Template-type: ReDIF-Paper 1.0
Author-Name: Andrew Harvey
Author-Workplace-Name: Faculty of Economics, Cambridge University
Author-Name: Ryoko Ito
Author-Workplace-Name: Dept of Economics and Nuffield College, Oxford University
Author-Email: ryoko.ito@economics.ox.ac.uk
Title: Modeling time series with zero observations
Abstract: We consider situations in which a signi?cant proportion of observations in a time series are zero, but the remaining observations are
positive and measured on a continuous scale. We propose a new dynamic model in which the conditional distribution of the observations
is constructed by shifting a distribution for non-zero observations to the left and censoring negative values. The key to generalizing the
censoring approach to the dynamic case is to have (the logarithm of) the location/scale parameter driven by a ?lter that depends on the 
score of the conditional distribution. An exponential link function means that seasonal effects can be incorporated into the model and
this is done by means of a cubic spline (which can potentially be time-varying). The model is ?tted to daily rainfall in northern Australia
and compared with a dynamic zero-augmented model.

Classification-JEL: C22
Keywords: Censored distributions; dynamic conditional score
model; generalized beta distribution; rainfall; seasonality, zero aug-
mented model.
Length: 48 pages
Creation-Date: 2017-02-21
Number: 2017-W01
File-URL: https://www.nuffield.ox.ac.uk/economics/papers/2017/CensorAus5d_Submit.pdf
File-Format: application/pdf
Handle: RePEc:nuf:econwp:1701