Abstract
It may occur that disturbances in a regression model are serially correlated and that some observations are missing. Savin and White (1978a) and Richardson and White (1979) present various Durbin-Watson type tests for autocorrelation when observations are missing. Wansbeek and Kapteyn (1985) describe a maximum likelihood estimator and several two-step estimators of the model parameters for the case that the disturbances follow a first order Markov process. Their method is partly based on the well-known first order autocorrelation transformation of the data with a specific adjustment for the cases where data are missing.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Knottnerus, P. (1991). Estimation of Regression Models with Missing Observations and Serially Correlated Disturbances. In: Linear Models with Correlated Disturbances. Lecture Notes in Economics and Mathematical Systems, vol 358. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-48383-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-48383-7_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53901-8
Online ISBN: 978-3-642-48383-7
eBook Packages: Springer Book Archive