Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Bayesian modeling for overdispersed event-count time series

Bayesian modeling for overdispersed event-count time series Social scientists are frequently interested in event-count time-series data. One of the state-of-the-art methods, the Poisson exponentially weighted moving average (P-EWMA) model, leads to incorrect inference in the presence of omitted variables even if they are not confounding. To tackle this problem, this paper proposes a nega- tive binomial integrated error [NB-I(1)] model, which can be estimated via Markov Chain Monte Carlo methods. Simulations show that when the data are generated by a P-EWMA model, but an non-confounding covariate is omitted at the stage of esti- mation, the P-EWMA model’s credible interval is optimistically too narrow to con- tain the true value at the nominal level, whereas the NB-I(1) model does not suffer this problem. To explore the models’ performance, we replicate a study on an annual count of militarized interstate disputes. Keywords Non-negative integers · Dynamic models · Markov Chain Monte Carlo · Militarized interstate disputes · Omitted variables Communicated by Takahiro Hoshino. Will H. Moore: deceased. Previous versions of this paper were presented at the Annual Meetings of the Japan Election Studies Association, Tokyo, Japan, May 17–18, 2014 and May 20–21, 2006; the Annual Meetings of the Midwest Political Science Association, Chicago, IL, USA, April 11–14, 2013 and April 20–23, 2006; http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Behaviormetrika Springer Journals

Bayesian modeling for overdispersed event-count time series

Fukumoto, Kentaro; Beger, Andreas; Moore, Will
Behaviormetrika , Volume OnlineFirst – Sep 11, 2019
Download PDF
18 pages

Loading next page...
 
/lp/springer-journals/bayesian-modeling-for-overdispersed-event-count-time-series-Gi0c8oKjDz
Publisher
Springer Journals
Copyright
Copyright © 2019 by The Behaviormetric Society
Subject
Statistics; Statistical Theory and Methods; Statistics for Business, Management, Economics, Finance, Insurance; Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences
ISSN
0385-7417
eISSN
1349-6964
DOI
10.1007/s41237-019-00093-5
Publisher site
See Article on Publisher Site

Abstract

Social scientists are frequently interested in event-count time-series data. One of the state-of-the-art methods, the Poisson exponentially weighted moving average (P-EWMA) model, leads to incorrect inference in the presence of omitted variables even if they are not confounding. To tackle this problem, this paper proposes a nega- tive binomial integrated error [NB-I(1)] model, which can be estimated via Markov Chain Monte Carlo methods. Simulations show that when the data are generated by a P-EWMA model, but an non-confounding covariate is omitted at the stage of esti- mation, the P-EWMA model’s credible interval is optimistically too narrow to con- tain the true value at the nominal level, whereas the NB-I(1) model does not suffer this problem. To explore the models’ performance, we replicate a study on an annual count of militarized interstate disputes. Keywords Non-negative integers · Dynamic models · Markov Chain Monte Carlo · Militarized interstate disputes · Omitted variables Communicated by Takahiro Hoshino. Will H. Moore: deceased. Previous versions of this paper were presented at the Annual Meetings of the Japan Election Studies Association, Tokyo, Japan, May 17–18, 2014 and May 20–21, 2006; the Annual Meetings of the Midwest Political Science Association, Chicago, IL, USA, April 11–14, 2013 and April 20–23, 2006;

Journal

Behaviormetrika – Springer Journals

Published: Sep 11, 2019

References

  • An integer-valued pth-order autoregressive structure (INAR (p)) process
    Alzaid, AA; Al-Osh, M
  • Pivotal politics and initiative use in the American states
    Boehmke, FJ; Osborn, TL; Schilling, EU
  • Bayesian inference for the negative binomial distribution via polynomial expansions
    Bradlow, ET; Hardie, BGS; Fader, PS
  • A bayesian poisson vector autoregression model
    Brandt, PT; Sandler, T
  • A linear poisson autoregressive model: the poisson AR(p) model
    Brandt, PT; Williams, JT
  • Dynamic modeling for persistent event-count time series
    Brandt, PT; Williams, JT; Fordham, BO; Pollins, B
  • Regression analysis of count data
    Cameron, AC; Trivedi, PK
  • Observation-driven models for poisson counts
    Davis, RA; Dunsmuir, WTM; Streett, SB
  • Time series analysis of non-gaussian observations based on state space models from both classical and bayesian perspectives
    Durbin, J; Koopman, SJ
  • Time series analysis: methods and applications
    Fokianos, K
  • Legislative production in comparative perspective: cross sectional study of 42 countries and time-series analysis of the Japan case
    Fukumoto, K
  • Some properties and generalizations of non-negative bayesian time series models
    Grunwald, GK; Hamza, K; Hyndman, R
  • Time series models for count or qualitative observations
    Harvey, AC; Fernandes, C
  • Divided government and the legislative productivity of congress, 1945–94
    Howell, W; Adler, S; Cameron, C; Riemann, C
  • Power without persuasion: the politics of direct presidential action
    Howell, WG
  • Time series of count data: modeling, estimation and diagnostics
    Jung, RC; Kukuk, M; Liesenfeld, R
  • Statistical models for political science event counts: bias in conventional procedures and evidence for the exponential poisson regression model
    King, G
  • Unifying political methodology: the likelihood theory of statistical inference
    King, G
  • Variance specification in event count models: from restrictive assumptions to a generalized estimator
    King, G
  • Divided we govern: party control, lawmaking, and investigations, 1946–2002
    Mayhew, DR
  • Some ARMA models for dependent sequences of poisson counts
    McKenzie, E
  • Antigovernment networks in civil conflicts: how network structures affect conflictual behavior
    Metternich, NW; Dorff, C; Gallop, M; Weschle, S; Ward, MD
  • Presidential uses of force during the cold war: aggregation, truncation, and temporal dynamics
    Mitchell, SM; Moore, WH
  • Structural change in the U.S. presidents’ use of force abroad
    Park, JH
  • Global political order, economic change, and armed conflict: coevolving systems and the use of force
    Pollins, BM
  • Handbook of empirical economics and finance
    Trivedi, PK; Munkin, MK
  • A regression model for time series of counts
    Zeger, SL