Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Handling Compositional Time Series with Varying Number of Parts

Bergman, Jakob LU orcid (2018) CoDaWork 2017 In Austrian Journal of Statistics 47(5). p.26-33
Abstract
When different polling organisations conduct political party preference polls at different times, different parties might be reported. If the estimated voter shares of these polls are combined into a time series we obtain a compositional time series, but with varying number of parts, thus prohibiting the use of standard compositional time series analysis tools. We discuss the problem and suggest a solution by imputing the unreported parts. The method is applied to a short compositional time series of party preference polls from Sweden.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
compositional loess, compositional time series, imputation, political party preference polls, polls Sweden
in
Austrian Journal of Statistics
volume
47
issue
5
pages
26 - 33
publisher
Austrian Society for Statistics
conference name
CoDaWork 2017
conference location
Abbadia San Salvatore, Siena, Italy
conference dates
2017-06-05 - 2017-06-09
external identifiers
  • scopus:85063482942
ISSN
1026-597X
DOI
10.17713/ajs.v47i5.738
language
English
LU publication?
yes
id
9004462b-e009-4fce-8942-fe059b4bb2ee
date added to LUP
2018-06-25 11:45:57
date last changed
2024-03-13 15:59:49
@article{9004462b-e009-4fce-8942-fe059b4bb2ee,
  abstract     = {{When different polling organisations conduct political party preference polls at different times, different parties might be reported. If the estimated voter shares of these polls are combined into a time series we obtain a compositional time series, but with varying number of parts, thus prohibiting the use of standard compositional time series analysis tools. We discuss the problem and suggest a solution by imputing the unreported parts. The method is applied to a short compositional time series of party preference polls from Sweden.}},
  author       = {{Bergman, Jakob}},
  issn         = {{1026-597X}},
  keywords     = {{compositional loess; compositional time series; imputation; political party preference polls; polls Sweden}},
  language     = {{eng}},
  month        = {{09}},
  number       = {{5}},
  pages        = {{26--33}},
  publisher    = {{Austrian Society for Statistics}},
  series       = {{Austrian Journal of Statistics}},
  title        = {{Handling Compositional Time Series with Varying Number of Parts}},
  url          = {{https://lup.lub.lu.se/search/files/51836842/738_Article_Text_2928_1_10_20180826.pdf}},
  doi          = {{10.17713/ajs.v47i5.738}},
  volume       = {{47}},
  year         = {{2018}},
}