A Review of Hot Deck Imputation for Survey Non-response

被引:717
作者
Andridge, Rebecca R. [1 ]
Little, Roderick J. A. [2 ]
机构
[1] Ohio State Univ, Div Biostat, Columbus, OH 43210 USA
[2] Univ Michigan, Dept Biostat, Ann Arbor, MI 48109 USA
关键词
Item non-response; missing data; multiple imputation; variance estimation; JACKKNIFE VARIANCE-ESTIMATION; MULTIPLE-IMPUTATION; MISSING-DATA; INFERENCE; COEFFICIENTS; ADJUSTMENTS; BOOTSTRAP; WEIGHTS; VALUES; BIAS;
D O I
10.1111/j.1751-5823.2010.00103.x
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
P>Hot deck imputation is a method for handling missing data in which each missing value is replaced with an observed response from a "similar" unit. Despite being used extensively in practice, the theory is not as well developed as that of other imputation methods. We have found that no consensus exists as to the best way to apply the hot deck and obtain inferences from the completed data set. Here we review different forms of the hot deck and existing research on its statistical properties. We describe applications of the hot deck currently in use, including the U.S. Census Bureau's hot deck for the Current Population Survey (CPS). We also provide an extended example of variations of the hot deck applied to the third National Health and Nutrition Examination Survey (NHANES III). Some potential areas for future research are highlighted.Resume L'imputation hot deck est une methode de gestion des donnees manquantes dans laquelle chaque valeur manquante est remplacee par une reponse observee a partir d'une unite "similaire." Bien qu'elle soit largement utilisee en pratique, sa theorie n'est pas aussi developpee que celle des autres methodes d'imputation. Nous avons constate qu'il n'existe aucun consensus quant a la meilleure faon d'appliquer les hot deck et obtenir des inferences a partir de la serie de donnees complete. Ici, nous passons en revue les differentes formes de hot deck et les recherches existantes sur ses proprietes statistiques. Nous decrivons les applications du hot deck actuellement utilisees, y compris le hot deck du Bureau US du recensement pour la Current Population Survey (CPS). Nous proposons aussi des exemples nombreux de variations du hot deck a la troisieme National Health and Nutrition Examination Survey (NHANES III). Certains domaines possibles de recherches futures sont mises en evidence.
引用
收藏
页码:40 / 64
页数:25
相关论文
共 95 条
[1]  
Andridge RR, 2009, J OFF STAT, V25, P21
[2]  
[Anonymous], 1999, 99054 TNOVGZPG
[3]  
[Anonymous], 2002, NCES STAT STAND
[4]  
[Anonymous], 2000, SURV METHODOL
[5]  
[Anonymous], METRIKA
[6]  
[Anonymous], 2000, J. Official Statistics
[7]  
[Anonymous], 1992, SURV METHODOL
[8]  
[Anonymous], 2007, R LANG ENV STAT COMP
[9]  
Bailar J.C., 1978, AM STAT ASS P SURVEY, P462
[10]   Doubly robust estimation in missing data and causal inference models [J].
Bang, H .
BIOMETRICS, 2005, 61 (04) :962-972