Weighting and Prediction in Sample Surveys

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. 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.

Accelerometry-Assessed Latent Class Patterns of Physical Activity and Sedentary Behavior With Mortality

“…16 A linear test for trend was calculated by representing the latent class assignments as an ordinal score and obtaining a p -value for that variable. Although the authors had information on the measurement day of the week, the order of these days was not known (e.g., one participant might start the 7-day window on Friday, so that Thursday and Friday data were collected 1 week apart).…”

Abundance estimation with sightability data: aBayesian data augmentation approach

“…Assuming the credible intervals have good frequentist coverage rates (i.e. 95% intervals include the true abundance 95% of the time), these results illustrate the potential advantage of parametric, model‐based inferences from survey data (Little ).…”

On Information Quality

“…In other words, h ( X ) is chosen to maximize U [ f { h ( X | g )}]=MSE. Yet, there is disagreement between survey statisticians regarding the usefulness of reweighting data, because ‘weighted estimators can do very badly, particularly in small samples’ (Little, ). When the analysis goal is estimating a population parameter, and f is equivalent to estimation, adjusting for estimator bias is common.…”