[Statlist] SEMINAR ON SURVEY DATA, March 10, 2023, Université de Neuchâtel

TILLE Yves Yve@@T|||e @end|ng |rom un|ne@ch
Mon Jan 16 22:44:21 CET 2023


SEMINAR ON SURVEY DATA, March 10, 2023, 10h-12h.

Université de Neuchâtel, Auditoire Louis-Guillaume, ALG, F200, Emile-Argand, 2000 Neuchâtel, 10h-12h
___________________________________________________________________

Poverty mapping under area-level random regression coefficient Poisson models
María José Lombardía, Universidade da Coruña

Robust Estimation for Survey Data with the R-package robsurvey
Beat Hulliger, FHNW School of Business

Design-based consistency of the Horvitz-Thompson estimators in spatial sampling
Lorenzo Fattorini, University of Siena
__________________________________________________________________

ABSTRACTS

Poverty mapping under area-level random regression coefficient Poisson models
María José Lombardía
Joint work with Naomi Diz-Rosales1, María José Lombardía1, Domingo Morales2
1Universidade da Coruña, CITIC, Spain.
2Universidad Miguel Hernández de Elche, IUCIO, Spain.

Under an area-level random regression coefficient Poisson model, this work derives small area predictors of counts and proportions and introduces bootstrap estimators of the mean squared errors. The maximum likelihood estimators of the model parameters and the model predictors of the random effects are calculated by a Laplace approximation algorithm. Simulation experiments are implemented to investigate the behavior of the fitting algorithm, the predictors and the mean squared error estimators with and without bias correction. The new statistical methodology is applied to data from the Spanish living conditions survey. The target is the estimation of proportions of women and men under the poverty line by province.
________________________________

Robust Estimation for Survey Data with the R-package robsurvey
Beat Hulliger and Tobias Schoch
FHNW School of Business, Olten, Switzerland

Robust methods are needed to cope with outliers in quantitative variables. The classical robust methods for infinite populations like trimming, winsorisation and M-estimators for the location of univariate variables are adapted to account for complex sample designs (robust Horvitz-Thompson and Hajek estimators). Robust ratio and regression estimators including robust GREG estimators are also implemented in package robsurvey. Barebone functions in robsurvey give the estimates alone while variance estimators are provided using the survey package. The application of the estimators is demonstrated on realistic data sets. 
________________________________

Design-based consistency of the Horvitz-Thompson estimators in spatial sampling
Lorenzo Fattorini
Department of Economics and Statistics, University of Siena (Italy) 

Spatial populations are usually located on a continuous support. They can be surfaces representing the values of the survey variable at any location, finite collections of units with the corresponding values of the survey variable, or finite collections of areal units partitioning the support, where the survey variable is the total amount of an attribute within. We derive conditions on the design sequence ensuring consistency of the Horvitz-Thompson estimator of spatial population totals, supposing minimal requirements on the survey variable. Consistency and its implications in real surveys are discussed with focus on environmental surveys.



More information about the Statlist mailing list