Statistical Methods for Reconstructing Infection Curves
The objective of this paper is to consider statistical issues for reconstructing infection curves. We investigate the method of back-calculation using a nonstationary incubation period distribution to account for recent treatment advances. A spline methodology based on a penalized likelihood is used for estimating historical infection rates. Estimates can be obtained through iteratively reweighted least squares. Some theoretical calculations to investigate mean square error are presented. There is tradeoff between bias and variance when choosing the smoothing parameter. An approach for choosing a range of sensible smoothing parameters is suggested. Some of the methods are illustrated with the U.S. AIDS epidemic.
KeywordsInfection Rate Smoothing Parameter Calendar Time Roughness Penalty AIDS Epidemic
Unable to display preview. Download preview PDF.
- Brookmeyer, R., Gail, M. H. (1986). Minimum Size of the Acquired Immunodeficiency Syndrome (AIDS) Epidemic in the United States. Lancet 2, 1320.Google Scholar
- Day, N. E., Gore, S. M. (1989). Prediction of the Number of New AIDS Cases and the Number of New Persons Infected with HIV up to 1992: The Results of “Back Projection” Methods. In: Short-term Prediction of HIV Infections and AIDS in England and Wales. London: Her Majesty’s Stationary Office.Google Scholar
- Gail, M. H., Rosenberg, P. S., Goedert, J. J. (1990). Therapy May Explain Recent Deficits in AIDS Incidence. Journal of AIDS 3, 296–306.Google Scholar
- Silverman, B. (1985). Some Aspects of the Spline Smoothing Approach to Non-parametric Regression Curve Fitting. Journal of the Royal Statistical Society B 47, 1–52.Google Scholar
- Wahba, G. (1983). A Comparison of GCV and GML for Choosing the Smoothing Parameter in the Generalized Spline Smoothing Problem. Technical Report 712, Department of Statistics, University of Wisconsin.Google Scholar