Compositional data analysis and zeros in micro data

Jane M. Fry, Tim R.L. Fry, Keith R. Mclaren

Research output: Contribution to journalArticlepeer-review

Abstract

The application of compositional data analysis methods in economics has some attraction. The methodology relies upon the use of 'log-ratios' in the statistal analysis. Such an approach is not possible when the data to be analysed include observations where the observed budget share is zero. We, therefore, consider and extend the methods of compositional data analysis in the situation where the data to be analysed include observations where the observed budget share is zero. The modified compositional data methods are discussed both in statistical terms and through potential economic interpretations of the method. Further, the modified methodology is applied to the 1988-89 Australian Household Expenditure Survey yielding estimates for a system of Engel curves.

Original languageEnglish
Pages (from-to)953-959
Number of pages7
JournalApplied Economics
Volume32
Issue number8
DOIs
Publication statusPublished - 2000

Fingerprint

Dive into the research topics of 'Compositional data analysis and zeros in micro data'. Together they form a unique fingerprint.

Cite this