Estimation of MA(1) model based on rounded data

Abstract

Most recorded data of continuous distributions are rounded to
the nearest decimal place due to the precision of the recording mechanism. This
rounding entails errors in estimation and measurement. In this study, we consider
parameter estimation of time series models based on rounded data. The adjusted
maximum likelihood estimates of Stam and Cogger (1993) are derived theoreti-
cally for the first order moving average MA(1) model. Simulations are performed
to compare the e±ciencies of the adjusted maximum likelihood estimators with
other estimators.