An effective approach to the repeated cross-sectional design

Matthew J. Lebo, Christopher Weber

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Repeated cross-sectional (RCS) designs are distinguishable from true panels and pooled cross-sectional time series (PCSTS) since cross-sectional units (e.g., individual survey respondents) appear but once in the data. This poses two serious challenges. First, as with PCSTS, autocorrelation threatens inferences. However, common solutions like differencing and using a lagged dependent variable are not possible with RCS since lags for i cannot be used. Second, although RCS designs contain information that allows both aggregate- and individual-level analyses, available methods-from pooled ordinary least squares to PCSTS to time series-force researchers to choose one level of analysis. The PCSTS tool kit does not provide an appropriate solution, and we offer one here: double filtering with ARFIMA methods to account for autocorrelation in longer RCS followed by the use of multilevel modeling to estimate both aggregate- and individual-level parameters simultaneously. We use Monte Carlo experiments and three applied examples to explore the advantages of our framework.

Original languageEnglish (US)
Pages (from-to)242-258
Number of pages17
JournalAmerican Journal of Political Science
Volume59
Issue number1
DOIs
StatePublished - Jan 1 2015

Fingerprint

time series
experiment

ASJC Scopus subject areas

  • Sociology and Political Science

Cite this

An effective approach to the repeated cross-sectional design. / Lebo, Matthew J.; Weber, Christopher.

In: American Journal of Political Science, Vol. 59, No. 1, 01.01.2015, p. 242-258.

Research output: Contribution to journalArticle

@article{00520f3873e34a04ba4b7a77e7e49621,
title = "An effective approach to the repeated cross-sectional design",
abstract = "Repeated cross-sectional (RCS) designs are distinguishable from true panels and pooled cross-sectional time series (PCSTS) since cross-sectional units (e.g., individual survey respondents) appear but once in the data. This poses two serious challenges. First, as with PCSTS, autocorrelation threatens inferences. However, common solutions like differencing and using a lagged dependent variable are not possible with RCS since lags for i cannot be used. Second, although RCS designs contain information that allows both aggregate- and individual-level analyses, available methods-from pooled ordinary least squares to PCSTS to time series-force researchers to choose one level of analysis. The PCSTS tool kit does not provide an appropriate solution, and we offer one here: double filtering with ARFIMA methods to account for autocorrelation in longer RCS followed by the use of multilevel modeling to estimate both aggregate- and individual-level parameters simultaneously. We use Monte Carlo experiments and three applied examples to explore the advantages of our framework.",
author = "Lebo, {Matthew J.} and Christopher Weber",
year = "2015",
month = "1",
day = "1",
doi = "10.1111/ajps.12095",
language = "English (US)",
volume = "59",
pages = "242--258",
journal = "American Journal of Political Science",
issn = "0092-5853",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - An effective approach to the repeated cross-sectional design

AU - Lebo, Matthew J.

AU - Weber, Christopher

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Repeated cross-sectional (RCS) designs are distinguishable from true panels and pooled cross-sectional time series (PCSTS) since cross-sectional units (e.g., individual survey respondents) appear but once in the data. This poses two serious challenges. First, as with PCSTS, autocorrelation threatens inferences. However, common solutions like differencing and using a lagged dependent variable are not possible with RCS since lags for i cannot be used. Second, although RCS designs contain information that allows both aggregate- and individual-level analyses, available methods-from pooled ordinary least squares to PCSTS to time series-force researchers to choose one level of analysis. The PCSTS tool kit does not provide an appropriate solution, and we offer one here: double filtering with ARFIMA methods to account for autocorrelation in longer RCS followed by the use of multilevel modeling to estimate both aggregate- and individual-level parameters simultaneously. We use Monte Carlo experiments and three applied examples to explore the advantages of our framework.

AB - Repeated cross-sectional (RCS) designs are distinguishable from true panels and pooled cross-sectional time series (PCSTS) since cross-sectional units (e.g., individual survey respondents) appear but once in the data. This poses two serious challenges. First, as with PCSTS, autocorrelation threatens inferences. However, common solutions like differencing and using a lagged dependent variable are not possible with RCS since lags for i cannot be used. Second, although RCS designs contain information that allows both aggregate- and individual-level analyses, available methods-from pooled ordinary least squares to PCSTS to time series-force researchers to choose one level of analysis. The PCSTS tool kit does not provide an appropriate solution, and we offer one here: double filtering with ARFIMA methods to account for autocorrelation in longer RCS followed by the use of multilevel modeling to estimate both aggregate- and individual-level parameters simultaneously. We use Monte Carlo experiments and three applied examples to explore the advantages of our framework.

UR - http://www.scopus.com/inward/record.url?scp=84921028772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921028772&partnerID=8YFLogxK

U2 - 10.1111/ajps.12095

DO - 10.1111/ajps.12095

M3 - Article

AN - SCOPUS:84921028772

VL - 59

SP - 242

EP - 258

JO - American Journal of Political Science

JF - American Journal of Political Science

SN - 0092-5853

IS - 1

ER -