Inference From Stratified Samples: Properties of the Linearization, Jackknife and Balanced Repeated Replication Methods

Krewski, Daniel; Rao, J. N. K.

doi:10.1214/aos/1176345580

Cited by 230 publications

(147 citation statements)

References 7 publications

Supporting

Mentioning

146

Contrasting

Order By: Relevance

“…We 160 consider that c * i (ψ) is differentiable with respect to ν for all i ∈ s in a neighbourhood around the true population value ν N . Condition (13) can be found in Krewski & Rao (1981, p.1014 and guarantees that π i andπ are of the same order of magnitude. Condition (14) assumes thatĈ * π (ψ N ) is √ n design-consistent, and can be justified by using the Isaki & Fuller (1982, p.91) sufficient conditions.…”

Section: Asymptotic Propertiesmentioning

confidence: 99%

“…We need to include the constantπ within the definition of c * i (ψ N ) to ensure that (16) holds, butπ can 6 M. OGUZ-ALPER AND Y. G. BERGER be omitted for the computation of the function (11). Condition (17) ensures the existence of moments (e.g., Krewski & Rao, 1981). It can be shown that the following simpler set of sufficient and stronger conditions,…”

Section: Asymptotic Propertiesmentioning

confidence: 99%

See 1 more Smart Citation

Modelling complex survey data with population level information: an empirical likelihood approach

Oguz–Alper

Berger

2016

Biometrika

View full text Add to dashboard Cite

SUMMARY 10Survey data are often collected with unequal probabilities from a stratified population. In many modelling situations, the parameter of interest is a subset of a set of parameters, with the others treated as nuisance parameters. We show that in this situation the empirical likelihood ratio statistic follows a chi-squared distribution asymptotically, under stratified single and multi-stage unequal probability sampling, with negligible sampling fractions. Simulation studies show that 15 the empirical likelihood confidence interval may achieve better coverages and has more balanced tail error rates than standard approaches, which involve variance estimation, linearization or resampling.

show abstract

Section: Asymptotic Propertiesmentioning

confidence: 99%

Section: Asymptotic Propertiesmentioning

confidence: 99%

Modelling complex survey data with population level information: an empirical likelihood approach

Oguz–Alper

Berger

2016

Biometrika

View full text Add to dashboard Cite

show abstract

“…Two key results are that as H fi ¥ , if conditions (ii), (iii), (v), and (vi) hold, then . These results can be proved using Lemmas 3.1 and 3.2, given in Krewski and Rao (1981), which are a central limit theorem and a law of large numbers for independent, nonidentically distributed random variables.…”

Section: Hicmentioning

confidence: 99%

“…A set of half-samples is orthogonally balanced if being the estimated post-stratum total based on half-sample a , both of which are defined explicitly below. Other, asymptotically equivalent choices involving the complement to each half-sample have been studied by Krewski and Rao (1981) and others, but (12) appears to be the most popular choice in practice.…”

Section: R S Tmentioning

confidence: 99%

Poststratification and Conditional Variance Estimation

Valliant¹

1993

Journal of the American Statistical Association

View full text Add to dashboard Cite

Post-stratification estimation is a technique used in sample surveys to improve efficiency of estimators. Survey weights are adjusted to force the estimated numbers of units in each of a set of estimation cells to be equal to known population totals. The resulting weights are then used in forming estimates of means or totals of variables collected in the survey. For example, in a household survey the estimation cells may be based on age/race/sex categories of individuals and the known totals may come from the most recent population census. Although the variance of a post-stratified estimator can be computed over all possible sample configurations, inferences made conditionally on the achieved sample configuration are desirable. Theory and a simulation study using data from the U.S. Current Population Survey are presented to study both the conditional bias and variance of the post-stratified estimator of a total. The linearization, balanced repeated replication, and jackknife variance estimators are also examined to determine whether they appropriately estimate the conditional variance.

show abstract

“…The Horvitz-Thompson estimator is unbiased and has been shown to be consistent and asymptotically Normal under various sets of asymptotics (Krewski and Rao, 1981;Hájek, 1964;Sen, 2009). These asymptotic properties extend to estimators solving weighted estimating equations, at least in simple cases; completely general asymptotic results are not yet available (Binder, 1983;Breslow and Chatterjee, 1999;Lin, 2000;Breslow and Wellner, 2008).…”

mentioning

confidence: 99%

Association of the IGF1 gene with fasting insulin levels

et al. 2016

View full text Add to dashboard Cite

Targeted resequencing of DNA at specific genes or other genomic loci is now feasible for hundreds or thousands of samples, and costs for larger-scale resequencing are decreasing rapidly. For at least the AMS 2000 subject classifications: Primary 62D05, 62P10; secondary 62J12 Keywords and phrases: case-cohort design, case-control design, sampling weights 1 2 T. LUMLEY ET AL.next few years, resequencing will need to be confined to small subsets of the large samples on which genome-wide association studies have been recently been performed. This paper describes some strategies for subsampling an existing cohort for resequencing, and flexibly analysing the resulting data. We illustrate these strategies by describing the actual design and planned analyses for the example that motivated our research, the CHARGE-S resequencing study carried out by the CHARGE (Cohorts in Heart and Aging Research in Genomic Epidemiology) Consortium.

show abstract

Inference From Stratified Samples: Properties of the Linearization, Jackknife and Balanced Repeated Replication Methods

Cited by 230 publications

References 7 publications

Modelling complex survey data with population level information: an empirical likelihood approach

Modelling complex survey data with population level information: an empirical likelihood approach

Poststratification and Conditional Variance Estimation

Association of the IGF1 gene with fasting insulin levels

Contact Info

Product

Resources

About