Koons, Bruce K.2015-07-092015-07-091989http://hdl.handle.net/10919/54221Time series data often is observed with measurement error. One type of measurement error almost always present is rounding error. A procedure is proposed for estimating parameters of a finite moving average time series which is observed only after rounding. Method of moments estimators are proposed for estimation of parameters of time series observed with general measurement error, including error, ε<sub>n</sub>, which is correlated with the series X<sub>t</sub> being measured. This procedure requires knowledge of the autocovariance function (ACF) of ε<sub>t</sub>, and the cross covariances between X<sub>t</sub> and ε<sub>r</sub>. For rounding error, the rounding error series is shown to approach uniform white noise as the rounding interval width, R, approaches zero, and the cross correlations between X<sub>t</sub>, and rounding error ε<sub>t</sub>, are shown to approach zero as R -> 0. For both small R and large R, the ACF of ε<sub>t</sub>, and the cross covariances between X<sub>t</sub> and ε<sub>t</sub>, are approximated. These values are then used to estimate the parameters of the moving average model for X<sub>t</sub> when X<sub>t</sub> is observed after rounding.x, 124 leavesapplication/pdfen-USIn CopyrightLD5655.V856 1989.K666Time-series analysisRegression analysisParameter estimation for series observed with round-off errorDissertation