Expectation of quadratic forms in normal and nonnormal variables with applications. (English) Zbl 1181.62075

Bao, Yong; Ullah, Aman

J. Stat. Plann. Inference 140, No. 5, 1193-1205 (2010).

Summary: We derive some new results on the expectation of quadratic forms in normal and non-normal variables. Using a non-stochastic operator, we show that the expectation of the product of an arbitrary number of quadratic forms in noncentral normal variables follows a recurrence formula. This formula includes the existing result for central normal variables as a special case. For nonnormal variables, while the existing results are available only for quadratic forms of limited order (up to 3), we derive analytical results to a higher order 4. We use the nonnormal results to study the effects of nonnormality on the finite sample mean squared error of the OLS estimator in an AR(1) model and the QMLE in an MA(1) model.

MSC:

62H10	Multivariate distribution of statistics
62M10	Time series, auto-correlation, regression, etc. in statistics (GARCH)
62H12	Estimation in multivariate analysis

Keywords:

expectation; quadratic form; nonnormality

References:

[1]	Bao, Y., The approximate moments of the least squares estimator for the stationary autoregressive model under a general error distribution, Econometric theory, 23, 1013-1021, (2007) · Zbl 1237.62110
[2]	Bao, Y.; Ullah, A., Finite sample properties of maximum likelihood estimator in spatial models, Journal of econometrics, 137, 396-413, (2007) · Zbl 1360.62474
[3]	Bao, Y.; Ullah, A., The second-order bias and Mean squared error of estimators in time series models, Journal of econometrics, 140, 650-669, (2007) · Zbl 1247.91148
[4]	Chandra, R., 1983. Estimation of econometric models when disturbances are not necessarily normal. Ph.D. Dissertation, Department of Statistics, Lucknow University, India.
[5]	Don, F.J.H., The expectations of products of quadratic forms in normal variables, Statistica neerlandica, 33, 73-79, (1979) · Zbl 0416.62041
[6]	Dressel, P.L., Statistical semi-invariants and their estimates with particular emphasis on their relation to algebraic invariants, Annals of mathematical statistics, 11, 33-57, (1940) · Zbl 0063.01163
[7]	Dufour, J.-M., Unbiasedness of predictions from estimated autoregressions when the true order is unknown, Econometrica, 52, 209-215, (1984) · Zbl 0527.62086
[8]	Fisher, R.A., Moments and product moments of sampling distributions, Proceedings of the London mathematical society, 30, 199-238, (1928) · JFM 55.0924.01
[9]	Ghazal, G.A., Recurrence formula for expectations of products of quadratic forms, Statistics and probability letters, 27, 101-109, (1996) · Zbl 0849.62028
[10]	Hoque, A.; Magnus, J.R.; Pesaran, B., The exact multi-period Mean-square forecast error for the first-order autoregressive model, Journal of econometrics, 39, 327-346, (1988) · Zbl 0668.62070
[11]	Kadane, J.B., Comparison of k-class estimators when the disturbances are small, Econometrica, 39, 723-737, (1971) · Zbl 0232.62011
[12]	Kiviet, J.F.; Phillips, G.D.A., Alternative bias approximations in regressions with a lagged dependent variable, Econometric theory, 9, 62-80, (1993)
[13]	Komunjer, I., Asymmetric power distribution: theory and applications to risk measurement, Journal of applied econometrics, 22, 891-921, (2007)
[14]	Kumar, A., Expectations of product of quadratic forms, Sanhkya (series B), 35, 359-362, (1973)
[15]	Lieberman, O., Saddlepoint approximations for the least squares estimator in first-order autoregression, Biometrika, 81, 807-811, (1994) · Zbl 0825.62670
[16]	Lieberman, O., The effect of nonnormality, Econometric theory, 13, 52-78, (1997)
[17]	Magee, L., Efficiency of iterative estimators in the regression model with AR(1) disturbances, Journal of econometrics, 29, 275-287, (1985) · Zbl 0609.62083
[18]	Magnus, J.R., The moments of products of quadratic forms in normal variables, Statistica neerlandica, 32, 201-210, (1978) · Zbl 0406.62031
[19]	Magnus, J.R., The expectation of products of quadratic forms in normal variables: the practice, Statistica neerlandica, 33, 131-136, (1979) · Zbl 0412.60024
[20]	Magnus, J.R.; Neudecker, H., The commutation matrix: some properties and applications, Annals of statistics, 7, 381-394, (1979) · Zbl 0414.62040
[21]	Mathai, A.M.; Provost, S.B., Quadratic forms in random variables, (1992), Marcel Dekker New York · Zbl 0792.62045
[22]	Mishra, P.N., Recurrence formula for mathematical expectation of products of matrices of structural disturbances, Sanhkya (series B), 34, 379-384, (1972)
[23]	Nagar, A.L., The bias and moment matrix of the general k-class estimators of the parameters in simultaneous equations, Econometrica, 27, 575-595, (1959) · Zbl 0091.15202
[24]	Pesaran, M.H.; Yamagata, T., Testing slope homogeneity in large panels, Journal of econometrics, 142, 50-93, (2008) · Zbl 1418.62530
[25]	Smith, M.D., Expectations of ratios of quadratic forms in normal variables: evaluating some top order invariant polynomials, Australian journal of statistics, 35, 271-282, (1993) · Zbl 0803.62044
[26]	Srivastava, V.K.; Maekawa, K., Efficiency properties of feasible generalized least squares estimators in SURE models under nonnormal disturbances, Journal of econometrics, 66, 99-121, (1995) · Zbl 0814.62035
[27]	Srivastava, V.K.; Tiwari, R., Evaluation of expectations of products of stochastic matrices, Scandinavian journal of statistics, 3, 135-138, (1976) · Zbl 0341.62041
[28]	Stuart, A.; Ord, J.K., Kendall’s advanced theory of statistics, vol. 1, (1987), Oxford University Press New York
[29]	Theil, H.; Nagar, A.L., Testing the independence of regression disturbances, Journal of the American statistical association, 56, 793-806, (1961) · Zbl 0102.35703
[30]	Ullah, A., Finite sample econometrics: a unified approach, (), 242-292 · Zbl 0787.62119
[31]	Ullah, A., Finite sample econometrics, (2004), Oxford University Press New York
[32]	Ullah, A.; Srivastava, V.K.; Chandra, R., Properties of shrinkage estimators when the disturbances are not normal, Journal of econometrics, 21, 389-402, (1983) · Zbl 0508.62064
[33]	White, J.S., Approximate moments for the serial correlation coefficients, Annals of mathematical statistics, 28, 798-803, (1957) · Zbl 0082.13802
[34]	Zivot, E.; Startz, R.; Nelson, C.R., Valid confidence intervals and inference in the presence of weak instruments, International economic review, 39, 1119-1144, (1998)