Menu Expand



Hasenkamp, G. Fehlende Beobachtungen in autoregressiven Verhaltensgleichungen. Journal of Contextual Economics – Schmollers Jahrbuch, 104(1), 21-28.
Hasenkamp, Georg "Fehlende Beobachtungen in autoregressiven Verhaltensgleichungen" Journal of Contextual Economics – Schmollers Jahrbuch 104.1, 1984, 21-28.
Hasenkamp, Georg (1984): Fehlende Beobachtungen in autoregressiven Verhaltensgleichungen, in: Journal of Contextual Economics – Schmollers Jahrbuch, vol. 104, iss. 1, 21-28, [online]


Fehlende Beobachtungen in autoregressiven Verhaltensgleichungen

Hasenkamp, Georg

Journal of Contextual Economics – Schmollers Jahrbuch, Vol. 104 (1984), Iss. 1 : pp. 21–28

Additional Information

Article Details

Hasenkamp, Georg


  1. Degenais, M. G. (1973), The use of incomplete observations in multiple regression analysis, a generalized least squares approach. Journal of Econometrics 1, 317 - 328.  Google Scholar
  2. Gourieroux, Ch. and A. Monfont (1981), On the problem of missing Data in linear models. Review of Economic Studies 48, 579 - 586.  Google Scholar
  3. Kmenta, J. (1981), On the problem of missing measurements in the estimation of economic relationship, in: E. G. Charatsis (ed.), Proceedings of the Econometric Society Meeting 1979, North-Holland, Arnsterdam.  Google Scholar
  4. Palm, F. C. and Th. E. Nijman (1982), Missing observations in the dynamic regression model, Paper presented at the Econometric Society European Meeting in Dublin. Sept. 1982.  Google Scholar
  5. Wansbeek, T. and A. Kapteyn (1981), Maximum likelihood estimation in a linear model with serially correlated errors when observations are missing, Central Bureau of Statistics, The Netherlands, manuscript.  Google Scholar
  6. White, H. and I. Domowitz (1981), Nonlinear regression with dependent observations, Dept. of Economics, University of California - San Diego, Discussion Paper 81 - 32.  Google Scholar
  7. Zellner, A. (1966), On the analysis of first order autoregressive models with incomplete data. International Economic Review 7, 72 - 76.  Google Scholar


This paper illustrates a method to estimate autoregressive equations whenever some observations are missing. By substituting for the missing observation one obtains a combination of linear and non-linear equations. The common parameters in these equations are estimated by a two-step-method. An empirical illustration of this method is provided by using data on industrial demand for electricity