Search PubMed⌕ Search

Biomedical subjects

N G Becker

Publications and source records attributed to N G Becker.

42 records · Page 3Linked to original sources
PubMedDate not supplied

Dependent HIV incidences in back-projection of AIDS incidence data.

Techniques for reconstructing plausible HIV incidence curves from AIDS incidence data are called methods of back-projection, or back-calculation. Approaches to back-projection tend to make the simplifying assumption that the quarterly HIV incidences are independent, which is not even approximately true. Here we investigate whether smoothed non-parametric back-projection based on this simplifying assumption gives sensible back-projections and appropriate measures of precision for these reconstructed HIV incidence curves. Simple models for HIV transmission are shown to have much greater variation than the corresponding non-homogeneous Poisson process arising from the independence assumption. Nevertheless, bearing in mind that the objective is to reconstruct the HIV epidemic curve for the current epidemic, it is argued that such back-projection does give sensible HIV curves. This conclusion is supported by a simulation study, which also finds that confidence intervals for the HIV incidences are wider for transmission data than those determined from independent Poisson data.

Acquired Immunodeficiency Syndrome↗
PubMedDate not supplied

Non-parametric analysis of transfusion-related HIV and AIDS incidence data.

The method for making non-parametric inferences about the probability distribution of the incubation period for AIDS from transfusion-related AIDS data is extended to include data on individuals who have tested positive for HIV but do not have AIDS at the time of analysis. The method is illustrated with data on individuals infected by transfusion in Australia. The shape of the incubation distribution, as represented by the truncated distribution function, can be estimated, but the additional data contribute very little to the estimation of this shape. With a general non-parametric form for the incubation distribution the additional data do not overcome the identifiability problem that exists for non-parametric estimation of this distribution from AIDS data alone. If quarterly rates for HIV testing are specified, the additional data make it possible to estimate the cumulative distribution function for the incubation period. This is also possible when a simple parametric form, with one or two unknown parameters, is used for the testing rates. However, the additional data do not allow effective estimation of the HIV testing rates. The estimated shape of the incubation distribution indicates a higher proportion of short incubation periods than an earlier estimate based on U.S. data. Estimates for the incubation distribution itself do not vary much over a plausible range of HIV testing rates.

Acquired Immunodeficiency Syndrome↗
PubMedDate not supplied

Parametric inference for epidemic models.

The likelihood function corresponding to epidemic data is often very complicated. We illustrate that the EM algorithm can sometimes help to simplify likelihood inferences. Difficulties with likelihood inferences about parameters of epidemic models have established a role for martingale methods. These are methods of statistical inference based on estimating equations derived from the rich theory of martingales, and they have produced simple methods of inference in a number of important applications to epidemic data. We contrast likelihood methods with martingale methods and determine which specific assumptions cause changes in inferences about the infection potential of a disease. It is found that the martingale-based estimate of the infection potential remains unaltered under a variety of commonly used model specifications but that the precision of this estimate changes as model assumptions are altered.

Algorithms↗