduces tests for residual serial correlation in cointegrating regressions. The tests are devised in the frequency domain by using the spectral measure estimates. The asymptotic distributions of the tests are derived and test consistency is established. The asymptotic distributions are obtained by using the assumptions and methods that are different from those used in Grenander and Rosenblatt (1957) and Durlauf (1991). Small-scale simulation results are reported to illustrate the finite sample performance of the tests under various distributional assumptions on the data generating process. The distributions considered are normal and t-distributions. The tests are shown to have stable size at sample sizes as large as 50 or 100. Additionally, it is shown that the tests are reasonably powerful against the ARMA residuals. An empirical application of the tests to investigate the ‘weak-form’ efficiency in the foreign exchange market is also reported.     

Estimating the Size of a Criminal Population from Police Records Using the Truncated Poisson Regression Model

The truncated Poisson regression model is used to arrive at point and interval estimates of the size of two offender populations, i.e. drunk drivers and persons who illegally possess firearms. The dependent capture–recapture variables are constructed from Dutch police records and are counts of individual arrests for both violations. The population size estimates are derived assuming that each count is a realization of a Poisson distribution, and that the Poisson parameters are related to covariates through the truncated Poisson regression model. These assumptions are discussed in detail, and the tenability of the second assumption is assessed by evaluating the marginal residuals and performing tests on overdispersion. For the firearms example, the second assumption seems to hold well, but for the drunk drivers example there is some overdispersion. It is concluded that the method is useful, provided it is used with care.     

Mixed MNL models for discrete response

This paper considers mixed, or random coefficients, multinomial logit (MMNL) models for discrete response, and establishes the following results. Under mild regularity conditions, any discrete choice model derived from random utility maximization has choice probabilities that can be approximated as closely as one pleases by a MMNL model. Practical estimation of a parametric mixing family can be carried out by Maximum Simulated Likelihood Estimation or Method of Simulated Moments, and easily computed instruments are provided that make the latter procedure fairly efficient. The adequacy of a mixing specification can be tested simply as an omitted variable test with appropriately defined artificial variables. An application to a problem of demand for alternative vehicles shows that MMNL provides a flexible and computationally practical approach to discrete response analysis. Copyright © 2000 John Wiley & Sons, Ltd.     

The demand for teleshopping: An application of discrete choice models

New telecommunications technologies have often been suggested to act as substitutes for travel. Teleshopping may be a substitute for traditional store shopping. This paper studies the determination of the demand for teleshopping. In general, the demand for telecommunications is derived from the demand for information. So we look at teleshopping as a form of information gathering. Agents can engage in various shopping activities, including teleshopping, which entail different time and monetary costs. Through a discrete choice model, we analyze the effect of costs on the choice of shopping activities. The model is estimated based on a pilot experiment in which individuals had to choose among information bundles when shopping for differentiated products. Implicit in the choice set were information items which can only be transmitted by specific media. Limitations of this preliminary work and suggestions for future research are discussed.     

Time aggregation and the distributional shape of unemployment duration

This paper reports empirical evidence on the sensitivity of unemployment duration regression estimates to distributional assumptions and to time aggregation. The results indicate that parameter estimates are robust to distributional assumptions, while estimates of duration dependence are not. Time aggregation does not seem to have drastic effects on the estimates in a simple parametric model like the Weibull, but can produce dramatic changes in the more complicated extended generalized gamma model. Semiparametric models for grouped data produce stable estimates, and perform much better than continuous-time models in terms of significance at high levels of time aggregation.     

EMPIRICAL ESTIMATION OF NON-LINEAR INPUT–OUTPUT MODELS: AN ENTROPY ECONOMETRICS APPROACH

Despite theoretical advances, non-linear input–output models have been empirically applied only to a limited extent. This is mainly due to the fact that the number of parameters to be estimated is much higher than the number of available data points. Taking advantage of the recent proliferation of input–output databases and by applying an estimation strategy that relies on entropy econometrics, this paper suggests a way to estimate the parameters that characterize non-linear relationships between inputs and output. This non-linear modelling allows for considering time-specific input coefficients, instead of fixed ones. Several types of multipliers can be derived from this non-linear model, and the proposed generalized maximum entropy (GME) estimator allows estimating them from time series or cross-sectional datasets of input–output tables. The proposed GME technique is illustrated by means of an empirical application that estimates the parameters that characterize a non-linear input–output model for the Spanish economy over the period 1995–2011.     

Robust firm pricing with panel data

Firms often have imperfect information about demand for their products. We develop an integrated econometric and theoretical framework to model firm demand assessment and subsequent pricing decisions with limited information. We introduce a panel data discrete choice model whose realistic assumptions about consumer behavior deliver partially identified preferences and thus generate ambiguity in the firm pricing problem. We use the minimax-regret criterion as a decision-making rule for firms facing this ambiguity. We illustrate the framework’s benefits relative to the most common discrete choice analysis approach through simulations and empirical examples with field data.