Stepwise multiple testing as formalized data snooping

It is common in econometric applications that several hypothesis tests arecarried out at the same time. The problem then becomes how to decide whichhypotheses to reject, accounting for the multitude of tests. In this paper,we suggest a stepwise multiple testing procedure which asymptoticallycontrols the familywise error rate at a desired level. Compared to relatedsingle-step methods, our procedure is more powerful in the sense that itoften will reject more false hypotheses. In addition, we advocate the useof studentization when it is feasible. Unlike some stepwise methods, ourmethod implicitly captures the joint dependence structure of the teststatistics, which results in increased ability to detect alternativehypotheses. We prove our method asymptotically controls the familywise errorrate under minimal assumptions. We present our methodology in the context ofcomparing several strategies to a common benchmark and deciding whichstrategies actually beat the benchmark. However, our ideas can easily beextended and/or modied to other contexts, such as making inference for theindividual regression coecients in a multiple regression framework. Somesimulation studies show the improvements of our methods over previous proposals. We also provide an application to a set of real data.

Global Nash convergence of Foster and Young's regret testing

We construct an uncoupled randomized strategy of repeated play such that, if every player follows such a strategy, then the joint mixed strategy profiles converge, almost surely, to a Nash equilibrium of the one-shot game. The procedure requires very little in terms of players' information about the game. In fact, players' actions are based only on their own past payoffs and, in a variant of the strategy, players need not even know that their payoffs are determined through other players' actions. The procedure works for general finite games and is based on appropriate modifications of a simple stochastic learningrule introduced by Foster and Young.

Compact matrix expressions for generalized Wald tests of equality of moment vectors

Asymptotic chi-squared test statistics for testing the equality ofmoment vectors are developed. The test statistics proposed aregeneralizedWald test statistics that specialize for different settings by inserting andappropriate asymptotic variance matrix of sample moments. Scaled teststatisticsare also considered for dealing with situations of non-iid sampling. Thespecializationwill be carried out for testing the equality of multinomial populations, andtheequality of variance and correlation matrices for both normal andnon-normaldata. When testing the equality of correlation matrices, a scaled versionofthe normal theory chi-squared statistic is proven to be an asymptoticallyexactchi-squared statistic in the case of elliptical data.

Testing I(1) against I(d) alternatives in the presence of deteministic components

This paper discusses the role of deterministic components in the DGP and in the auxiliaryregression model which underlies the implementation of the Fractional Dickey-Fuller (FDF) test for I(1) against I(d) processes with d [0, 1). This is an important test in many economic applications because I(d) processess with d < 1 are mean-reverting although, when 0.5 = d < 1, like I(1) processes, they are nonstationary. We show how simple is the implementation of the FDF in these situations, and argue that it has better properties than LM tests. A simple testing strategy entailing only asymptotically normally distributedtests is also proposed. Finally, an empirical application is provided where the FDF test allowing for deterministic components is used to test for long-memory in the per capita GDP of several OECD countries, an issue that has important consequences to discriminate between growth theories, and on which there is some controversy.

Scaled and adjusted restricted tests in multi-sample analysis of moment structures

We extend to score, Wald and difference test statistics the scaled and adjusted corrections to goodness-of-fit test statistics developed in Satorra and Bentler (1988a,b). The theory is framed in the general context of multisample analysis of moment structures, under general conditions on the distribution of observable variables. Computational issues, as well as the relation of the scaled and corrected statistics to the asymptotic robust ones, is discussed. A Monte Carlo study illustrates thecomparative performance in finite samples of corrected score test statistics.

Bringing game theory to hypothesis testing: Establishing finite sample bounds on inference

Small sample properties are of fundamental interest when only limited data is avail-able. Exact inference is limited by constraints imposed by speci.c nonrandomizedtests and of course also by lack of more data. These e¤ects can be separated as we propose to evaluate a test by comparing its type II error to the minimal type II error among all tests for the given sample. Game theory is used to establish this minimal type II error, the associated randomized test is characterized as part of a Nash equilibrium of a .ctitious game against nature.We use this method to investigate sequential tests for the di¤erence between twomeans when outcomes are constrained to belong to a given bounded set. Tests ofinequality and of noninferiority are included. We .nd that inference in terms oftype II error based on a balanced sample cannot be improved by sequential sampling or even by observing counter factual evidence providing there is a reasonable gap between the hypotheses.

Testing for convergence clubs in income per-capita: A predictive density approach

The paper proposes a technique to jointly test for groupings of unknown size in the cross sectional dimension of a panel and estimates the parameters of each group, and applies it to identifying convergence clubs in income per-capita. The approach uses the predictive density of the data, conditional on the parameters of the model. The steady state distribution of European regional data clusters around four poles of attraction with different economic features. The distribution of incomeper-capita of OECD countries has two poles of attraction and each grouphas clearly identifiable economic characteristics.

Testing the descriptive performance of the rank-dependent utility in the domain of health profiles

Expected utility theory (EUT) has been challenged as a descriptive theoryin many contexts. The medical decision analysis context is not an exception.Several researchers have suggested that rank dependent utility theory (RDUT)may accurately describe how people evaluate alternative medical treatments.Recent research in this domain has addressed a relevant feature of RDU models-probability weighting-but to date no direct test of this theoryhas been made. This paper provides a test of the main axiomatic differencebetween EUT and RDUT when health profiles are used as outcomes of riskytreatments. Overall, EU best described the data. However, evidence on theediting and cancellation operation hypothesized in Prospect Theory andCumulative Prospect Theory was apparent in our study. we found that RDUoutperformed EU in the presentation of the risky treatment pairs in whichthe common outcome was not obvious. The influence of framing effects onthe performance of RDU and their importance as a topic for future researchis discussed.

Exact and approximate stepdown methods for multiple hypothesis testing

Consider the problem of testing k hypotheses simultaneously. In this paper,we discuss finite and large sample theory of stepdown methods that providecontrol of the familywise error rate (FWE). In order to improve upon theBonferroni method or Holm's (1979) stepdown method, Westfall and Young(1993) make eective use of resampling to construct stepdown methods thatimplicitly estimate the dependence structure of the test statistics. However,their methods depend on an assumption called subset pivotality. The goalof this paper is to construct general stepdown methods that do not requiresuch an assumption. In order to accomplish this, we take a close look atwhat makes stepdown procedures work, and a key component is a monotonicityrequirement of critical values. By imposing such monotonicity on estimatedcritical values (which is not an assumption on the model but an assumptionon the method), it is demonstrated that the problem of constructing a validmultiple test procedure which controls the FWE can be reduced to the problemof contructing a single test which controls the usual probability of a Type 1error. This reduction allows us to draw upon an enormous resamplingliterature as a general means of test contruction.

Testing financing constraints on firm investment using variable capital

We consider a dynamic multifactor model of investment with financing imperfections,adjustment costs and fixed and variable capital. We use the model to derive a test offinancing constraints based on a reduced form variable capital equation. Simulation resultsshow that this test correctly identifies financially constrained firms even when the estimationof firms investment opportunities is very noisy. In addition, the test is well specified inthe presence of both concave and convex adjustment costs of fixed capital. We confirmempirically the validity of this test on a sample of small Italian manufacturing companies.

Full insurance, asymmetric information and genetic testing

This paper extends previous resuls on optimal insurance trading in the presence of a stock market that allows continuous asset trading and substantial personal heterogeneity, and applies those results in a context of asymmetric informationwith references to the role of genetic testing in insurance markets.We find a novel and surprising result under symmetric information:agents may optimally prefer to purchase full insurance despitethe presence of unfairly priced insurance contracts, and other assets which are correlated with insurance.Asymmetric information has a Hirschleifer-type effect whichcan be solved by suspending insurance trading. Nevertheless,agents can attain their first best allocations, which suggeststhat the practice of restricting insurance not to be contingenton genetic tests can be efficient.

Testing calibrated general equilibrium models

This paper illustrates the philosophy which forms the basis of calibrationexercises in general equilibrium macroeconomic models and the details of theprocedure, the advantages and the disadvantages of the approach, with particularreference to the issue of testing ``false'' economic models. We provide anoverview of the most recent simulation--based approaches to the testing problemand compare them to standard econometric methods used to test the fit of non--lineardynamic general equilibrium models. We illustrate how simulation--based techniques can be used to formally evaluate the fit of a calibrated modelto the data and obtain ideas on how to improve the model design using a standardproblem in the international real business cycle literature, i.e. whether amodel with complete financial markets and no restrictions to capital mobility is able to reproduce the second order properties of aggregate savingand aggregate investment in an open economy.

A scaled difference chi-square test statistic for moment structure analysis

A family of scaling corrections aimed to improve the chi-square approximation of goodness-of-fit test statistics in small samples, large models, and nonnormal data was proposed in Satorra and Bentler (1994). For structural equations models, Satorra-Bentler's (SB) scaling corrections are available in standard computer software. Often, however, the interest is not on the overall fit of a model, but on a test of the restrictions that a null model say ${\cal M}_0$ implies on a less restricted one ${\cal M}_1$. If $T_0$ and $T_1$ denote the goodness-of-fit test statistics associated to ${\cal M}_0$ and ${\cal M}_1$, respectively, then typically the difference $T_d = T_0 - T_1$ is used as a chi-square test statistic with degrees of freedom equal to the difference on the number of independent parameters estimated under the models ${\cal M}_0$ and ${\cal M}_1$. As in the case of the goodness-of-fit test, it is of interest to scale the statistic $T_d$ in order to improve its chi-square approximation in realistic, i.e., nonasymptotic and nonnormal, applications. In a recent paper, Satorra (1999) shows that the difference between two Satorra-Bentler scaled test statistics for overall model fit does not yield the correct SB scaled difference test statistic. Satorra developed an expression that permits scaling the difference test statistic, but his formula has some practical limitations, since it requires heavy computations that are notavailable in standard computer software. The purpose of the present paper is to provide an easy way to compute the scaled difference chi-square statistic from the scaled goodness-of-fit test statistics of models ${\cal M}_0$ and ${\cal M}_1$. A Monte Carlo study is provided to illustrate the performance of the competing statistics.

When in peril, retrench: Testing the portfolio channel of contagion

One plausible mechanism through which financial market shocks may propagate across countriesis through the impact that past gains and losses may have on investors risk aversion and behavior. This paper presents a stylized model illustrating how heterogeneous changes in investors risk aversion affect portfolio allocation decisions and stock prices. Our empirical findings suggest that when funds returns are below average, they adjust their holdings toward the average (or benchmark) portfolio. In so doing, funds tend to sell the assets of countries in which they were overweight , increasing their exposure to countries in which they were underweight. Based on this insight, the paper constructs an index of financial interdependence which reflects the extent to which countries share overexposed funds. The index helps in explain the pattern of stock market comovement across countries. Moreover, a comparison of this interdependence measure to indices of trade or commercial bank linkages indicates that our index can improve predictions about which countries are more likely to be affected by contagion from crisis centers.

The economic effects of the Protestant Reformation: Testing the Weber hypothesis in the German Lands

Many theories, most famously Max Weber s essay on the Protestant ethic, have hypothesizedthat Protestantism should have favored economic development. With their considerablereligious heterogeneity and stability of denominational affiliations until the 19th century, theGerman Lands of the Holy Roman Empire present an ideal testing ground for this hypothesis.Using population figures in a dataset comprising 272 cities in the years 1300 1900, I find no effectsof Protestantism on economic growth. The finding is robust to the inclusion of a varietyof controls, and does not appear to depend on data selection or small sample size. In addition,Protestantism has no effect when interacted with other likely determinants of economic development.I also analyze the endogeneity of religious choice; instrumental variables estimates ofthe effects of Protestantism are similar to the OLS results.