Stats NZ has a new website.

For new releases go to

www.stats.govt.nz

As we transition to our new site, you'll still find some Stats NZ information here on this archive site.

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
Analysis of non-respondents to the Household Labour Force Survey – Using linked 2013 Census data

Statistics New Zealand Working Paper No 16–02

Julia Hall and Vinayak Anand-Kumar

Abstract

An increase in survey non-response rates can have implications for the accuracy of the survey outputs. If units that don't respond to a survey are different from the units that do respond, non-response bias is introduced – the survey outcomes of interest are either over- or underestimated.

The Household Labour Force Survey (HLFS) managed non-response bias by grouping units based on a set of characteristics/variables, and within each group weighting up responding households to represent the non-responding households. This is referred to as non-response adjustment. It can reduce the bias of survey outputs if the variables used to group the households are related to the likelihood of response and to the survey outputs.

This work aimed to investigate what effect non-response adjustment has on reducing non-response bias in the HLFS, and to potentially improve the non-response adjustment by identifying significant predictors of response likelihood. Individuals selected for the March 2013 HLFS were linked to their responses from the 2013 Census of Population and Dwellings. The census datasets provided characteristics of both the respondents and non-respondents, which were used in a logistic regression model to predict the likelihood of response.

The results suggest that the calibration employed by the HLFS does a reasonable job of adjusting for non-response (once region is included as a benchmark), and that further non-response adjustments have minimal effect on reducing the bias introduced by non-response.

Key words: Non-response, bias, adjustment, HLFS, Census, linked, logistic regression

To read the paper, download or print the PDF from the 'Available files' box. If you have problems viewing the file, see Opening files and PDFs.

Citation

Hall, J, & Anand-Kumar, V (2016). Analysis of non-respondents to the Household Labour Force Survey (Statistics New Zealand Working Paper No 16–02). Retrieved from www.stats.govt.nz.

ISBN 978-0-908350-31-5 (online)
ISSN 1179-934X (online)

Published 21 April 2016

  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+
Top
  • Share this page to Facebook
  • Share this page to Twitter
  • Share this page to Google+