A method of non-parametric back-projection and its application to AIDS data.

The method of back-projection has been used to estimate the unobserved past incidence of infection with the human immunodeficiency virus (HIV) and to obtain projections of future AIDS incidence. Here a new approach to back-projection, which avoids parametric assumptions about the form of the HIV infection intensity, is described. This approach gives the data greater opportunity to determine the shape of the estimated intensity function. The method is based on a modification of an EM algorithm for maximum likelihood estimation that incorporates smoothing of the estimated parameters. It is easy to implement on a computer because the computations are based on explicit formulae. The method is illustrated with applications to AIDS data from Australia, U.S.A. and Japanese haemophiliacs.

[1]  M H Gail,et al.  Backcalculation of flexible linear models of the human immunodeficiency virus infection curve. , 1991, Journal of the Royal Statistical Society. Series C, Applied statistics.

[2]  L Billard,et al.  The distribution of the incubation period for the acquired immunodeficiency syndrome (AIDS) , 1988, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  W. Darrow,et al.  The epidemiology of AIDS: current status and future prospects. , 1985, Science.

[4]  T. Tango.  Estimation of haemophilia-associated AIDS incidence in Japan using individual dates of diagnosis. , 1989, Statistics in medicine.

[5]  Valerie Isham,et al.  Mathematical modelling of the transmission dynamics of HIV infection and AIDS (a review) , 1988 .

[6]  J. D. Wilson,et al.  A smoothed EM approach to indirect estimation problems, with particular reference to stereology and emission tomography , 1990 .

[7]  M. Mcevoy,et al.  SOME PROBLEMS IN THE PREDICTION OF FUTURE NUMBERS OF CASES OF THE ACQUIRED IMMUNODEFICIENCY SYNDROME IN THE UK , 1985, The Lancet.

[8]  J J Goedert,et al.  Censoring in an epidemic with an application to hemophilia-associated AIDS. , 1989, Biometrics.

[9]  L. Shepp,et al.  A Statistical Model for Positron Emission Tomography , 1985 .

[10]  J F Lawless,et al.  Estimating the incubation time distribution and expected number of cases of transfusion‐associated acquired immune deficiency syndrome , 1989, Transfusion.

[11]  Jerald F. Lawless,et al.  Inference Based on Retrospective Ascertainment: An Analysis of the Data on Transfusion-Related AIDS , 1989 .

[12]  V. Isham,et al.  Estimation of the incidence of HIV infection. , 1989, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[13]  J M Taylor,et al.  Models for the HIV infection and AIDS epidemic in the United States. , 1989, Statistics in medicine.

[14]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[15]  S. Lagakos,et al.  The value of AIDS incidence data in assessing the spread of HIV infection. , 1989, Statistics in medicine.

[16]  Mitchell H. Gail,et al.  A Method for Obtaining Short-Term Projections and Lower Bounds on the Size of the AIDS Epidemic , 1988 .

[17]  N. Day,et al.  Predictions of the AIDS epidemic in the U.K.: the use of the back projection method. , 1989, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[18]  P J Solomon,et al.  Accommodating change due to treatment in the method of back projection for estimating HIV infection incidence. , 1990, Biometrics.

[19]  Peter Bacchetti,et al.  Incubation period of AIDS in San Francisco , 1989, Nature.