Abstract
A linear model in which random errors are distributed independently and identically according to an arbitrary continuous distribution is assumed. Second- and third-order accurate confidence intervals for regression parameters are constructed from Charlier differential series expansions of approximately pivotal quantities around Student’s t distribution. Simulation verifies that small sample performance of the intervals surpasses that of conventional asymptotic intervals and equals or surpasses that of bootstrap percentile-t and bootstrap percentile-|t| intervals under mild to marked departure from normality.
Similar content being viewed by others
References
Boik R.J. (1998). A local parameterization of orthogonal and semi-orthogonal matrices with applications. Journal of Multivariate Analysis.67, 244–276
Box G.E.P., Cox D.R. (1964). An analysis of transformations. Journal of the Royal Statistical Society, Series B, 26, 211–252
Bowman K.O., Beauchamp J.J., Shenton L.R. (1977). The distribution of the t-statistic under non-normality. International Statistical Review, 45, 233–242
Chung K.L. (1946). The approximate distribution of Student’s statistic. The Annals of Mathematical Statistics. 17, 447–465
Cornish E.A., Fisher R.A. (1937). Moments and cumulants in the specification of distributions. Revue de l’Institut International de Statistique. 5, 307–320
Cressie N.A.C. (1980). Relaxing the assumptions in the one sample t-test. Australian Journal of Statistics. 22, 143–153
Cressie N.A.C., Sheffield L.J., Whitford H.J. (1984). Use of the one-sample t-test in the real world. Journal of Chronic Diseases. 37, 107–114
DiCiccio T.J., Monti A.C. (2002). Accurate confidence limits for scalar functions of vector M-estimands. Biometrika 89, 437–450
Finney D.J. (1963). Some properties of a distribution specified by its cumulants. Technometrics. 5, 63–69
Fisher R.A. (1925). Expansion of “Student’s” integral in powers of n −1. Metron 5, 109–120
Fujioka Y., Maesono Y. (2000). Higher order normalizing transformations of asymptotic U-statistics for removing bias, skewness and kurtosis. Journal of Statistical Planning and Inference 83, 47–74
Gayen A.K. (1949). The distribution of Student’s t in random samples of any size drawn from non-normal universes. Biometrika. 36, 353–369
Geary R.C. (1947). Testing for normality. Biometrika 34, 209–242
Hall P. (1983). Inverting an Edgeworth expansion. The Annals of Statistics 11, 569–576
Hall P. (1987). Edgeworth expansion for Student’s t statistic under minimal moment conditions. The Annals of Probability 15, 920–931
Hall P. (1989). Unusual properties of bootstrap confidence intervals in regression problems. Probability Theory and Related Fields 81, 247–273
Hall P. (1992a). On the removal of skewness by transformation. Journal of the Royal Statistical Society, Series B 54, 221–228
Hall P. (1992b). The Bootstrap and Edgeworth Expansion. Berlin Heidelberg New York: Springer
Hill G.W., Davis A.W. (1968). Generalized expansions of Cornish-Fisher type. The Annals of Mathematical Statistics 39, 1264–1273
Huber P. (1973). Robust regression, asymptotics, conjectures and Monte Carlo. The Annals of Statistics 1, 799–821
Johnson N.J. (1978). Modified t tests and confidence intervals for asymmetrical populations. Journal of the American Statistical Association 73, 536–544
Kong F., Levin B. (1996). Edgeworth expansions for the conditional distributions in logistic regression models. Journal of Statistical Planning and Inference 52, 109–129
Konishi S. (1991). Normalizing transformations and bootstrap confidence intervals. The Annals of Statistics 19, 2209–2225
Navidi W. (1989). Edgeworth expansions for bootstrapping regression models. The Annals of Statistics 4, 1472–1478
Pace L., Salvan A. (1997). Principles of Statistical Inference from a Neo-Fisherian Perspective. World Scientific, Singapore
Pearson E.S., Please N.W. (1975). Relation between the shape of population distribution and the robustness of four simple test statistics. Biometrika 62, 223–241
Peiser A.M. (1949). Correction to “Asymptotic formulas for significance levels of certain distributions”. The Annals of Mathematical Statistics 20, 128–129
Posten H.O. (1979). The robustness of the one-sample t-test over the Pearson system. Journal of Statistical Computation and Simulation 9, 133–149
Qumsiyeh M.B. (1990). Edgeworth expansions in regression models. Journal of Multivariate Analysis 35, 86–101
Qumsiyeh M.B. (1994). Bootstrapping and empirical Edgeworth expansions in multiple linear regression models. Communications in Statistics – Theory and Methods 23, 3227–3239
Ractliffe, J. F. (1968). The effect on the t distribution of non-normality in the sampled population. Applied Statistics, 17, 42–48. Corr. (1968), 17, 203.
Rousseeuw P.J., Leroy A.M. (1987). Robust Regression and Outlier Detection. New York: Wiley
Scheffé H. (1959). The Analysis of Variance. New York: Wiley
Sen P.K., Singer J.M. (1993). Large Sample Methods in Statistics: An Introduction with Applications. London: Chapman & Hall
Staudte R.G., Sheather S.J. (1990). Robust Estimation and Testing. New York: Wiley
Tiku M.L. (1963). Approximation to Student’s t distribution in terms of Hermite and Laguerre polynomials. The Journal of the Indian Mathematical Society. 27, 91–102
Venables W.N., Ripley B.D. (2002). Modern Applied Statistics with S, 4th edition. Berlin Heidelberg New York: Springer
Wallace D.L. (1958). Asymptotic approximations to distributions. The Annals of Mathematical Statistics. 29, 635–654
Wilcox R.R. (1997). Introduction to Robust Estimation and Hypothesis Testing. San Diego: Academic Press
Wilcox R.R. (1998). The goals and strategies of robust methods. British Journal of Mathematical and Statistical Psychology, 51, 1–39
Yanagihara H. (2003). Asymptotic expansion of the null distribution of test statistic for linear hypothesis in nonnormal linear model. Journal of Multivariate Analysis. 84, 222–246
Yanagihara H., Yuan K.H. (2005). Four improved statistics for contrasting means by correcting skewness and kurtosis. British Journal of Mathematical and Statistical Psychology 58, 209–237
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Boik, R.J. Accurate confidence intervals in regression analyses of non-normal data. AISM 60, 61–83 (2008). https://doi.org/10.1007/s10463-006-0085-1
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-006-0085-1