Abstract
A class of generalized multiplicity-adjusted Horvitz–Thompson (GMHT) estimators was introduced by Singh and Mecatti (J. Official Stat. 27(4):633–650, 2011, JOS) to provide a unified and systematic approach to existing estimators via GMHT-Regression. The main purpose of this chapter is to present key observations that led to the development of the unified principled framework. These are based on the use of zero functions as predictors in regression which play a fundamental role in statistical estimation such as quasi-likelihood. The key observations are listed below. First, an optimal combination of two estimators of the same domain is equivalent to regression of the simple multiplicity-adjusted HT (i.e., average of the two estimators) on the zero function defined by the difference of two estimators. Second, there are two types of zero functions for each overlapping domain—one based on domain count estimates and the other based on domain total estimates. Some estimators use both types of zero functions as predictors in regression while others optimally combine first the two domain count estimates and then apply Hájek-type ratio adjustments for each sample to optimally estimated domain counts before regressing on domain total zero functions. Third, the regression need not be optimal as it can be based on a working covariance structure to obtain robust consistent estimates; this is in view of the observation that optimal regression estimators are typically unstable (i.e., with high coefficient of variation) for complex designs due to lack of adequate degrees of freedom for estimating regression parameters. Fourth, for any regression estimator, it may be better to use count zero functions via Hájek-adjustment first because the initial GMHT estimator may not be well correlated with count zero functions. Fifth, it might be preferable to use a suitable working covariance matrix than the optimal one in order to obtain a calibration form in addition to making the estimator more stable. Finally, sixth, the basic principles used in the unified framework make it possible to construct new improved estimators over other estimators in the literature. GMHT-Regression estimators are constructed as sums of contributions from each frame which allow for application of standard variance estimation techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Binder, D.A.: On the variances of asymptotically normal distributed estimators from complex surveys. Int. Stat. Rev. 51, 279–292 (1983)
Deville, J.-C., Särndal, C.-E.: Calibration estimators in survey sampling. J. Am. Stat. Assoc. 87, 376–382 (1992)
Folsom, R.E. Jr., Singh, A.C.: A generalized exponential model for sampling weight calibration for a unified approach to nonresponse, poststratification, and extreme weight adjustments. In: Proceedings of the American Statistical Association, Survey Research Methods Section, pp. 598–603 (2000)
Fuller, W.A.: Regression analysis for sample surveys. Sankhya Ser. C 37, 117–132 (1975)
Fuller, W.A., Rao, J.N.K.: A regression composite estimator with application to the Canadian labour force. Surv. Methodol. 27, 45–51 (2001)
Godambe, V.P., Thompson, M.E.: Parameters of super-population and survey population: their relationships and estimation. Int. Stat. Rev. 54(2), 127–138 (1986)
Godambe, V.P., Thompson, M.E.: An extension of quasi-likelihood estimation (with discussion). J. Stat. Plan. Res. 12, 137–172 (1989)
Godambe, V.P., Thompson, M.E.: Estimating functions and survey sampling. In: Pfeffermann, D., Rao, C.R. (eds.) Handbook of Statistics: Sample Surveys: Inference and Analysis, vol. 29B, pp. 83–101. Elsevier, North-Holland (2009)
Kott, P.A.: Using calibration weighting to adjust for nonresponse and coverage errors. Surv. Methodol. 33, 133–144 (2006)
McCullagh, P., Nelder, J.A.: Generalized Linear Models, 2nd edn. Chapman and Hall, London (1989)
Rao, J.N.K.: Estimating totals and distribution functions using auxiliary information at the estimation stage. J. Official Stat. 10, 153–165 (1994)
Särndal, C.-E.: On π-inverse weighting versus best linear unbiased weighting in probability sampling. Biometrika 67, 639–650 (1980)
Särndal, C.-E.: The calibration approach in survey theory and practice. Surv. Methodol. 33, 99–119 (2007)
Singh, A.C.: Categorical data analysis for simple and complex surveys. In: Pfeffermann, D., Rao, C.R. (eds.) Handbook of Statistics: Sample Surveys: Inference and Analysis, vol. 29B, pp. 329–370. Elsevier, North-Holland (2009)
Singh, A.C.: Combining information in survey sampling by modified regression. In: Proceedings of the Survey Research Methods Section, American Statistical Association, pp. 120–129 (1996)
Singh, A.C., Folsom, R.E. Jr.: Bias corrected estimating functions approach for variance estimation adjusted for poststratification. In: Proceedings of the American Statistical Association, Section on Survey Research Methods, pp. 610–615 (2000)
Singh, A.C., Mecatti, F.: Generalized multiplicity-adjusted Horvitz–Thompson-type estimation as a unified approach to multiple frame surveys. J. Official Stat. 27(4), 633–650 (2011)
Singh, A.C., Mecatti, F.: Generalized multiplicity-adjusted multiple frame estimation via regression. In: Proceedings of the Statistics Canada Symposium on Producing Reliable Estimates from Imperfect Frames, Ottawa (2013)
Singh, A.C., Rao, R.P.: Optimal instrumental variable estimation for linear models with stochastic regressors using estimating functions. In: Basawa, I.V., Godambe, V.P., Taylor, R.L. (eds.) Selected Proceedings of the Symposium on Estimating Functions. IMS Lecture Notes-Monograph Series, vol. 32, pp. 177–192. Institute of Mathematical Statistics, California, Hayward (1997)
Singh, A.C., Wu, S.: Estimation for multiframe complex surveys by modified regression. In: Proceedings of the Statistical Society of Canada, Section on Survey Methods, pp. 69–77 (1996)
Singh, A.C., Wu, S.: An extension of generalized regression estimator to dual frame survey. In: Proceedings of the American Statistical Association, Section on Survey Research Methods, pp. 3911–3918 (2003)
Singh, A.C., Kennedy, B., Wu, S.: Composite estimation for the Canadian labour force survey with a rotating panel design. Surv. Methodol. 27, 33–44 (2001)
Singh, A.C., Ganesh, N., Lin, Y.: Improved sampling weight calibration by generalized raking with optimal unbiased modification. In: Proceedings of the American Statistical Association, Survey Research Methods Section, pp. 3572–3583 (2013)
Skinner, C.J.: Domain means, regression, and multivariate analysis. In: Skinner, C.J., Holt, D., Smith, T.M.F. (eds.) Analysis of Complex Surveys, pp. 59–88. Wiley, New York (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Singh, A.C., Mecatti, F. (2014). Use of Zero Functions for Combining Information from Multiple Frames. In: Mecatti, F., Conti, P., Ranalli, M. (eds) Contributions to Sampling Statistics. Contributions to Statistics. Springer, Cham. https://doi.org/10.1007/978-3-319-05320-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-05320-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-05319-6
Online ISBN: 978-3-319-05320-2
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)