Some Consequences of Using Measurement Error Shockss When Estimating Time Series Models

Abstract

In a number of time times models there are I(1) variables that appear in data sets in differenced from. This note shows that an emerging practice of assuming that observed data relates to model variables through the use of error when estimating these models can imply that there is a lack of co-integration between model and data variables, and also between data variables themselves. An analysis is provided of what the nature of the measurement error would need to be if it was desired to reproduce the same co-integration information as seen in the data. Sometimes this adjustment can be complex. It is very unlikely that measurement error can be described properly with the white noise shocks that are commonly used for measurement error.