LOGSPLINE ESTIMATION OF A POSSIBLY MIXED SPECTRAL DISTRIBUTION
- 1 July 1995
- journal article
- Published by Wiley in Journal of Time Series Analysis
- Vol. 16 (4) , 359-388
- https://doi.org/10.1111/j.1467-9892.1995.tb00240.x
Abstract
Cubic splines and indicator functions are used to estimate the spectral density function and line spectrum, respectively, for a stationary time series. A fully automatic procedure involving maximum likelihood, stepwise addition and deletion of basis functions, and the Bayes information criterion (BIC) is used to select the final model.Keywords
This publication has 23 references indexed in Scilit:
- Nonparametric Spectral Density Estimation Using Penalized Whittle LikelihoodJournal of the American Statistical Association, 1994
- Nonparametric Spectral Density Estimation Using Penalized Whittle LikelihoodJournal of the American Statistical Association, 1994
- A General Resampling Scheme for Triangular Arrays of $\alpha$-Mixing Random Variables with Application to the Problem of Spectral Density EstimationThe Annals of Statistics, 1992
- Efficient bias corrected nonparametric spectral estimationBiometrika, 1991
- Optimal high-order Yule-Walker estimation of sinusoidal frequenciesIEEE Transactions on Signal Processing, 1991
- SOME PROPERTIES OF AUTOREGRESSIVE ESTIMATES FOR PROCESSES WITH MIXED SPECTRAJournal of Time Series Analysis, 1990
- CROSS‐VALIDATORY CHOICE OF A SPECTRUM ESTIMATE AND ITS CONNECTIONS WITH AICJournal of Time Series Analysis, 1990
- The bootstrap applied to power spectral density function estimationBiometrika, 1986
- Automatic Smoothing of the Log PeriodogramJournal of the American Statistical Association, 1980
- A Survey of Statistical Work on the Mackenzie River Series of Annual Canadian Lynx Trappings for the Years 1821-1934 and a New AnalysisJournal of the Royal Statistical Society. Series A (General), 1977