A method is presented for generating test statistics that share the same first order asymptotic optimality properties of the classical statistics. Generalizing J. Neyman's work (1959), t he linearized classical statistic tests restrictions in implicit func tion form using a parameter estimator that is consistent and symptoti cally normally distributed under the alternative hypothesis. By judic ious choice of estimator and form of restrictions at which to evalua te the statistic, a class of asymptotically optimal statistics is obt ained, among which are numbered some familiar classical statistics. A n application is presented for testing common factor restrictions in a single equation dynamic regression model with moving average distu rbances.

This note considers a stochastic version of the Baumol-Tobin model of the demand for money. A dynamic demand function is derived for the case in which independent variables change to new, steady-state values. The (S, s) inventory policy is shown to give rise to an aggregate, partial-adjustment equation with a variable adjustment speed. The methodology is that introduced to target-threshold models by Milbourne, Buckholtz, and Wasan (1983) in their study of the Miller-Orr model.

Journal Article General Equilibrium with a Replenishable Natural Resource Get access Vernon L. Smith Vernon L. Smith California Institute of Technology Search for other works by this author on: Oxford Academic Google Scholar The Review of Economic Studies, Volume 41, Issue 5, December 1974, Pages 105–115, https://doi.org/10.2307/2296374 Published: 01 December 1974

Most studies of the demand for cars are designed to explain new purchases and assume that purchases are divided into net investment and replacement. Replacement is invariably identified with stock depletion, defined either as scrapping (determined by the length of life of a car) or as depreciation (determined by the decline in the price of a used car with age). Implicit in these theories is the assumption that the elasticity of substitution between the new and used car markets is rather high. This assumption is necessary to ensure that the price mechanism will induce consumers to buy new cars to make good the stock depleted by the scrapping or depreciation of used cars. Most empirical evidence indicates that this assumption is not justified and that new and used cars are poor substitutes, e.g. [1], [8] and [6]. Since the low degree of substitution between the two markets insulates new car purchases from the factors that influence the stock of used cars, stock depletion cannot explain replacement purchases of new cars. In this note an alternative approach will be suggested and its use illustrated by the case of new car sales in the US. The advantages of this approach are: (1) replacement is directly observable; (2) the assumption of perfect substitution between new and used car services is not necessary; and (3) it may help account for a series of implausible estimates of the depreciation rate that have been obtained from more orthodox models. It is generally accepted in the US automobile industry that new and used cars are bought by distinct groups. For instance, White in a recent study of the industry [6] says: New cars are not bought by a random selection of car owners but, instead, tend to be bought by a small group who buy new cars comparatively frequently and sell their used cars to the general public to hold. As an approximation, therefore, we can split buyers into two groups, those who buy their car new and those who buy it used, treating these groups as distinct. The demand of the new car buying group is primarily for replacement, since between 80 and 90 per cent of them trade-in or sell an old car when buying a new one; the average time from purchase to resale is between two and three years. This leads us to a definition of replacement as the process by which a consumer disposes of a car bought i years ago and purchases a new one. The existence of a well-developed second-hand market confirms that the replacement interval, i, is considerably shorter than the lifetime of a car, so that replacement does not equal scrapping. This replacement interval will vary between household and we shall observe a distribution of intervals, say c(i), which will determine the lag distribution generating replacement, U, from past purchases, Q; i.e.

Journal Article Risk and the Optimal Utilization of Capital Get access Kenneth R. Smith Kenneth R. Smith University of Wisconsin, Madison Search for other works by this author on: Oxford Academic Google Scholar The Review of Economic Studies, Volume 37, Issue 2, April 1970, Pages 253–259, https://doi.org/10.2307/2296417 Published: 01 April 1970 Article history Received: 01 December 1968 Accepted: 01 July 1969 Published: 01 April 1970

Journal Article Minimization of Economic Rent in Spatial Price Equilibrium Get access Vernon L. Smith Vernon L. Smith Lafayette and Stanford Search for other works by this author on: Oxford Academic Google Scholar The Review of Economic Studies, Volume 30, Issue 1, February 1963, Pages 24–31, https://doi.org/10.2307/2296027 Published: 01 February 1963

What mental models do individuals use to approximate their tax schedule? Using incentivized forecasts of the U.S. Federal income tax schedule, we estimate the prevalence of the “schmeduling” heuristics for constructing mental representations of nonlinear incentive schemes. We find evidence of widespread reliance on the “ironing” heuristic, which linearizes the tax schedule using one’s average tax rate. In our preferred specification, 43% of the population irons. We find no evidence of reliance on the “spotlighting” heuristic, which linearizes the tax schedule using one’s marginal tax rate. We show that the presence of ironing rationalizes a number of empirical patterns in individuals’ perceptions of tax liability across the income distribution. Furthermore, while our empirical framework accommodates a rich class of other misperceptions, we find that a simple model including only ironers and correct forecasters accurately predicts average underestimation of marginal tax rates. We replicate our finding of prevalent ironing, and a lack of other systematic misperceptions, in a controlled experiment that studies real-stakes decisions across exogenously varied tax schedules. To illustrate the policy relevance of the ironing heuristic, we show that it augments the benefits of progressive taxation in a standard model of earnings choice. We quantify these benefits in a calibrated model of the U.S. tax system.

This paper shows that accounting for variation in mistakes can be crucial for welfare analysis. Focusing on consumer underreaction to not-fully-salient sales taxes, we show theoretically that the efficiency costs of taxation are amplified by differences in underreaction across individuals and across tax rates. To empirically assess the importance of these issues, we implement an online shopping experiment in which 2,998 consumers purchase common household products, facing tax rates that vary in size and salience. We replicate prior findings that, on average, consumers underreact to non-salient sales taxes-consumers in our study react to existing sales taxes as if they were only 25% of their size. However, we find significant individual differences in this underreaction, and accounting for this heterogeneity increases the efficiency cost of taxation estimates by at least 200%. Tripling existing sales tax rates nearly doubles consumers' attention to taxes, and accounting for this endogeneity increases efficiency cost estimates by 336%. Our results provide new insights into the mechanisms and determinants of boundedly rational processing of not-fully-salient incentives, and our general approach provides a framework for robust behavioral welfare analysis.

Missing values are endemic in the data sets available to econometricians. This paper suggests a semiparametrically efficient likelihood-based approach to deal with general non-ignorable missing data problems for discrete choice models. Our concern is when the dependent variable and/or covariates are unobserved for some sampling units. A supplementary random sample of observations on all covariates may be available. The key insight of this paper is the recognition of non-response as a modification of choice-based (CB) samples. Semiparametrically efficient generalized method of moments (GMM) estimation appropriate for CB samples is then adapted for the non-response framework considered in this paper. Simulation results for various GMM estimators proposed here are very encouraging.

The timing of elections is flexible in many countries. We study this optimization by first creating a Bayesian learning model of a mean-reverting political support process. We then explore optimal electoral timing, modelling it as a renewable American option with interacting waiting and stopping values. Inter alia, we show that the expected longevity is a convex, then concave, function of the support. Finally, we calibrate our model to the post-1945 Labour-Tory U.K. rivalry. Our story quite well explains when the elections were called. We also show that election options approximately double the expected time in power in the current streak.