Application of Truncated and Mixture Distributions to Comparisons of Birthweight
Mixture models can arise in a variety of situations. For example, in , a two component mixture model was fitted to grouped, truncated data using the EM algorithm when analysing the volume of red blood cells. Aitkin, , has considered the analysis of mixture distributions using the EM algorithm in GLIM. The motivation for the present work is the analysis of birthweight, which various studies have analysed by assuming a predominantly Normal distributions but with additional births in the tail - an obvious application of some form of mixture distribution; see, for example Ashford et al.,.
Unable to display preview. Download preview PDF.
- Aitkin, M. (1980). Mixture applications of the EMalgorithm in GLIM. In COMPSTAT 1980, pp 537–541.Google Scholar
- Pearson, K. A study of Trypanosome Strains. Biometrika, 10, pp 85–143.Google Scholar
- Pethybridge, R.J., Ashford, J.R., Fryer, J.G. (1974) Some features of the distribution of birthweight of human infants. Br. J. Prev. Soc. Med. 28pp. 10–18.Google Scholar
- Roger, J. (1985). Using factors when fitting the scale parameter to Weibull and other survival regression models with censored data. GLIM Newsletter, 11, pp 14–15.Google Scholar
- Scallan, A.J., Evans, S.J.W. (1989) GLIM macros for fitting truncated distributions to grouped data. To appear in GLIM Newsletter Google Scholar
- Vanderhoeft, C. (1985). Macros for calculating the covariance matrix of functions of parameter estimates. GLIM Newsletter 11, pp 21–24.Google Scholar