Department of Economics
http://hdl.handle.net/10919/24208
Mon, 16 Sep 2019 22:46:56 GMT
20190916T22:46:56Z

Nonnested Model Selection/Validation: Making Credible Postsample Inference Feasible
http://hdl.handle.net/10919/91475
Ashley, Richard
Sat, 01 Apr 1995 00:00:00 GMT
http://hdl.handle.net/10919/91475
19950401T00:00:00Z
Effective, credible inference with respect to the postsample forecasting performance of time series models is widely held to be infeasible. Consequently, the model selection and Grangercausality literatures have focussed almost exclusively on insample tests, which can easily be biased by typical specificationsearch activity. Indeed, the postsample error series generated by competing models are typically crosscorrelated, serially correlated, and not even clearly gaussian; thus, postsample inference procedures are necessarily only asymptotically valid. As a result, a postsample period large enough to yield credible inferences is perceived to be too costly in terms of sample observations foregone. This paper describes a new, resampling based, approach to postsample inference which, by explicitly quantifying the inferential uncertainty caused by the limited length of the postsample period, makes it feasible to obtain credible postsample inferences using postsample periods of reasonable length. For a given target level of inferential precision – e.g., significance at the 5% level – this new approach also provides explicit estimates of both how strong the postsample forecasting efficiency evidence in favor of one of two models must be (for a given length postsample period) and how long a postsample period is necessary, if the evidence is of given strength. These results indicate that postsample model validation periods substantially longer than the 5 to 20 periods typically reserved in past studies are necessary in order to credibly detect 20%  30% MSE reductions. This approach also quantifies the inferential impact of different forecasting efficiency criterion choices – e.g., MSE vs. MAE vs. asymmetric criteria and the use of expected loss differentials (as in Diebold and Mariano(1994)) vs. ratios of expected losses. The value of this new approach to postsample inference is illustrated using postsample forecasting error data from Ashley, Granger, and Schmalensee(1980), in which evidence was presented for unidirectional Grangercausation from fluctuations in aggregate U.S. consumption expenditures to fluctuations in U.S. aggregate expenditures on advertising.

Beyond Optimal Forecasting
http://hdl.handle.net/10919/91473
Ashley, Richard A.
Sat, 04 Nov 2006 00:00:00 GMT
http://hdl.handle.net/10919/91473
20061104T00:00:00Z
While the conditional mean is known to provide the minimum mean square error (MSE) forecast – and hence is optimal under a squarederror loss function – it must often in practice be replaced by a noisy estimate when model parameters are estimated over a small sample. Here two results are obtained, both of which motivate the use of forecasts biased toward zero (shrinkage forecasts) in such settings. First, the noisy forecast with minimum MSE is shown to be a shrinkage forecast. Second, a condition is derived under which a shrinkage forecast stochastically dominates the unbiased forecast over the class of loss functions monotonic in the forecast error magnitude. The appropriate amount of shrinkage from either perspective depends on a noisiness parameter which must be estimated, however, so the actual reduction in expected losses from shrinkage forecasting is an empirical issue. Simulation results over forecasts from a large variety of multiple regression models indicate that feasible shrinkage forecasts typically do provide modest improvements in forecast MSE when the noise in the estimate of the conditional mean is substantial.

An Elementary Method for Detecting and Modeling Regression Parameter Variation Across Frequences With an Application to Testing the Permanent Income Hypothesis
http://hdl.handle.net/10919/91476
Boon, Tan Hui; Ashley, Richard
Sat, 01 Mar 1997 00:00:00 GMT
http://hdl.handle.net/10919/91476
19970301T00:00:00Z
A simple technique for directly testing the parameters of a time series regression model for instability across frequencies is presented. The method can be easily implemented in the time domain, so parameter instability across frequency bands can be conveniently detected and modeled in conjunction with other econometric features of the problem at hand, such as simultaneity, cointegration, missing observations, crossequation restrictions, etc. The usefulness of the new technique is illustrated with an application to a cointegrated consumptionincome regression model, yielding a straightforward test of the permanent income hypothesis.

Sensitivity Analysis of OLS Multiple Regression Inference with Respect to Possible Linear Endogeneity in the Explanatory Variables
http://hdl.handle.net/10919/91478
Ashley, Richard A.; Parmeter, Christopher F.
Mon, 17 Jun 2019 00:00:00 GMT
http://hdl.handle.net/10919/91478
20190617T00:00:00Z
This work describes a versatile sensitivity analysis of OLS hypothesis test rejection pvalues with respect to possible endogeneity in the explanatory variables of the usual kvariate linear multiple regression model which practitioners can readily deploy in their research. This sensitivity analysis is based on a derivation of the asymptotic distribution of the OLS parameter estimator, but extended in a particularly straightforward way to the case where some or all of the explanatory variables are endogenous to a specified degree — that is, where the population covariances of the explanatory variables with the model errors are given. In exchange for restricting attention to possible endogeneity which is solely linear in nature, no additional model assumptions must be made, beyond the usual ones for a model with stochastic regressors. In addition, we also use simulation methods to quantify the uncertainty in the sensitivity analysis results introduced by replacing the population variancecovariance matrix by its sample estimate. The usefulness of the analysis — as a `screen' for potential endogeneity issues — is illustrated with an example from the empirical growth literature.

A Reconsideration of Consistent Estimation of a Dynamic Panel Data Model in the Random Effects (Error Components) Framework
http://hdl.handle.net/10919/91477
Ashley, Richard A.
Mon, 19 Apr 2010 00:00:00 GMT
http://hdl.handle.net/10919/91477
20100419T00:00:00Z
It is widely believed that the inclusion of lagged dependent variables in a panel data model necessarily renders the Random Effects (RE) estimators, based on OLS applied to the quasidifferenced variables, inconsistent. It is shown here that this belief is incorrect under the usual assumption made in this context — i.e., that the other regressors are strictly exogenous. This result follows from the fact that lagged values of the deviation of the quasidifferenced dependent variable from its mean can be written as a weighted sum of the past values of the quasidifferenced model error term, whereas these quasidifferenced errors are serially uncorrelated by construction. The RE estimators are therefore consistent. Thus, since instrumental variables methods { e.g., Arellano and Bond (1991) — clearly provide less precise estimates, the RE estimates are preferable if a Hausman test is unable to reject the null hypothesis that the parameter estimates of interest from both methods are equal.

International Evidence On The Oil PriceReal Output Relationship: Does Persistence Matter?
http://hdl.handle.net/10919/91472
Ashley, Richard; Tsang, Kwok Ping
Wed, 28 Aug 2013 00:00:00 GMT
http://hdl.handle.net/10919/91472
20130828T00:00:00Z
The literature on the relationship between real output growth and the growth rate in the price of oil, including an allowance for asymmetry in the impact of oil prices on output, continues to evolve. Here we show that a new technique, which allows us to control for both this asymmetry and also for the persistence of oil price changes, yields results implying that such control is necessary for a statistically adequate specification of the relationship. The new technique also yields an estimated model for the relationship which is more economically interpretable. In particular, using quarterly data from 1976 – 2007 on each of six countries which are essentially net oil importers, we find that changes in the growth rate of oil prices which persist for more than four years have a large and statistically significant impact on future output growth, whereas less persistent changes (lasting more than one year but less than four years) have no significant impact on output growth. In contrast, ‘temporary’ fluctuations in the oil price growth rate – persisting for only a year or less – again have a large and statistically significant impact on output growth for most of these countries. The results for the single major net oil producer in our sample (Norway) are distinct in an interesting way.

Identification of Coefficients in a Quadratic Moving Average Process Using the Generalized Method of Moments
http://hdl.handle.net/10919/91474
Ashley, Richard A.; Patterson, Douglas M.
Fri, 21 Jun 2002 00:00:00 GMT
http://hdl.handle.net/10919/91474
20020621T00:00:00Z
The output of a causal, stable, timeinvariant nonlinear filter can be approximately represented by the linear and quadratic terms of a finite parameter Volterra series expansion. We call this representation the “quadratic nonlinear MA model” since it is the logical extension of the usual linear MA process. Where the actual generating mechanism for the data is fairly smooth, this quadratic MA model should provide a better approximation to the true dynamics than the twostate threshold autoregression and Markov switching models usually considered. As with linear MA processes, the nonlinear MA model coefficients can be estimated via least squares fitting, but it is essential to begin with a reasonably parsimonious model identification and nonarbitrary preliminary estimates for the parameters. In linear ARMA modeling these are derived from the sample correlogram and the sample partial correlogram, but these tools are confounded by nonlinearity in the generating mechanism. Here we obtain analytic expressions for the second and third order moments – the autocovariances and third order cumulants – of a quadratic MA process driven by i.i.d. symmetric innovations. These expressions allow us to identify the significant coefficients in the process by using GMM to obtain preliminary coefficient estimates and their concomitant estimated standard errors. The utility of the method for specifying nonlinear time series models is illustrated using artificially generated data.

Amenities, affordability, and housing vouchers
http://hdl.handle.net/10919/88861
Bieri, David S.; Dawkins, Casey J.
Tue, 19 Jun 2018 00:00:00 GMT
http://hdl.handle.net/10919/88861
20180619T00:00:00Z
Against the background of an emerging rental affordability crisis, we examine how the standard rule that households should not spend more than 30% of their income on housing expenditures leads to inefficiencies in the context of federal lowincome housing policy. We quantify how the current practice of locally indexing individual rent subsidies in the Housing Choice Voucher (HCV) program regardless of qualityoflife conditions implicitly incentivizes recipients to live in highamenity areas. We also assess a novel scenario for housing policy reform that adjusts subsidies by the amenity expenditures of lowincome households, permitting national HCV program coverage to increase. © 2018 The Authors. Journal of Regional Science published by Wiley Periodicals, Inc.

Land and Racial Wealth Inequality
http://hdl.handle.net/10919/80469
Miller, Melinda C.
Sat, 01 Jan 2011 00:00:00 GMT
http://hdl.handle.net/10919/80469
20110101T00:00:00Z
...Explanations for the persistent and large racial wealth gap largely fall into two categories. First, racially discriminatory policies in credit markets, labor markets, school finance, and other institutions may have inhibited the ability of blacks to earn income and accumulate wealth. And, second, the effect of such policies may have amplified the impact of an alternate source of the racial wealth gap—low initial levels of black wealth. During slavery, law and custom prevented most slaves from owning property or other assets. After the Thirteenth Amendment abolished slavery, emancipation grants of “forty acres and a mule” were proposed to remedy the freedmen’s lack of capital. They never came to fruition, thus ensuring that former slaves entered freedom with little to no wealth, lagging substantially behind whites.

Selection and Historical Height Data: Evidence from the 1892 Boas Sample of the Cherokee Nation
http://hdl.handle.net/10919/80468
Miller, Melinda C.
Sun, 01 Jan 2017 00:00:00 GMT
http://hdl.handle.net/10919/80468
20170101T00:00:00Z
Economists have increasingly turned to height data to gain insight into a population’s standard of living. Because height measures are used when other data is unavailable, testing their reliability can be difficult, and concerns over sample selection have lead to several vigorous debates within the heights literature. In this paper, I use a unique contemporaneous census to gauge the extent of selection into a contested sample of American Indian heights. I have linked people from the 1892 Boas sample of the Cherokee Nation to the 1890 Cherokee Census. An initial analysis finds evidence of negative selection into the Boas sample. A detailed examination of those measured reveals a more complex story. Two distinct groups are present within the data. The first group consists of 64 members of the Cherokee elite. Their households owned more land, had invested more in improvements to their land, and had higher literacy rates. The remainder of the Boas sample is poor relative to both the elite and the rest of the Cherokee Nation. Part, but not all, of this difference is due to their residential location. Forty percent of the Boas sample lived in poorest district of Cherokee Nation. These differences in wealth between the two groups were mirrored by a fairly dramatic difference in average heights. The average height of all men in elite group was 173.9 cm while the nonelite were several centimeters shorter at just 171.2 cm.