Jushan Bai

Estimation Of A Change Point In Multiple Regression Models

This paper studies the least squares estimation of a change point in multiple regressions. Consistency, rate of convergence, and asymptotic distributions are obtained. The model allows for lagged dependent variables and trending regressors. The error process can be dependent and heteroskedastic. For nonstationary regressors or disturbances, the asymptotic distribution is shown to be skewed. The analytical density function and the cumulative distribution function for the general skewed distribution are derived. The analysis applies to both pure and partial changes. The method is used to analyze the response of market interest rates to discount rate changes.

ESTIMATING MULTIPLE BREAKS ONE AT A TIME

Sequential (one-by-one) rather than simultaneous estimation of multiple breaks is investigated in this paper. The advantage of this method lies in its computational savings and its robustness to misspecification in the number of breaks. The number of least-squares regressions required to compute all of the break points is of order T , the sample size. Each estimated break point is shown to be consistent for one of the true ones despite underspecification of the number of breaks. More interestingly and somewhat surprisingly, the estimated break points are shown to be T -consistent, the same rate as the simultaneous estimation. Limiting distributions are also derived. Unlike simultaneous estimation, the limiting distributions are generally not symmetric and are influenced by regression parameters of all regimes. A simple method is introduced to obtain break point estimators that have the same limiting distributions as those obtained via simultaneous estimation. Finally, a procedure is proposed to consistently estimate the number of breaks.

Critical values for multiple structural change tests

to enable proper empirical applications. We provide response surface regressions valid for a wide range of parameters. Copyright Royal Economic Society, 2003

Testing For and Dating Common Breaks in Multivariate Time Series

This paper develops methods for constructing asymptotically valid confidence intervals for the date of a single break in multivariate time series, including I(0), I(1), and deterministically trending regressors. Although the width of the asymptotic confidence interval does not decrease as the sample size increases, it is inversely related to the number of series which have a common break date, so there are substantial gains to multivariate inference about break dates. These methods are applied to two empirical examples: the mean growth rate of output in three European countries, and the mean growth rate of U.S. consumption, investment, and output.

Determining the Number of Primitive Shocks in Factor Models

A widely held but untested assumption underlying macroeconomic analysis is that the number of shocks driving economic fluctuations, q, is small. In this article we associate q with the number of dynamic factors in a large panel of data. We propose a methodology to determineq without having to estimate the dynamic factors. We first estimate a VAR in r static factors, where the factors are obtained by applying the method of principal components to a large panel of data, then compute the eigenvalues of the residual covariance or correlation matrix. We then test whether their eigenvalues satisfy an asymptotically shrinking bound that reflects sampling error. We apply the procedure to determine the number of primitive shocks in a large number of macroeconomic time series. An important aspect of the present analysis is to make precise the relationship between the dynamic factors and the static factors, which is a result of independent interest.

Tests for Skewness, Kurtosis, and Normality for Time Series Data

We present the sampling distributions for the coefficient of skewness, kurtosis, and a joint test of normality for time series observations. We show that when the data are serially correlated, consistent estimates of three-dimensional long-run covariance matrices are needed for testing symmetry or kurtosis. These tests can be used to make inference about any conjectured coefficients of skewness and kurtosis. In the special case of normality, a joint test for the skewness coefficient of 0 and a kurtosis coefficient of 3 can be obtained on construction of a four-dimensional long-run covariance matrix. The tests are developed for demeaned data, but the statistics have the same limiting distributions when applied to regression residuals. Monte Carlo simulations show that the test statistics for symmetry and normality have good finite-sample size and power. However, size distortions render testing for kurtosis almost meaningless except for distributions with thin tails, such as the normal distribution. Combining skewness and kurtosis is still a useful test of normality provided that the limiting variance accounts for the serial correlation in the data. The tests are applied to 21 macroeconomic time series.

Testing Parametric Conditional Distributions of Dynamic Models

This paper proposes a nonparametric test for parametric conditional distributions of dynamic models. The test is of the Kolmogorov type coupled with Khmaladzes martingale transformation. It is asymptotically distribution-free and has nontrivial power against root-n local alternatives. The method is applicable for various dynamic models, including autoregressive and moving average models, generalized autoregressive conditional heteroskedasticity (GARCH), integrated GARCH, and general nonlinear time series regressions. The method is also applicable for cross-sectional models. Finally, we apply the procedure to testing conditional normality and the conditional t-distribution in a GARCH model for the NYSE equal-weighted returns.

Large Dimensional Factor Analysis

Econometric analysis of large dimensional factor models has been a heavily researched topic in recent years. This review surveys the main theoretical results that relate to static factor models or dynamic factor models that can be cast in a static framework. Among the topics covered are how to determine the number of factors, how to conduct inference when estimated factors are used in regressions, how to assess the adequacy of observed variables as proxies for latent factors, how to exploit the estimated factors to test unit root tests and common trends, and how to estimate panel cointegration models. The fundamental result that justifies these analyses is that the method of asymptotic principal components consistently estimates the true factor space. We use simulations to better understand the conditions that can affect the precision of the factor estimates.

Likelihood ratio tests for multiple structural changes

Abstract This paper proposes a likelihood-ratio-type test for multiple structural changes in regression models. The model allows for lagged-dependent variables and trending regressors. The limiting distribution of the test is derived. We show that asymptotic critical values can be obtained analytically. In addition, the number and the locations of change points can be consistently determined via the test procedure. The method is straightforward to implement.

Instrumental Variable Estimation In A Data Rich Environment

We consider estimation of parameters in a regression model with endogenous regressors. The endogenous regressors along with a large number of other endogenous variables are driven by a small number of unobservable exogenous common factors. We show that the estimated common factors can be used as instrumental variables and they are more efficient than the observed variables in our framework. Whereas standard optimal generalized method of moments estimator using a large number of instruments is biased and can be inconsistent, the factor instrumental variable estimator (FIV) is shown to be consistent and asymptotically normal, even if the number of instruments exceeds the sample size. Furthermore, FIV remains consistent even if the observed variables are invalid instruments as long as the unobserved common components are valid instruments. We also consider estimating panel data models in which all regressors are endogenous but share exogenous common factors. We show that valid instruments can be constructed from the endogenous regressors. Although single equation FIV requires no bias correction, the faster convergence rate of the panel estimator is such that a bias correction is necessary to obtain a zero-centered normal distribution.