Stepwise estimators for three-phase sampling of categorical variables

Steen Magnussen

Journal of Applied Statistics, 2003, vol. 30, issue 5, 461-475

Abstract: Three-phase sampling can be a very effective design for the estimation of regional and national forest cover type frequencies. Simultaneous estimation of frequencies and sampling variances require estimation of a large number of parameters; often so many that consistency and robustness of results becomes an issue. A new stepwise estimation model, in which bias in phase one and two is corrected sequentially instead of simultaneously, requires fewer parameters. Simulated three-phase sampling tested the new model with 144 settings of sample sizes, the number of classes and classification accuracy. Relative mean absolute deviations and root mean square errors were, in most cases, about 8% lower with the stepwise method than with a simultaneous approach. Differences were a function of design parameters. Average expected relative root mean square errors, derived from the assumption of a Dirichlet distribution of cover-type frequencies, tracked the empirical root mean square errors obtained from repeated sampling with - 10%. Resampling results indicate that the relative bias of the most frequent cover types was slightly inflated by the stepwise method. For the least common cover type, the simultaneous method produced the largest relative bias.

Date: 2003
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.tandfonline.com/doi/abs/10.1080/0266476032000053628 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:japsta:v:30:y:2003:i:5:p:461-475

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/0266476032000053628

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().