The problems created by multicollinearity when estimating a single equation least squares model are well-known. This problem is particularly troublesome in ecological research because of the heavy reliance of this field on census data and other secondary data sources. This paper explores one solution to the problem of multicollinearity in ecological research—ridge regression. Using census-tract data from Cleveland, Ohio for the years 1960–1970, an ecological model, known as the tipping-point model, of neighborhood change, was evaluated. It was determined that multicollinearity was a problem. To minimize the detrimental effects of multicollinearity and to facilitate structural interpretation, the model was reestimated with the ridge regression technique. The result was a total mean square error that was significantly smaller than the total variance resulting from an ordinary least squares solution. Hence, the estimates of the coefficients produced by the ridge regression were closer, on the average, to the true population parameters than the ordinary least squares estimates.
Results of the ordinary least squares and ridge regression are presented and discussed and the utility of ridge regression in ecological research is evaluated.
Get full access to this article
View all access options for this article.
References
1.
AlthauserR P, 1971, “Multicollinearity and nonadditive regression models” in Causal Models in the Social Sciences Ed. BlalockH M (Aldine, Chicago, IL) pp 453–472.
2.
BlalockH M, 1963, “Correlated independent variables: The problem of multicollinearity”Social Forces42233–237.
3.
BlalockH M, 1964Causal Inferences in Nonexperimental Research (University of North Carolina Press, Chapel Hill, NC).
4.
BurgessE W, 1925, “The growth of the city: An introduction to a research project” in The City Eds ParkR EBurgessE WMcKenzieR D (University of Chicago Press, Chicago, IL) pp 47–62.
5.
ChevanA, 1971, “Family growth, household density, and moving”Demography8451–458.
6.
ChristC F, 1966Econometric Models and Methods (John Wiley, New York).
7.
ChurchillG A, 1975, “A regression estimation method for collinear predictors”Decision Sciences6670–687.
8.
Civil Rights Act, 1964Public Law 88–352, 78Statutes at Large, 241.
9.
ConniffeDStoneJ, 1973, “A critical view of ridge regression”The Statistician22(2) 181–187.
10.
DeeganJ, 1975, “The process of political development: An illustrative use of a strategy for regression in the presence of multicollinearity”Sociological Methods and Research3384–415.
11.
DraperN RSmithH, 1966Applied Regression Analysis (John Wiley, New York).
12.
DuncanO DDuncanB, 1957The Negro Population of Chicago (University of Chicago Press, Chicago, IL).
13.
FarebrotherR W, 1975, “The minimum mean square error linear estimator and ridge regression”Technometrics17127–128.
14.
FarrarD EGlauberR R, 1967, “Multicollinearity in regression analysis: The problem revisited”Review of Economics and Statistics4992–107.
15.
FeigD G, 1978, “Ridge regression: When biased estimation is better”Social Science Quarterly58708–16.
16.
FennesseyJd'AmicoR, 1980, “Collinearity, ridge regression and investigatory judgement”Sociological Methods and Research8309–340.
17.
GordonR A, 1968“Issues in multiple regression”American Journal of Sociology73592–616.
KasardaJ DBidwellC E, 1977, “The organization as an ecosystem”paper presented to the annual meeting of the American Sociological Society, Chicago, IL; obtainable from Dr Kasarda, Department of Sociology, University of North Carolina, Chapel Hill, NC 27514, USA.
24.
KasardaJ DWen-FuShih P, 1977, “Optimal bias in ridge regression approaches to multicollinearity”Sociological Methods and Research5461–469.
25.
McKenzieR D, 1925, “The scope of human ecology” in The City Eds ParkR EBurgessE WMcKenzieR D (University of Chicago Press, Chicago, IL) pp 163–191.
26.
MaddalaG S, 1977Econometrics (McGraw-Hill, New York).
27.
MarquardtD W, 1970, “Generalized inverses, ridge regression, biased linear estimation, and nonlinear estimation”Technometrics12591–612.
28.
MasonRBrownW G, 1975, “Multicollinearity problems and ridge regression in sociological models”Social Science Research4135–149.
29.
MillerM KSmithK R, 1980, “Biased estimation in policy research: An illustrative example of ridge regression in a health system model”Rural Sociology45(3) 483–500.
30.
PinchS P, 1977, “Patterns of local authority housing allocation in Greater London between 1966 and 1973: An inter-borough analysis”Transactions: Institute of British Geographers New Series2(3)35–54.
31.
RaoC R, 1965Linear Statistical Inference and its Application (John Wiley, New York).
32.
RockwellR G, 1975, “Assessment of multicollinearity: The Haitovsky test of the determinant”Sociological Methods and Research3308–320.
33.
RossiP, 1955Why Families Move: A Study in the Social Psychology of Urban Residential Mobility (The Free Press, Glencoe, IL).
34.
SchwabW AMarshE, 1980, “The tipping-point model: Prediction of change in the racial composition of Cleveland, Ohio, neighborhoods, 1940–1970”Environment and Planning A12385–398.
35.
SmithK WSasakiM S, 1979, “Decreasing multicollinearity: A method for models with multiplicative functions”Sociological Methods and Research835–36.
36.
SpeareAJr, 1970, “Home ownership, life-cycle stage, and residential mobility”Demography7449–458.
37.
SteinH D (Ed.), 1969The Crisis in Welfare in Cleveland: Report of the Mayor's Commission (Case Western Reserve University Press, Cleveland, OH).
38.
SteinnesD N, 1977, “Alternative models of neighborhood change”Social Forces551043–1057.
39.
US Bureau of the Census, 1942U.S. Census of Population and Housing, 1940: Statistics for Census Tracts Cleveland, Ohio and Adjacent Area (US Government Printing Office, Washington, DC).
40.
US Bureau of the Census, 1952U.S. Census of Population and Housing, 1950: Census Tract Statistics Cleveland, Ohio and Adjacent Area (US Government Printing Office, Washington, DC).
41.
US Bureau of the Census, 1963U.S. Census of Population and Housing, 1960 Census Tracts: Final Report PHC(1)-28 (US Government Printing Office, Washington, DC).
42.
US Bureau of the Census, 1972U.S. Census of Population and Housing, 1970 Census Tracts: Final Report (US Government Printing Office, Washington, DC).
