Spatial prediction in small area estimation
- Small area estimation methods have become a widely used tool to provide accurate estimates for regional indicators such as poverty measures. Recent research has provided evidence that spatial modelling still can improve the precision of regional and local estimates. In this paper, we provide an intrinsic spatial autocorrelation model and prove the propriety of the posterior under a flat prior. Further, we show using the SAIPE poverty data that the gain in efficiency using a spatial model can be essentially important in the presence of a lack of strong auxiliary variables.
Download full text files
Additional Services
| Author: | Martin VogtORCiD, Partha LahiriORCiD, Ralf MünnichORCiD |
|---|---|
| URN: | urn:nbn:de:hbz:tr5-10094 |
| DOI: | https://doi.org/10.59170/stattrans-2023-037 |
| Parent Title (English): | Statistics in Transition new series |
| Publisher: | Statistics Poland |
| Document Type: | Article (specialist journals) |
| Language: | English |
| Date of OPUS upload: | 2024/09/12 |
| Date of first Publication: | 2023/06/13 |
| Publishing University: | Hochschule Trier |
| Release Date: | 2024/09/12 |
| Tag: | CAR; Fay-Herriot; poverty estimation; spatial models |
| GND Keyword: | Armut; Messung; Modellierung |
| Volume: | 24 |
| Issue: | 3 |
| First Page: | 77 |
| Last Page: | 94 |
| Departments: | FB Wirtschaft |
| Dewey Decimal Classification: | 3 Sozialwissenschaften / 33 Wirtschaft |
| Licence (German): |  Creative Commons - CC BY-SA - Namensnennung - Weitergabe unter gleichen Bedingungen 4.0 International |
