Comparing robust regression lines associated with two dependent groups when there is heteroscedasticity. (English) Zbl 1306.65150

Summary: The paper deals with three approaches to comparing the regression lines corresponding to two dependent groups when using a robust estimator. The focus is on the Theil-Sen estimator with some comments about alternative estimators that might be used. The first approach is to test the global hypothesis that the two groups have equal intercepts and slopes in a manner that allows a heteroscedastic error term. The second approach is to test the hypothesis of equal intercepts, ignoring the slopes, and testing the hypothesis of equal slopes, ignoring the intercepts. The third approach is to test the hypothesis that the regression lines differ at a specified design point. This last goal corresponds to the classic Johnson and Neyman method when dealing with independent groups and when using the ordinary least squares regression estimator. Based on extant studies, there are guesses about how to proceed in a manner that will provide reasonably accurate control over the Type I error probability: Use some type of percentile bootstrap method. (Methods that assume the regression estimator is asymptotically normal were not considered for reasons reviewed in the paper.) But there are no simulation results providing some sense of how well they perform when dealing with a relatively small sample size. Data from the Well Elderly II study are used to illustrate that the choice between the ordinary least squares estimator and the Theil-Sen estimator can make a practical difference.


62-08 Computational methods for problems pertaining to statistics
62J05 Linear regression; mixed models
62F35 Robustness and adaptive procedures (parametric inference)
62F40 Bootstrap, jackknife and other resampling methods


Full Text: DOI


[1] Bradley JV (1978) Robustness? British J Math Stat Psychol 31:144-152
[2] Chida Y, Steptoe A (2009) Cortisol awakening response and psychosocial factors: a systematic review and meta-analysis. Biol Psychol 80:265-278
[3] Clark F, Jackson J, Carlson M, Chou C-P, Cherry BJ, Jordan-Marsh M, Knight BG, Mandel D, Blanchard J, Granger DA, Wilcox RR, Lai MY, White B, Hay J, Lam C, Marterella A, Azen SP (2012) Effectiveness of a lifestyle intervention in promoting the well-being of independently living older people: results of the well Elderly 2 randomise controlled trial. J Epidemiol Community Health 66:782-790. doi:10.1136/jech.2009.099754
[4] Cleveland WS (1979) Robust locally weighted regression and smoothing scatterplots. J Am Stat Assoc 74:829-836 · Zbl 0423.62029
[5] Cleveland WS, Devlin SJ (1988) Locally-weighted Regression: an approach to regression analysis by local fitting. J Am Stat Assoc 83:596-610 · Zbl 1248.62054
[6] Clow A, Thorn L, Evans P, Hucklebridge F (2004) The awakening cortisol response: methodological issues and significance. Stress 7:29-37
[7] Dietz EJ (1987) A comparison of robust estimators in simple linear regression. Commun Stat-Simul Comput 16: 1209-1227 · Zbl 0695.62156
[8] Donoho DL, Gasko M (1992) Breakdown properties of the location estimates based on halfspace depth and projected outlyingness. Ann Stat 20:1803-1827 · Zbl 0776.62031
[9] Eakman AM, Carlson ME, Clark FA (2010) The meaningful activity participation assessment: a measure of engagement in personally valued activities. Int J Aging Human Dev 70:299-317
[10] Hampel FR, Ronchetti EM, Rousseeuw PJ, Stahel WA (1986) Robust statistics. Wiley, New York · Zbl 0593.62027
[11] Hoaglin, DC; Hoaglin, D. (ed.); Mosteller, F. (ed.); Tukey, J. (ed.), Summarizing shape numerically: the g-and-h distribution, 461-515 (1985), New York
[12] Huber PJ, Ronchetti E (2009) Robust statistics, 2nd edn. Wiley, New York · Zbl 1276.62022
[13] Jackson J, Mandel D, Blanchard J, Carlson M, Cherry B, Azen S, Chou C-P, Jordan-Marsh M, Forman T, White B, Granger D, Knight B, Clark F (2009) Confronting challenges in intervention research with ethnically diverse older adults: the USC Well Elderly II trial. Clin Trials 6:90-101
[14] Jöckel K-H (1986) Finite sample properties and asymptotic efficiency of Monte Carlo tests. Ann Stat 14:336-347 · Zbl 0589.62015
[15] Johnson P, Neyman J (1936) Tests of certain linear hypotheses and their application to some educational problems. Stat Res Mem 1:57-93 · JFM 62.0633.08
[16] Koenker R, Bassett G (1978) Regression quantiles. Econometrika 46:33-50 · Zbl 0373.62038
[17] Peng H, Wang S, Wang X (2008) Consistency and asymptotic distribution of the Theil-Sen estimator. J Stat Plan Inference 138:1836-1850 · Zbl 1131.62059
[18] Pratt JW (1968) A normal approximation for binomial, F, beta, and other common, related tail probabilities, I. J Am Stat Assoc 63:1457-1483 · Zbl 0167.47403
[19] Racine J, MacKinnon JG (2007) Simulation-based tests than can use any number of simulations. Commun Stat-Simul Comput 36:357-365 · Zbl 1118.62046
[20] Sen PK (1968) Estimate of the regression coefficient based on Kendall’s tau. J Am Stat Assoc 63:1379-1389 · Zbl 0167.47202
[21] Serlin RC (2000) Testing for robustness in Monte Carlo studies. Psychol Methods 5:230-240
[22] Staudte RG, Sheather SJ (1990) Robust estimation and testing. Wiley, New York · Zbl 0706.62037
[23] Theil H (1950) A rank-invariant method of linear and polynomial regression analysis. Indagationes Mathematicae 12:85-91 · Zbl 0038.29504
[24] Wang XQ (2005) Asymptotics of the Theil-Sen estimator in simple linear regression models with a random covariate. Nonparametric Stat 17:107-120 · Zbl 1055.62083
[25] Wilcox RR (1998) Simulation results on extensions of the Theil-Sen regression estimator. Commun Stat-Simul Comput 27: 1117-1126 · Zbl 0919.62068
[26] Wilcox RR (2012) Introduction to robust estimation and hypothesis testing, 3rd edn. Academic Press, San Diego, CA · Zbl 1270.62051
[27] Wilcox RR, Clark F (2013) Within groups comparisons of least squares regression lines when there is heteroscedasticity. Submitted for publication Dornsife.usc.edu/cf/labs/wilcox/wilcox-faculty-display.cfm · Zbl 0624.62037
[28] Yohai VJ (1987) High breakdown point and high efficiency robust estimates for regression. Ann Stat 15:642-656 · Zbl 0624.62037
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.