It is not uncommon in socioeconomic analysis to measure variables with error, as in a 10% census. The estimation of linear regression coefficients using such ‘errors-in-variables’ models requires modification of the usual ordinary least squares techniques. The underlying theory both for simple and for multiple regression models is explained, and followed up with a numerical example based on a structure plan model of car ownership.
Get full access to this article
View all access options for this article.
References
1.
BaxterR S, 1976Computer and Statistical Techniques for Planners (Methuen, Andover, Hants)
2.
DoE, 1973, “Using predictive models for structure plans”Department of the Environment (HMSO, London)
3.
FrancisM K, 1970, “The projection of socio-economic groups and their use in estimating future levels of car ownership”Journal of the Town Planning Institute56224–229
4.
JohnstonJ, 1984Econometric Methods (McGraw-Hill, New York)
5.
JohnstonR J, 1978Multivariate Statistical Analysis in Geography (Longman, Harlow, Essex)
6.
JudgeG GGriffithsW EHillR CLeeT C, 1980The Theory and Practice of Econometrics (John Wiley, New York)
7.
KendallMStuartA, 1979The Advanced Theory of StatisticsVolume 2, 4th edition (Charles Griffin, High Wycombe, Bucks)
8.
KoutsoyiannisA, 1977Theory of Econometrics2nd edition (Macmillan, London)
9.
LeeC, 1973Models in Planning (Pergamon Press, Oxford)
10.
OPCS, 1979, “Census 1971: England and Wales, General report. Part 1. Definitions”Office of Population Censuses and Surveys (HMSO, London)
11.
TaylorP J, 1977Quantitative Methods in Geography (Houghton Mifflin, Boston, MA)
12.
WilsonHWomersleyL, 1971, submission by H Wilson and L Womersley (Chartered Architects and Town Planners) and Scott Wilson Kirkpatrick and Partners (Chartered Engineers) for “Teesside Survey and Plan. Final Report to the Steering Committee. Volume 2: Analysis Part 2” (HMSO, London) pp 269–299
