Regression Analysis in Sample Surveys

Konijn, H. S.

doi:10.2307/2282397

Cited by 15 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So which is correct? The answer is not obvious -the role of sampling weights in regression has been extensively debated in the literature-see for example Konijn (1962), Brewer and Mellor (1973), Dumouchel andDuncan (1983), Smith (1988), Little (1991), Pfeifermann (1993 , Korn and Graubard (1999) . In fact, it rests fundamentally on whether one adopts a design-based or model-based perspective on statistical inference.…”

Section: Model-based Inferencementioning

confidence: 99%

Weighting and Prediction in Sample Surveys

Little

2008

Calcutta Statistical Association Bulletin

View full text Add to dashboard Cite

A fundamental technique in survey sampling is to weight included units by the inverse of their probability of inclusion, which may be known (as in the case of sampling weights) or estimated (as in the case of nonresponse weights). The technique is closely associated with the design-based approach to survey inference, with the idea that units in the sample are representing a certain number of units in the population. I discuss weighting from a modeling perspective. Some common misconceptions of weighting will be addressed, including the idea that modelers can ignore the sampling weights, or that weighting necessarily reduces bias at the expense of increased variance, or that units entering the calculation of nonresponse weights should be weighted by their sampling weights. A robust model-based perspective suggests that selection weights cannot be ignored, but there may be better ways of incorporating them in the inference than via the standard Horvitz-Thompson estimator and its variants. February 23, 2009 Weighting and prediction in sample surveys Roderick J. Little Revised Draft University of MichiganHosted by The Berkeley Electronic Press 1 Abstract A fundamental technique in survey sampling is to weight included units by the inverse of their probability of inclusion, which may be known (as in the case of sampling weights) or estimated (as in the case of nonresponse weights). The technique is closely associated with the design-based approach to survey inference, with the idea that units in the sample are representing a certain number of units in the population. I discuss weighting from a modeling perspective. Some common misconceptions of weighting will be addressed, including the idea that modelers can ignore the sampling weights, or that weighting necessarily reduces bias at the expense of increased variance, or that units entering the calculation of nonresponse weights should be weighted by their sampling weights. A robust model-based perspective suggests that selection weights cannot be ignored, but there may be better ways of incorporating them in the inference than via the standard Horvitz-Thompson estimator and its variants.

show abstract

Section: Model-based Inferencementioning

confidence: 99%

Weighting and Prediction in Sample Surveys

Little

2008

Calcutta Statistical Association Bulletin

View full text Add to dashboard Cite

show abstract

“…Part of the growing literature on the subject is based on the traditional sampling framework such as, for example, the works of Konijn (1962) and Kish and Frankel (1974). Others such as Scott and Holt (1982), Deaton and Irish (1983), King and Evans (1986), Christensen (1984Christensen ( , 1986Christensen ( , 1987a, Moulton (1986Moulton ( , 1990), Dorfman (1993), Rao et al (1993), and more recently, Bhatti (1995Bhatti ( , 1996Bhatti ( , 1997Bhatti ( , 1999 have focused on the model-based approach.…”

Section: Ishaq Bhatti Is a Consultant At The Department Of Operatimentioning

confidence: 99%

Environmetric analysis in complex surveys

Bhatti

2001

Complexity

View full text Add to dashboard Cite

“…The properties of ordinary least squares (OLS) estimates, when used to analyze data collected from two-stage sampling, have been considered by Campbell (1979), Fuller (1975), Konijn (1962), and Scott and Holt (1982). In particular, Scott and Holt concluded that OLS estimates of parameters are quite good but that the corresponding estimates of standard errors could be quite bad.…”

Section: Introductionmentioning

confidence: 99%

The Analysis of Two-Stage Sampling Data by Ordinary Least Squares

Christensen

1987

Journal of the American Statistical Association

View full text Add to dashboard Cite

A reasonably broad class of models for analyzing two-stage samples is considered. For models in this class, ordinary least squares (OLS) estimates are best linear unbiased estimates (BLUE's) and a large variety of exact tests and confidence intervals are available. The necessary computations can be made simply by fitting two models in the ordinary fashion using least squares. The most stringent assumption made is that there are equal numbers of observations taken in each cluster. For such a sampling scheme, OLS estimates are BLUE's iff for each variable in the model, the variable obtained by replacing each component with the corresponding cluster average is also, either implicitly or explicitly, contained in the model. A quite general condition on the parameterization (actually the design matrix) of such models is given that, if satisfied, assures the existence of exact inferential procedures for a wide variety of parametric functions. For any model in which OLS estimates are BLUES there exist parameterizations that satisfy the condition in question. Results are also given for the problem of testing a given model against a reduced model.

show abstract

Regression Analysis in Sample Surveys

Cited by 15 publications

References 0 publications

Weighting and Prediction in Sample Surveys

Weighting and Prediction in Sample Surveys

Environmetric analysis in complex surveys

The Analysis of Two-Stage Sampling Data by Ordinary Least Squares

Contact Info

Product

Resources

About