Sage Journals: Discover world-class research

Abstract

The important assumption of independent errors should be evaluated routinely in the application of interrupted time-series regression models. The two most frequently recommended tests of this assumption [Mood's runs test and the Durbin-Watson (D-W) bounds test] have several weaknesses. The former has poor small sample Type I error performance and the latter has the bothersome property that results are often declared to be “inconclusive.” The test proposed in this article is simple to compute (special software is not required), there is no inconclusive region, an exact p-value is provided, and it has good Type I error and power properties relative to competing procedures. It is shown that these desirable properties hold when design matrices of a specified form are used to model the response variable. A Monte Carlo evaluation of the method, including comparisons with other tests (viz., runs, D-W bounds, and D-W beta), and examples of application are provided.

Get full access to this article

View all access options for this article.

References

Bradley

J. V.

(1978) Robustness? British Journal of Mathematical and Statistical Psychology, 31, 144–152.

Chatterjee

Hadi

A. S.

Price

(2000) Regression analysis by example. (3rd ed.) New York: Wiley.

Draper

N. R.

Smith

(1998) Applied regression analysis. (3rd ed.) New York: Wiley.

Durbin

Watson

G. S.

(1950) Testing for serial correlation in least squares regression: I. Biometrika, 37, 409–428.

Durbin

Watson

G. S.

(1951) Testing for serial correlation in least squares regression: II. Biometrika, 38, 159–178.

Dyer

Schwartz

I. S.

Luce

S. C.

(1984) A supervision program for increasing functional activities for severely handicapped students in a residential setting. Journal of Applied Behavior Analysis, 17, 249–259.

Freund

R. J.

Wilson

W. J.

(1998) Regression analysis: Statistical modeling of a response variable. San Diego. CA: Academic Press.

Hazlett

R. L.

Haynes

S. N.

(1992) Fibromyalgia: A time-series analysis of the stressor-physical symptom association. Journal of Behavioral Medicine, 15, 541–558.

Huitema

B. E.

McKean

J. W.

(1991) Autocorrelation estimation and inference with small samples. Psychological Bulletin, 110, 291–304.

10.

Huitema

B. E.

McKean

J. W.

(1998) Irrelevant autocorrelation in least-squares intervention models. Psychological Methods, 3, 104–116.

11.

Huitema

B. E.

McKean

J. W.

(2000) Design specification issues in time-series intervention models. Educational and Psychological Measurement, 60, 38–58.

12.

Huitema

B. E.

McKean

J. W.

Zhao

(1996) The runs test for autocorrelated errors: Unacceptable properties. Journal of Educational and Behavioral Statistics, 21, 390–404.

13.

Johnston

(1984) Econometric methods. New York: McGraw-Hill.

14.

Kahaner

Moler

Nash

(1989) Numerical methods and software. Englewood Cliffs, NJ: Prentice-Hall.

15.

Marcantonio

Cook

T. D.

(1994) Convincing quasi-experiments: The interrupted time series and regression-discontinuity designs. In Wholey

J. S.

Hatry

H. P.

Newcomer

K. E.

(Eds.), Handbook of practical program evaluation. San Francisco, CA: Jossey-Bass. Pp. 133–154.

16.

Marsaglia

Bray

T. A.

(1964) A convenient method for generating normal variables. SIAM Review, 6, 260–264.

17.

McKean

J. W.

Huitema

B. E.

(1999) PBETA.MAC. [Computer software] Kalamazoo, MI: Department of Mathematics and Statistics, Western Michigan Univer.

18.

McKnight

S. D.

McKean

J. W.

Huitema

B. E.

(2000) A double bootstrap method to analyze linear models with autoregressive error terms. Psychological Methods, 5, 87–101.

19.

Minitab, Inc. (1999) Minitab 12.0. [Computer software] State College, PA: Author.

20.

Mood

A. M.

(1940) The distribution theory of runs. Annals of Mathematical Statistics, 11, 367–392.

21.

Moran

P. A. P.

(1948) Some theorems on time series: II. The significance of the serial correlation coefficients. Biometrika, 35, 255–260.

22.

Neter

Kutner

M. H.

Nachtsheim

C. J.

Wasserman

(1996) Applied linear regression models. Chicago, IL: Irwin.

23.

Ramsey

F. L.

Schafer

D. W.

(1997) The statistical sleuth: A course in methods of data analysis. Belmont, CA: Duxbury.

24.

Savin

N. E.

White

K. J.

(1977) The Durbin-Watson test for serial correlation with extreme sample sizes or many regressors. Econometrica, 45, 1989–1996.

25.

SPSS, Inc. (1999) SPSS 9.0. [Computer software] Chicago, IL: Author.

26.

White

(1999) SHAZAM (Version 8). [Computer software] Vancouver, BC: Department of Economics, Univer. of British Columbia.

A Simple and Powerful Test for Autocorrelated Errors in OLS Intervention Models

Abstract

Get full access to this article

References