Robustness Test of Selected Estimators of Linear Regression with Autocorrelated Error Term: A Monte-Carlo Simulation Study
Asian Journal of Probability and Statistics,
Assumptions in the classical linear regression model include that of lack of autocorrelation of the error terms and the zero covariance between the explanatory variable and the error terms. This study is channeled towards the estimation of the parameters of the linear models for both time series and cross-sectional data when the above two assumptions are violated. The study used the Monte-Carlo simulation method to investigate the performance of six estimators: ordinary least square (OLS), Prais-Winsten (PW), Cochrane-Orcutt (CC), Maximum Likelihood (MLE), Restricted Maximum- Likelihood (RMLE) and the Weighted Least Square (WLS) in estimating the parameters of a single linear model in which the explanatory variable is also correlated with the autoregressive error terms. Using the models’ finite properties(mean square error) to measure the estimators’ performance, the results shows that OLS should be preferred when autocorrelation level is relatively mild (ρ = 0.3) and the PW, CC, RMLE, and MLE estimator will perform better with the presence of any level of AR (1) disturbance between 0.4 to 0.8 level, while WLS shows better performance at 0.9 level of autocorrelation and above. The study thus recommended the application of the various estimators considered to real-life data to affirm the results of this simulation study.
- linear regression model
How to Cite
Epps TW, Epps ML. The robustness of some standard tests for autocorrelation and heteroskedasticity when both problems are present. Econometrica: Journal of the Econometric Society. 1977;745–753.
Evans M. Robustness of size of tests of autocorrelation and heteroscedasticity to nonnormality. Journal of Econometrics. 1992;51(1–2):7–24.
Ayinde Kayode, Olaomi JO. Robustness of Some Estimators of Linear Model with Autocorrelated Error Terms When Stochastic Regressors are Normally Distributed. Journal of Modern Applied Statistical Methods. 2008;7(1):20.
Godfrey LG. Discriminating between autocorrelation and misspecification in regression analysis: An alternative test strategy. The Review of Economics and Statistics. 1987;128–134.
Henshaw Jr RC. Testing single-equation least squares regression models for autocorrelated disturbances. Econometrica: Journal of the Econometric Society. 1966;646–660.
Hidalgo J, Robinson PM. Adapting to unknown disturbance autocorrelation in regression with long memory. Econometrica. 2002;70(4):1545–1581.
Ayinde K, Lukman AF, Rauf RI, Alabi OO, Okon CE, Ayinde OE. Modeling Nigerian Covid-19 cases: A comparative analysis of models and estimators. Chaos, Solitons and Fractals. 2020;138.
Ayinde K, Lukman AF, Arowolo OT. Combined parameters estimation methods of linear regression model with multicollinearity and autocorrelation. Journal of Asian Scientific Research. 2015;5(5):243–250.
Bumb BL, Kelejian HH. Autocorrelated and Heteroskedastic Disturbances in Linear Regression Analysis: A Monte Carlo Study. Sankhyā: The Indian Journal of Statistics, Series B. 1983;257–270.
Calabrese R, Elkink JA. Estimators of binary spatial autoregressive models: A Monte Carlo study. Journal of Regional Science. 2014;54(4):664–687.
DeCarlo LT, Tryon WW. Estimating and testing autocorrelation with small samples: A comparison of the C-statistic to a modified estimator. Behaviour Research and Therapy. 1993;31(8):781–788.
Dubin R. Robustness of spatial autocorrelation specifications: some Monte Carlo evidence. Journal of Regional Science. 2003;43(2):221–248.
Edgerton D, Shukur G. Testing autocorrelation in a system perspective testing autocorrelation. Econometric Reviews. 1999;18(4):343–386.
Gosling BJ, Puterman ML. Ridge estimation in regression problems with autocorrelated errors: A monte carlo study. Communications in Statistics-Simulation and Computation. 1985;14(3):577–613.
Harris P. A simulation study on specifying a regression model for spatial data: Choosing between autocorrelation and heterogeneity effects. Geographical Analysis. 2019;51(2):151–181.
Hildreth CG, Lu JY. A Monte Carlo study of the regression model with autocorrelated disturbances. Rand Corp Santa Monica CA; 1969.
Magee L, Ullah A, Srivastava VK. Efficiency of estimators in the regression model with first-order autoregressive errors. Routledge; 2018.
Park RE, Mitchell BM. Estimating the autocorrelated error model with trended data. Journal of Econometrics. 1980;13(2):185–201.
Racine MD. The simultaneous occurrence of heteroscedasticity and autocorrelation: a Monte Carlo study. Theses (Dept. of Economics)/Simon Fraser University; 1983.
Zubair MA, Adenomon MO. Comparison of estimators efficiency for linear regressions with joint presence of autocorrelation and multicollinearity. Science World Journal. 2021;16(2):103–109.
West KD. Another heteroskedasticity-and autocorrelation-consistent covariance matrix estimator. Journal of Econometrics. 1997;76(1–2):171–191.
Wilford LL, Taylor D. The power of four tests of autocorrelation in the linear regression model. Journal of Econometrics. 1975;3(1):1–21.
Thornton DL. A note on the efficiency of the Cochrane-Orcutt estimator of the AR (1) regression model. Journal of Econometrics. 1987;36(3):369–376.
Abstract View: 69 times
PDF Download: 28 times