首页 | 本学科首页   官方微博 | 高级检索  
     


To be or not to be valid in testing the significance of the slope in simple quantitative linear models with autocorrelated errors
Abstract:

In this article, the validity of procedures for testing the significance of the slope in quantitative linear models with one explanatory variable and first-order autoregressive [AR(1)] errors is analyzed in a Monte Carlo study conducted in the time domain. Two cases are considered for the regressor: fixed and trended versus random and AR(1). In addition to the classical t -test using the Ordinary Least Squares (OLS) estimator of the slope and its standard error, we consider seven t -tests with n-2,hbox{df} built on the Generalized Least Squares (GLS) estimator or an estimated GLS estimator, three variants of the classical t -test with different variances of the OLS estimator, two asymptotic tests built on the Maximum Likelihood (ML) estimator, the F -test for fixed effects based on the Restricted Maximum Likelihood (REML) estimator in the mixed-model approach, two t -tests with n - 2 df based on first differences (FD) and first-difference ratios (FDR), and four modified t -tests using various corrections of the number of degrees of freedom. The FDR t -test, the REML F -test and the modified t -test using Dutilleul's effective sample size are the most valid among the testing procedures that do not assume the complete knowledge of the covariance matrix of the errors. However, modified t -tests are not applicable and the FDR t -test suffers from a lack of power when the regressor is fixed and trended ( i.e. , FDR is the same as FD in this case when observations are equally spaced), whereas the REML algorithm fails to converge at small sample sizes. The classical t -test is valid when the regressor is fixed and trended and autocorrelation among errors is predominantly negative, and when the regressor is random and AR(1), like the errors, and autocorrelation is moderately negative or positive. We discuss the results graphically, in terms of the circularity condition defined in repeated measures ANOVA and of the effective sample size used in correlation analysis with autocorrelated sample data. An example with environmental data is presented.
Keywords:Ar(1) Errors  First Differences  Fixed And Trended versus Random And Ar(1) Regressor  Least Squares  Maximum Likelihood  Modified t -test  Restricted Maximum Likelihood
相似文献(共20条):
[1]、Efficiency analysis of ten estimation procedures for quantitative linear models with autocorrelated errors[J].Journal of Statistical Computation and Simulation
[2]、Michael McAleer,M. Hashem Pesaran,Anil K. Bera.Alternative approaches to testing non-nested models with autocorrelated disturbances[J].统计学通讯:理论与方法,2013,42(10):3619-3644.
[3]、F. C. Palm,J. M. Sneek.Significance tests and spurious correlation in regression models with autocorrelated errors[J].Statistical Papers,1983,25(1):87-105.
[4]、Toni Stocker.On the asymptotic bias of OLS in dynamic regression models with autocorrelated errors[J].Statistical Papers,2007,48(1):81-93.
[5]、Jiewu Huang,Hu Yang.On a principal component two-parameter estimator in linear model with autocorrelated errors[J].Statistical Papers,2015,56(1):217-230.
[6]、C. Tilke.The relative efficiency of OLS in the linear regression model with spatially autocorrelated errors[J].Statistical Papers,1993,34(1):263-270.
[7]、Penalized weighted composite quantile regression in the linear regression model with heavy-tailed autocorrelated errors[J].Journal of the Korean Statistical Society
[8]、Lei Huang,Haitao Tian.The consistency of model selection for dynamic Semi-varying coefficient models with autocorrelated errors[J].统计学通讯:理论与方法,2019,48(3):549-558.
[9]、Marcia Feingold.Missing data in linear models with correlated errors[J].统计学通讯:理论与方法,2013,42(24):2831-2843.
[10]、Cross validation of ridge regression estimator in autocorrelated linear regression models[J].Journal of Statistical Computation and Simulation
[11]、On the simple linear regression model with correlated measurement errors[J].Journal of statistical planning and inference
[12]、Ancop Chaturvedi.Ridge regression estimators in the linear regression models with non-spherical errors[J].统计学通讯:理论与方法,2013,42(8):2275-2284.
[13]、Ridge regression methodology in partial linear models with correlated errors[J].Journal of Statistical Computation and Simulation
[14]、Xinwei Jia,M. Bhaskara Rao.On weak consistency in linear models with equi-correlated random errors[J].Statistics,2013,47(6):463-473.
[15]、Application of shrinkage estimation in linear regression models with autoregressive errors[J].Journal of Statistical Computation and Simulation
[16]、Giuliano Galimberti,Elena Scardovi,Gabriele Soffritti.Using mixtures in seemingly unrelated linear regression models with non-normal errors[J].Statistics and Computing,2016,26(5):1025-1038.
[17]、Wei-Ming Luh ,Jiin-Huarng Guo.Approximate transformation trimmed mean methods to the test of simple linear regression slope equality[J].Journal of applied statistics,2000,27(7):843-857.
[18]、Haibo Zhou,Jinhong You,Bin Zhou.Statistical inference for fixed-effects partially linear regression models with errors in variables[J].Statistical Papers,2010,51(3):629-650.
[19]、Xinghui Wang.The strong consistency of M-estimates in linear models with extended negatively dependent errors[J].统计学通讯:理论与方法,2017,46(10):5093-5108.
[20]、Guillermo, Ferreira,Luis, M., Castro,Ronaldo, Dias.Bayesian modeling of autoregressive partial linear models with scale mixture of normal errors[J].Journal of applied statistics,2013,40(8):1796-1816.
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号