Econometrics

THIS PAPER DISCUSSES the bias that results from using nonrandomly selected samples to estimate beliavioral relationships as an ordinary specification bias that arises because of a missing data problem. In contrast to the usual analysis of "omitted variables" or specification error ...

SUMMARY The propensity score is the conditional probability of assignment to a particular treatment given a vector of observed covariates. Both large and small sample theory show that adjustment for the scalar propensity score is sufficient to remove bias due to all observed covariates. ...

Estimation of the dynamic error components model is considered using two alternative linear estimators that are designed to improve the properties of the standard first-differenced GMM estimator. Both estimators require restrictions on the initial conditions process. Asymptotic efficiency comparisons and Monte Carlo simulations for the simple AR(1) model demonstrate the dramatic improvement in performance of the proposed estimators compared to the usual first-differenced GMM estimator, and compared to non-linear GMM. The importance of these results is illustrated in an application to the estimation of a labour demand model using company panel data.

Right to Buy" (RTB), a large-scale natural experiment by which incumbent tenants in public housing could buy properties at heavily-subsidised prices, increased the homeownership rate in Britain by over 10 percentage points between 1980 and the late 1990s. This paper studies its impact on crime, showing that RTB generated significant reductions in property and violent crime that persist up to today. The gentrification of incumbent tenants and their behavioural changes were the main drivers of the crime reduction. This is evidence of a novel means by which gentrification, and housing provision, may have contributed to the sizable crime drops observed in several Western economies in the 1990s and early 2000s.

The field now called Evolutionary Computation had a slow start. In the late 60s and early 70s a number of researchers in the USA and Germany applied the principles of Darwinian evolution, based on natural selection, for problem solving. Independently from each other they established the power of evolutionary techniques and worked on the theory and applications of their own approach. These were the times of rather separate development of Genetic Algorithms, Evolution Strategies and Evolutionary Programming. From the early 90s it is more and more acknowledged that the different approaches share the same basic principles, while differing only in technical details, terminology and sometimes in the philosophy behind it. In the meanwhile, a new branch, called Genetic Programming, has also emerged and joined the family. The entire family of algorithms is called nowadays the family of Evolutionary Algorithms-a name attempting to cover all the aforementioned techniques, and even more. An Evolutionary Algorithm (EA) can actually be any population-based, stochastic search algorithm that uses a (heuristic) quality measure, called fitness, of candidate solutions and applies reproduction operators to create, and fitness-based selection to reduce, diversity in the population.

This paper proposes unit root tests for dynamic heterogeneous panels based on the mean of individual unit root statistics. In particular it proposes a standardized t-bar test statistic based on the (augmented) Dickey–Fuller statistics averaged across the groups. Under a general setting this statistic is shown to converge in probability to a standard normal variate sequentially with T (the time series dimension) →∞, followed by N (the cross sectional dimension) →∞. A diagonal convergence result with T and N→∞ while N/T→k,k being a finite non-negative constant, is also conjectured. In the special case where errors in individual Dickey–Fuller (DF) regressions are serially uncorrelated a modified version of the standardized t-bar statistic is shown to be distributed as standard normal as N→∞ for a fixed T, so long as T>5 in the case of DF regressions with intercepts and T>6 in the case of DF regressions with intercepts and linear time trends. An exact fixed N and T test is also developed using the simple average of the DF statistics. Monte Carlo results show that if a large enough lag order is selected for the underlying ADF regressions, then the small sample performances of the t-bar test is reasonably satisfactory and generally better than the test proposed by Levin and Lin (Unpublished manuscript, University of California, San Diego, 1993).

This paper develops a new approach to the problem of testing the existence of a level relationship between a dependent variable and a set of regressors, when it is not known with certainty whether the underlying regressors are trend- or first-difference stationary. The proposed tests are based on standard F- and t-statistics used to test the significance of the lagged levels of the variables in a univariate equilibrium correction mechanism. The asymptotic distributions of these statistics are non-standard under the null hypothesis that there exists no level relationship, irrespective of whether the regressors are I(0) or I(1). Two sets of asymptotic critical values are provided: one when all regressors are purely I(1) and the other if they are all purely I(0). These two sets of critical values provide a band covering all possible classifications of the regressors into purely I(0), purely I(1) or mutually cointegrated. Accordingly, various bounds testing procedures are proposed. It is shown that the proposed tests are consistent, and their asymptotic distribution under the null and suitably defined local alternatives are derived. The empirical relevance of the bounds procedures is demonstrated by a re-examination of the earnings equation included in the UK Treasury macroeconometric model. Copyright © 2001 John Wiley & Sons, Ltd.

We consider the problem of comparing complex hierarchical models in which the number of parameters is not clearly defined. Using an information theoretic argument we derive a measure p D for the effective number of parameters in a model as the difference between the posterior mean of the deviance and the deviance at the posterior means of the parameters of interest. In general p D approximately corresponds to the trace of the product of Fisher's information and the posterior covariance, which in normal models is the trace of the 'hat' matrix projecting observations onto fitted values. Its properties in exponential families are explored. The posterior mean deviance is suggested as a Bayesian measure of fit or adequacy, and the contributions of individual observations to the fit and complexity can give rise to a diagnostic plot of deviance residuals against leverages. Adding p D to the posterior mean deviance gives a deviance information criterion for comparing models, which is related to other information criteria and has an approximate decision theoretic justification. The procedure is illustrated in some examples, and comparisons are drawn with alternative Bayesian and classical proposals. Throughout it is emphasized that the quantities required are trivial to compute in a Markov chain Monte Carlo analysis.

This book seeks to integrate research on cause and effect inference from cognitive science, econometrics, epidemiology, philosophy, and statistics+ It puts forward the work of its author, his collaborators, and others over the past two decades as a new account of cause and effect inference that can aid practical

We propose a test of the null hypothesis that an observable series is stationary around a deterministic trend. The series is expressed as the sum of deterministic trend, random walk, and stationary error, and the test is the LM test of the hypothesis that the random walk has zero variance.

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.

The paper provides a survey of the work that has been done in financial econometrics in the past decade. It proceeds by first establishing a set of stylized facts that are characteristics of financial series and then by detailing the range of techniques that have been developed to model series which possess these characteristics. Both univariate and multivariate models are considered.

Variable selection is fundamenta l to high-dimensiona l statistical modeling, including nonparametri c regression. Many approaches in use are stepwise selection procedures , which can be computationally expensive and ignore stochastic errors in the variable selection process. In this article, penalized likelihood approache s are proposed to handle these kinds of problems. The proposed methods select variables and estimate coef cients simultaneously. Hence they enable us to construct con dence intervals for estimated parameters. The proposed approaches are distinguished from others in that the penalty functions are symmetric, nonconcav e on 401ˆ5, and have singularities at the origin to produce sparse solutions. Furthermore, the penalty functions should be bounded by a constant to reduce bias and satisfy certain conditions to yield continuous solutions. A new algorithm is proposed for optimizing penalized likelihood functions. The proposed ideas are widely applicable. They are readily applied to a variety of parametric models such as generalized linear models and robust regression models. They can also be applied easily to nonparametri c modeling by using wavelets and splines. Rates of convergenc e of the proposed penalized likelihood estimators are established. Furthermore, with proper choice of regularization parameters, we show that the proposed estimators perform as well as the oracle procedure in variable selection; namely, they work as well as if the correct submodel were known. Our simulation shows that the newly proposed methods compare favorably with other variable selection techniques. Furthermore, the standard error formulas are tested to be accurate enough for practical applications.

The research program of the Center for Economic Studies produces a wide range of theoretical and empirical economic analyses which serve to improve the statistical programs of the U. S. Bureau of the Census. Many of these analyses take the form of research papers. The purpose of the Discussion Papers is to circulate intermediate and final results of this research among interested readers within and outside the Census Bureau. The opinions and conclusions expressed in the papers are those of the authors and do not necessarily represent those of the U. S. Bureau of the Census. All papers are screened to ensure that they do not disclose confidential information. Persons who wish to obtain a copy of the paper, submit comments about the paper, or obtain general information about the series should contact Sang. V.

Theoretical models predict that overcon dent investors trade excessively. We test this prediction by partitioning investors on gender. Psychological research demonstrates that, in areas such as nance, men are more overcon dent than women. Thus, theory predicts that men will trade more excessively than women. Using account data for over 35,000 households from a large discount brokerage, we analyze the common stock investments of men and women from February 1991 through January 1997. We document that men trade 45 percent more than women. Trading reduces men's net returns by 2.65 percentage points a year as opposed to 1.72 percentage points for women.

This paper disentangles the impact of schools and teachers in influencing achievement with special attention given to the potential problems of omitted or mismeasured variables and of student and school selection. Unique matched panel data from the UTD Texas Schools Project permit the identification of teacher quality based on student performance along with the impact of specific, measured components of teachers and schools. Semiparametric lower bound estimates of the variance in teacher quality based entirely on within-school heterogeneity indicate that teachers have powerful effects on reading and mathematics achievement, though little of the variation in teacher quality is explained by observable characteristics such as education or experience. The results suggest that the effects of a costly ten student reduction in class size are smaller than the benefit of moving one standard deviation up the teacher quality distribution, highlighting the importance of teacher effectiveness in the determination of school quality.

A presentation of the Partial Least Squares approach to Structural Equation Modeling (or PLS Path Modeling) is given together with a discussion of its extensions. This approach is compared with the estimation of Structural Equation Modeling by means of maximum likelihood (SEM-ML). Notwithstanding, this approach still shows some weaknesses. In this respect, some new improvements are proposed. Furthermore, PLS path modeling can be used for analyzing multiple tables so as to be related to more classical data analysis methods used in this ÿeld. Finally, a complete treatment of a real example is shown through the available software.

Bereits im 19. Jahrhundert formulierte John S. Mill eine einfache aber unerlässliche Voraussetzung für kausale Beziehungen: "the cause has to precede the effect in time". Für eine aufgeklärte Wissenschaft war damit der Königsweg für die Analyse kausaler Beziehungen vorgezeichnet, der allein dadurch beschritten w erden kann, dass im Experiment die durch einen bewusst gesetzten Stimulus behandelte Versuchgruppe eine Veränderung erfährt und sich darum -nachdem eine gewisse Zeit verstrichen ist -von der Kontrollgruppe unterscheidet. Kausale Analyse im experimentellen Design impliziert eine Längsschnittperspektive, weil Messungen der abhängigen Variable sowohl vor als auch nach Verabreichung des experimentellen Stimulus durchgeführt werden und sich bei der zweiten Messung ceteris paribus die Unterschiede zwischen den im Idealfall zufällig zusammengesetzten Gruppen logisch zwingend auf den Stimulus zurückführen lassen. So überzeugend die Rationalität der experimentellen Erkenntnismethode auch ist -in der deutschen Soziologie stellt sie eher eine Randerscheinung dar und man greift zumeist auf quasi-experimentelle Designs zurück. 1 Allerdings ermöglicht eine Längsschnittperspektive auch in diesen Studien kausale Analysen, die, wenngleich nicht ohne Theorie, wesentlich näher an der Empirie orientiert sein können, als Querschnittsanalysen. Analysen über die Zeit ermöglichen zeitveränderliche Messungen der abhängigen und unabhängigen Variablen. Auf diese Weise nähert sich die häufig auf Umfragedaten basierende Kausalanalyse dem experimentellen Design wieder an, da untersucht werden kann, inwieweit der Prozess der Veränderung der abhängigen Variable aus dem Prozess der Veränderung von unabhängigen Variablen resultiert. Daher ist es zu begrüßen, wenn in Lehrbüchern systematisch und verständlich in statistische Verfahren der Längsschnittanalyse eingeführt wird. Das im Jahre 2003 erschienene Buch "Applied longitudinal analysis" von Singer und Willet erfüllt diese Aufgabe in sehr innovativer Weise, da erstmals zwei unterschiedliche Zugänge zur Längsschnittanalyse ausführlich dargestellt und miteinander verglichen werden. Es handelt sich dabei einerseits um Messwiederholungsmodelle, die als "multilevel model for change" bezeichnet werden, andererseits um Hazardmodelle für diskrete und stetige Zeit, in der deutschsprachigen Soziologie eher bekannt unter der Bezeichnung "Ereignisanalyse". Im Prinzip ist ein derartiges Lehrbuch schon lange überfällig, da die beiden methodischen Ansätze des Messwiederholungsdesigns (auch bekannt als Panelanalyse) und der Ereignisanalyse zumeist in unterschiedlichen Forschungszweigen Anwendung finden und leider manchmal Unkenntnis herrscht über die Angemessenheit oder über mögliche Vorteile des jeweils anderen methodischen Zugangs. 1 Vgl. zu sozialwissenschaftlichen und medizinischen Experimenten insbesondere David M. : Design and Analysis of group randomized trials. Oxford: University Press.