Maximum likelihood estimation and inference for approximate factor models of high dimension

Bai, Jushan and Li, Kunpeng (2012): Maximum likelihood estimation and inference for approximate factor models of high dimension.

Abstract

An approximate factor model of high dimension has two key features. First, the idiosyncratic errors are correlated and heteroskedastic over both the cross-section and time dimensions; the correlations and heteroskedasticities are of unknown forms. Second, the number of variables is comparable or even greater than the sample size. Thus a large number of parameters exist under a high dimensional approximate factor model. Most widely used approaches to estimation are principal component based. This paper considers the maximum likelihood-based estimation of the model. Consistency, rate of convergence, and limiting distributions are obtained under various identification restrictions. Comparison with the principal component method is made. The likelihood-based estimators are more efficient than those of principal component based. Monte Carlo simulations show the method is easy to implement and an application to the U.S. yield curves is considered

• Item Type: MPRA Paper
• Language: English
• Keywords: Factor analysis; Approximate factor models; Maximum likelihood; Kalman smoother, Principal components; Inferential theory
• Subjects: C - Mathematical and Quantitative Methods > C5 - Econometric Modeling > C51 - Model Construction and Estimation; C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C33 - Panel Data Models ; Spatio-temporal Models

References

Amemiya Y., W. A. Fuller and S. G. Pantula (1987) The asymptotic distributions of some estimators for a factor analysis model, \textit{Journal of Multivariate Analysis}, \textbf{22:1}, 51--64.

Anderson, T. W. (2003) \textit{An Introduction to Multivariate Statistical Analysis}, John Wily \& Sons.

Anderson, T. W. and Y. Amemiya (1988) The asymptotic normal distribution of estimators in factor analysis under general conditions, \textit{The Annals of Statistics}, \textbf{16:2}, 759--771.

Anderson, T. W. and H. Rubin (1956) Statistical inference in factor analysis, In \textit{ Proceedings of the third Berkeley Symposium on mathematical statistics and probability: contributions to the theory of statistics}, University of California Press.

Bai, J. (2003) Inferential theory for factor models of large dimensions. \textit{Econometrica}, \textbf{71(1)}, 135--171.

Bai, J. and K. Li (2012) Statistical analysis of factor models of high dimension, \textit{The Annals of Statistics}, \textbf{40:1}, 436--465.

Bai, J. and S. Ng (2002) Determining the number of factors in approximate factor models,\textit{ Econometrica}, \textbf{70:1}, 191--221.

Bernanke, B. S. and J. Boivin (2003) Monetary policy in a data-rich environment, \textit{Journal of Monetary Economics}, \textbf{50:3}, 525--546

Bernanke, B. S., J. Boivin, and P. Eliasz (2005) Measuring the effects of monetary policy: a factor-augmented vector autoregressive (FAVAR) approach, \textit{The Quarterly Journal of Economics}, \textbf{120:1} 387--422

Breitung, J. and J. Tenhofen (2011) GLS estimation of dynamic factor models, \textit{ Journal of the American Statistical Association}, 106, 1150-1156.

Chamberlain, G. and M. Rothschild (1983) Arbitrage, factor structure, and mean-variance analysis on large asset markets, \textit{Econometrica}, \textbf{51:5}, 1281--1304.

Choi, I. (2007) Efficient Estimation of Factor Models, \textit{Econometric theory}, forthcoming.

Connor, G. and R. A. Korajczyk (1988) Risk and return in an equilibrium APT: Application of a new test methodology, \textit{Journal of Financial Economics}, \textbf{21:2}, 255--289.

Dempster, A.P., Laird, N.M., Rubin, D.B. (1977). Maximum Likelihood from Incomplete Data via the EM Algorithm. {\em Journal of the Royal Statistical Society,} Series B, 39, 1-38.

Diebold, F and C. Li (2006) Forecasting the term structure of government bond yields, \textit{Journal of Econometrics}, \textbf{130:2}, 337--364.

Diebold, F.X., G.D. Rudebusch and B. S. Aruoba (2006) The macroeconomy and the yield curve: a dynamic latent factor approach, \textit{Journal of Econometrics}, \textbf{131:1}, 309--338.

Doz, C., D. Giannone, and L. Reichlin (2011a), A qausi-maximum likelihood approach for large approximate dynamic factor models, \textit{Review of economics and statistics}, forthcoming.

Doz, C., D. Giannone, and L. Reichlin (2011b), A Two-Step estimator for large approximate dynamic factor models based on Kalman filtering, \textit{Journal of Econometrics}, \text{164:1}, 188--205.

Fan, J., Y. Liao, and M. Mincheva (2011). High Dimensional Covariance Matrix Estimation in Approximate Factor Models. {\em Annals of Statistics}, 39, 3320-3356.

Forni, M., M. Hallin, M. Lippi and L. Reichlin (2000), The generalized dynamic-factor model: Identification and estimation. \textit{ Review of Economics and Statistics}, \text{82(4)}: 540-554.

Goyal, A. C. Perignon, C. Villa (2008), How common are common return factors across the NYSE and Nasdaq, {\em Journal of Financial Economics,} 252-271.

Inoue, A. and X. Han (2011) Tests for Parameter Instability in Dynamic Factor Models. Department of Economics, North Carolina State University.

Jenrich, R. I. (1969) Asymptotic properties of non-linear least squares estimators, \textit{The Annals of Mathematical Statistics}, \textbf{40(2)}:633--643.

Jungbacker, B. and S.J. Koopman (2008), Likelihood-based analysis for dynamic factor models, unpublished manuscript, Tinbergen Institute.

Kose, M. A. and C. Otrok, and C.H. Whiteman (2003), International business cycles: World, region, and country-specific factors, \textit{American Economic Review}, \textbf{93(4)}: 1216--1239.

Lawley D. N. and A. E. Maxwell (1971), \textit{Factor Analysis as a Statistical Method}, New York: American Elsevier Publishing Company.

Meng, X.L. and D.B. Rubin (1993), Maximum likelihood estimation via the ECM algorithm: a genenral framework, \textit{Biometrika}, \textbf{80(2)}, 267--278.

Nelson, C.R. and A.F. Siegel (1987) Parsimonious modeling of yield curves, \textit{Journal of Business}, \textbf{60(4)}, 473--489.

Newey, W.K. and D. McFadden (1994) Large sample estimation and hypothesis testing, \textit{Handbook of econometrics}, Vol.4, 2111--2245

Quah, D. and T. Sargent (1992). A dynamic index model for large cross-section. Federal Reserve Bank of Minneapolis, Discussion Paper 77. In James Stock and Mark Watson, editors, Business Cycle, pages 161-200. Univeristy of Chicago Press, 1992.

Ross, S. A. (1976) The arbitrage theory of capital asset pricing, \textit{Journal of Economic Theory},\textbf{13:3}, 341--360.

Stock, J. H. and M. W. Watson (2002a) Macroeconomic forecasting using diffusion indexes" {\em Journal of Business and Economic Statistics}, 20, 147-162.

Stock, J. H. and M. W. Watson (2002b) Forecasting using principal components from a large number of predictors, {\em Journal of the American Statistical Association,} \textbf{97}, 1167--1179.

Wang, P. (2010) Large dimensional factor models with a multi-level factor structure: identification, estimation, and inference. Department of Economics, HKUST.

Watson, M.W. and R.F. Engle. (1983) Alternative algorithms for the estimation of dynamic factor, mimic and varying coefficient regression models. {\em Journal of Econometrics}, 23(3):385--400, 1983.

Wu, C.F.J. (1981) Asymptotic theory of nonlinear least squares estimation, \textit{The Annals of Statistics}, 501--513.

Wu, C.F.J. (1983) On the convergence properties of the EM algorithm, {\em The Annals of Statistics}, 95--103.