David W. Wilcox

Judging Instrument Relevance in Instrumental Variables Estimation

Recent research has emphasized the poor finite-sample performance of the instrumental variables estimator when the instruments are weakly correlated with the regressors. The authors show how the canonical correlations between regressors and instruments can provide a measure of instrument relevance in the general multiple-instrument-multiple-regressor case. However, their simulation results indicate that any such relevance measure probably has little practical merit, as its use may actually exacerbate the poor finite-sample properties of the instrumental variables estimator. Copyright 1996 by Economics Department of the University of Pennsylvania and the Osaka University Institute of Social and Economic Research Association.

Mismeasurement in the Consumer Price Index: An Evaluation

A number of analysts have claimed recently that the Consumer Price Index overstates the annual increase in the cost of living. This paper develops a framework for studying measurement problems in the CPI and systematically analyzes the available evidence concerning the magnitude of these problems. The evidence suggests that the bias is centered on 1.0 percentage point per year. To take into account uncertainty about the extent of the bias, the paper presents a probability distribution for the bias rather than a point estimate or range. It is estimated that there is a 10% chance that the bias is less than 0.6 percentage point and a 10% chance that it is greater than 1.5 percentage points per year. CPI methodology overstates the price increase for medical procedures that are subject to technological improvement. To illustrate this point and to show how better to measure medical care prices, the paper presents a prototypical price index for cataract surgery. This index grows much more slowly than a price index for cataract surgery constructed using the CPI methodology.

A Quantitative Exploration of the Opportunistic Approach to Disinflation

Under a conventional policy rule, a central bank adjusts its policy rate linearly according to the gap between inflation and its target, and the gap between output and its potential. Under “the opportunistic approach to disinflation” a central bank controls inflation aggressively when inflation is far from its target, but concentrates more on output stabilization when inflation is close to its target, allowing supply shocks and unforeseen fluctuations in aggregate demand to move inflation within a certain band. We use stochastic simulations of a small-scale rational expectations model to contrast the behavior of output and inflation under opportunistic and linear rules.

Econometric models and the monetary policy process

Abstract Econometric models play an important role in the monetary policy process of the Federal Reserve Board. Large-scale macroeconometric models are employed for forecasting, policy simulations, and the evaluation of monetary policy rules. However, in this work, we employ a mix of the algorithmic application of these models and judgment guided by information not available to models. We describe this approach and present an assessment of its strengths and weaknesses. The experience of the 1990–1991 recession and the subsequent recovery is used to illustrate some of the practical difficulties surrounding the use of econometric models for policy analysis.

A Comparison of Alternative Instrumental Variables Estimators of a Dynamic Linear Model

Using a dynamic linear equation that has a conditionally homoscedastic moving average disturbance, we compare two parameterizations of a commonly used instrumental variables estimator to one that is asymptotically optimal in a class of estimators that includes the conventional one. We find that, for some plausible data-generating processes, the optimal one is distinctly more efficient asymptotically. Simulations indicate that in samples of size typically available, asymptotic theory describes the distribution of the parameter estimates reasonably well but that test statistics sometimes are poorly sized.

Some Evidence on Finite Sample Behavior of an Instrumental Variables Estimator of the Linear Quadtratic Inventory Model

We evaluate some aspects of the finite sample distribution of an instrumental variables estimator of a first order condition of the Holt et al. (1960) linear quadratic inventory model. We find that for some but not all empirically relevant data generating processes and sample sizes, asymptotic theory predicts a wide dispersion of parameter estimates, with a substantial finite sample probability of estimates with incorrect signs. For such data generating processes, simulation evidence suggests that different choices of left hand side variables often produce parameter estimates of an opposite sign. More generally, while the asymptotic theory often provides a good approximation to the finite sample distribution, sometimes it does not

Estimation and inference in the linear-quadratic inventory model

Abstract We summarize some recent work of ours on estimation and hypothesis testing on the parameters of the linear-quadratic inventory model. For some data-generating processes calibrated to estimates from some existing studies, this work uses (1) asymptotic theory to compare alternative estimators on the basis of the asymptotic efficiency of parameter estimates, (2) asymptotic theory and simulations to consider how likely one will be to get sharp estimates of the parameters of the model, and (3) simulations to see how accurately sized are hypothesis tests about the parameters of the model.

Why Do Firms Offer Risky Defined-Benefit Pension Plans?

Even risky pension sponsors could offer essentially riskless pension promises by contributing a sufficient level of resources to their pension trust funds and by investing those resources in fixed-income securities designed to deliver their payoffs just as pension obligations are coming due. However, almost no firm has chosen to fund its plan in this manner. We study the optimal funding choice for plan sponsors by developing a simple model of pension financing in which the total compensation offered to workers must clear the labor market. We find that if workers understand the implications of pension risk, they will demand greater compensation for riskier pension promises than for safer ones, all else equal. Indeed, in our model, pension sponsors maximize their value by making their pension promises free of risk. We close by positing some explanations for why no real-world firm follows the prescription of our model.

Should Risky Firms Offer Risk-Free DB Pensions?

We develop a simple model of pension financing to study the effects of pension risk on shareholder value. In the model, firms minimize costs, total compensation must clear the labor market, and a government pension insurer guarantees a portion of promised benefits. We find that in the absence of mispriced pension insurance, the optimal pension strategy under most specifications is to immunize all sources of market risk. Mispriced pension insurance, however, gives firms the incentive to introduce risk into their pension promises, offering an explanation for some of the observed prevalence of risky pensions in the real world.

The Unequal Distribution of Economic Education: A Report on the Race, Ethnicity, and Gender of Economics Majors at Us Colleges and Universities

The distribution of economic education among US college graduates is quite unequal: female and underrepresented minority undergraduates, collectively, major in economics at 0.36 the rate that white, non-Hispanic male students do. This paper makes a four-part contribution to address this imbalance. First and foremost, we provide detailed comparative data at the institution level to provoke and inform the attention of economists and senior administrators at colleges and universities, among others. Second, we establish a definition of full inclusion in economic education on college and university campuses and use that definition to evaluate the status quo and to compare institutions. Third, we illuminate the reasons why the need to improve the distribution of economic education is urgent, including the imperative to support economic policymaking. Lastly, we point the way forward, identifying both currently available resources and reasonable next steps for all involved parties to take.