Variance estimation for annual point estimates and net changes for LFS using R package vardpoor

Research output: Contribution to journalArticlepeer-review


The paper is devoted to the function vardannual from R package vardpoor. The Central Statistical Bureau of Latvia in 2017 has developed the function vardannual which is included in the R package vardpoor. In the paper describes the variance estimation of quartely estimates, correlation estimation of two quarter change estimates, and finally it explains how to extend the approach to deal with variance estimation for annual point estimates and net changes for Labour Force Survey (LFS) indicators. Variance estimates for annual point estimates and net changes was estimated for LFS indicators using the function “vardannual”. This function was tested on simulated and real data. The function “vardannual” is important to assess quality of LFS estimates and statistical significance of the estimates. The annual net changes of all indicators are calculated with the confidence interval, and if the confidence interval for the difference is not equal to 0, then we are able to conclude that the difference is statistically significant. When looking at the results with calibration, it can be identified that the confidence interval is narrower than the results without calibration. The function “vardannual” in software R package “vardpoor” was implemented in practice, LFS in Latvia.
Original languageEnglish
Pages (from-to)74-84
Number of pages11
JournalRevista Romana De Statistica
Issue number4
Publication statusPublished - 20 Dec 2018
Externally publishedYes


  • Survey sampling
  • Annual point estimates
  • Net changes
  • Ratio
  • Variance estimation

Field of Science*

  • 1.2 Computer and information sciences
  • 3.5 Other medical sciences

Publication Type*

  • 1.1. Scientific article indexed in Web of Science and/or Scopus database


Dive into the research topics of 'Variance estimation for annual point estimates and net changes for LFS using R package vardpoor'. Together they form a unique fingerprint.

Cite this