Confidence distributions for the parameters in an autoregressive process
By: Rolf Larsson
Potential Business Impact:
Helps computers predict future patterns more accurately.
We suggest how to construct joint confidence distributions for several parameters and apply these ideas to an autoregressive process of general order. The implied non informative prior for the parameters, i.e. the ratio between the confidence density and the likelihood function, is proved to be asymptotically flat in the stationary case. However, in the presence of a unit root, the implied prior needs to be adjusted. The results are illustrated by simulation studies and empirical examples.
Similar Papers
Asymptotic analysis of the finite predictor for the fractional Gaussian noise
Statistics Theory
Predicts future data more accurately, even complex patterns.
Autocorrelation functions for point-process time series
Methodology
Finds patterns in event timing.
Estimating weak Markov-switching AR(1) models
Statistics Theory
Helps predict weather patterns more accurately.