TY - JOUR
T1 - Autoregressive times series methods for time domain astronomy
AU - Feigelson, Eric D.
AU - Jogesh Babu, G.
AU - Caceres, Gabriel A.
N1 - Funding Information:
We thank Andrew Stuhr (Penn State) for substantial assistance in the data analysis, and Joel Hartman (Princeton) for collaboration on the HAT South analysis. This work is supported by NSF grant AST-1614690 and NASA grant 80NSSC17K0122
Publisher Copyright:
© 2018 Feigelson, Babu and Caceres.
PY - 2018/8/7
Y1 - 2018/8/7
N2 - Celestial objects exhibit a wide range of variability in brightness at different wavebands. Surprisingly, the most common methods for characterizing time series in statistics-parametric autoregressive modeling-are rarely used to interpret astronomical light curves. We review standard ARMA, ARIMA, and ARFIMA (autoregressive moving average fractionally integrated) models that treat short-memory autocorrelation, long-memory 1/fα "red noise," and nonstationary trends. Though designed for evenly spaced time series, moderately irregular cadences can be treated as evenly-spaced time series with missing data. Fitting algorithms are efficient and software implementations are widely available. We apply ARIMA models to light curves of four variable stars, discussing their effectiveness for different temporal characteristics. A variety of extensions to ARIMA are outlined, with emphasis on recently developed continuous-time models like CARMA and CARFIMA designed for irregularly spaced time series. Strengths and weakness of ARIMA-type modeling for astronomical data analysis and astrophysical insights are reviewed.
AB - Celestial objects exhibit a wide range of variability in brightness at different wavebands. Surprisingly, the most common methods for characterizing time series in statistics-parametric autoregressive modeling-are rarely used to interpret astronomical light curves. We review standard ARMA, ARIMA, and ARFIMA (autoregressive moving average fractionally integrated) models that treat short-memory autocorrelation, long-memory 1/fα "red noise," and nonstationary trends. Though designed for evenly spaced time series, moderately irregular cadences can be treated as evenly-spaced time series with missing data. Fitting algorithms are efficient and software implementations are widely available. We apply ARIMA models to light curves of four variable stars, discussing their effectiveness for different temporal characteristics. A variety of extensions to ARIMA are outlined, with emphasis on recently developed continuous-time models like CARMA and CARFIMA designed for irregularly spaced time series. Strengths and weakness of ARIMA-type modeling for astronomical data analysis and astrophysical insights are reviewed.
UR - http://www.scopus.com/inward/record.url?scp=85052871688&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052871688&partnerID=8YFLogxK
U2 - 10.3389/fphy.2018.00080
DO - 10.3389/fphy.2018.00080
M3 - Article
AN - SCOPUS:85052871688
VL - 6
JO - Frontiers in Physics
JF - Frontiers in Physics
SN - 2296-424X
IS - AUG
M1 - 80
ER -