A domain outlier robust design and smooth estimation approach

Zhang, Li‐Chun; Hagesæther, Nina

doi:10.1002/cjs.10095

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gwet and Rivest (), Hulliger () and Duchesne () propose estimators related to the M‐estimation approach, replacing non‐robust regression coefficient estimators by robust alternatives (Beaumont and Rivest, ). Zhang and Hagesaether () propose a method related to the surprise stratum method and a smooth outlier‐robust domain estimator that extends the Winsorisation‐based estimator of Rivest and Hidiroglou (). We do not consider these approaches, instead concentrating on MSE‐optimal M‐estimators, as these are the main methods other than the surprise outlier method used by NSIs.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of two Robust Estimation Methods for Business Surveys

Clark

Kokic

Smith

2016

Int Statistical Rev

View full text Add to dashboard Cite

SummaryTwo alternative robust estimation methods often employed by National Statistical Institutes in business surveys are two-sided M-estimation and one-sided Winsorisation, which can be regarded as an approximate implementation of one-sided M-estimation. We review these methods and evaluate their performance in a simulation of a repeated rotating business survey based on data from the Retail Sales Inquiry conducted by the UK Office for National Statistics. One-and two-sided M -estimation are found to have very similar performance, with a slight edge for the former for positive variables. Both methods considerably improve both level and movement estimators. Approaches for setting tuning parameters are evaluated for both methods and this is a more important issue than the difference between the two approaches. M-estimation works best when tuning parameters are estimated using historical data but is serviceable even when only live data is available. Confidence interval coverage is much improved by the use of a bootstrap percentile confidence interval.

show abstract

Section: Introductionmentioning

confidence: 99%