2005
DOI: 10.1016/j.spl.2005.04.027
|View full text |Cite
|
Sign up to set email alerts
|

Optimal allocation in balanced sampling

Abstract: SummaryThe development of new sampling methods allows the selection of large balanced samples. In this paper we propose a method for computing optimal inclusion probabilities for balanced samples. Next, we show that the optimal Neyman allocation is a particular case of this method.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
13
0

Year Published

2011
2011
2019
2019

Publication Types

Select...
5
3

Relationship

1
7

Authors

Journals

citations
Cited by 15 publications
(13 citation statements)
references
References 8 publications
0
13
0
Order By: Relevance
“…If these quantities are unknown at the design stage, we propose to use estimates arising from another survey instead. Our simulation results suggest that the proposed method performs well, as compared to the approximation originally proposed by Tillé and Favre (2005).…”
Section: Introductionmentioning
confidence: 69%
See 1 more Smart Citation
“…If these quantities are unknown at the design stage, we propose to use estimates arising from another survey instead. Our simulation results suggest that the proposed method performs well, as compared to the approximation originally proposed by Tillé and Favre (2005).…”
Section: Introductionmentioning
confidence: 69%
“…For example, the Cube method was used for the selection of the PSUs in the 1999 French Master Sample (Bourdalle et al, 2000) with balanced sampling on variables such as taxable net income and age groups. In this paper, we propose to compute optimal inclusion probabilities for balanced sampling designs by means of a fixed-point algorithm, previously suggested by Tillé and Favre (2005). Under some conditions on the set of balancing variables, we show that the resulting inclusion probabilities always lead to a reduction in variance of the Horvitz-Thompson estimator.…”
Section: Introductionmentioning
confidence: 99%
“…Estimates of uncertainty from the parameters, such as the standard errors, in the preliminary models can be used to derive inclusion probabilities for randomized selection of study areas. Specifically, calculating inclusion probabilities that are inversely proportional to uncertainty will place more sampling effort in areas with greater variability and thereby increase precision and sampling efficiency (Tillé and Favre 2005). Such model-based designs, however, are most appropriate for targeted single-species sampling designs because levels of uncertainty in distribution models will vary spatially among species.…”
Section: Enhancing Survey Effortsmentioning
confidence: 99%
“…Amongst others, balanced sampling has been investigated in terms of variance estimation (Deville and Tillé 2005), extending the constraints to sub-populations (Chauvet 2009), allocating the sample size (Tillé and Favre 2005), and optimal selection probabilities when dealing with multivariate auxiliaries (Chauvet et al 2011). Particularly the fast version, which can easily be applied to real life surveys because it can deal with frames that have a very high number of records.…”
Section: Quality Of Balancing Totals Horvitzthompson_estimatorsmentioning
confidence: 99%