Aligning estimates from different surveys using empirical likelihood methods
Aligning estimates from different surveys using empirical likelihood methods
It is often the case that several surveys carried out independently in the same population measure some common variables. The population level parameters associated with these common variables are often unknown. Whether the common variable is of interest itself or is treated as an auxiliary information for estimation of other parameters, it may be beneficial to combine information gathered separately in different surveys. Combining information will usually increase precision and ensure that estimates are consistent across surveys. By consistency we mean a requirement that both samples give the same point estimate for the unknown population level parameter associated with the common variable. Typically there are also other side variables measured in the surveys, for which population level parameters, such as totals or means, are known. These variables are used to create benchmark constraints
Kabzinska, Ewa
3d907e04-e7e7-4059-9c3c-9938be5fd4c4
Berger, Yves G.
8fd6af5c-31e6-4130-8b53-90910bf2f43b
March 2015
Kabzinska, Ewa
3d907e04-e7e7-4059-9c3c-9938be5fd4c4
Berger, Yves G.
8fd6af5c-31e6-4130-8b53-90910bf2f43b
Kabzinska, Ewa and Berger, Yves G.
(2015)
Aligning estimates from different surveys using empirical likelihood methods.
New Techniques and Technologies for Statistics (NTTS) 2015, Brussels, Belgium.
10 - 12 Mar 2015.
5 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
It is often the case that several surveys carried out independently in the same population measure some common variables. The population level parameters associated with these common variables are often unknown. Whether the common variable is of interest itself or is treated as an auxiliary information for estimation of other parameters, it may be beneficial to combine information gathered separately in different surveys. Combining information will usually increase precision and ensure that estimates are consistent across surveys. By consistency we mean a requirement that both samples give the same point estimate for the unknown population level parameter associated with the common variable. Typically there are also other side variables measured in the surveys, for which population level parameters, such as totals or means, are known. These variables are used to create benchmark constraints
Text
Kabzinska_Aligning_estimates_from_different_surveys_using_EL_methods.pdf
- Accepted Manuscript
More information
Published date: March 2015
Venue - Dates:
New Techniques and Technologies for Statistics (NTTS) 2015, Brussels, Belgium, 2015-03-10 - 2015-03-12
Organisations:
Statistical Sciences Research Institute
Identifiers
Local EPrints ID: 375510
URI: http://eprints.soton.ac.uk/id/eprint/375510
PURE UUID: 3346108e-b7c8-468c-9b11-cd83bf1d15ac
Catalogue record
Date deposited: 27 Mar 2015 14:15
Last modified: 15 Mar 2024 03:01
Export record
Contributors
Author:
Ewa Kabzinska
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics