Estimation of panel correlations for the Canadian Labour Force Survey / Hyunshik Lee. : CS11-613/89-23E-PDF

"The Canadian Labour Force Survey uses the rotation panel design. Every month, one sixth of the sample rotates and five sixths remain. Hence, under this rotation scheme, once a rotation panel enters in the sample, it stays 6 months in the sample before it rotates out. Because of this design feature, the estimates based on the same panel in different months are highly correlated. Moreover, when a rotation panel rotates out, a neighbouring rotation panel usually rotates in. Since they are geographically close, estimates based on the neighbouring rotation panels are also correlated. These correlations are called panel correlations: their magnitudes are variable-specific and time-dependent. This paper describes a methodology for estimating the panel correlations and presents estimated correlations for selected variables using 1980-81 and 1985-87 data. The work was originated for the study of composite estimation technique. However, the results are useful in any situation in which the panel correlation plays a role"--Abstract.

Lien permanent pour cette publication :
publications.gc.ca/pub?id=9.837477&sl=1

• Format MARC XML
• Format MARC HTML

Demander des formats alternatifs