SUSSER,
E.(http://cait.cpmc.columbia.edu/research/faculty/facu0330.html)
WITTKOWSKI, K.M. (1997-08-10..14) Joint Statistical Meetings Anaheim, CA
Assessment of risk factors and evaluation of intervention strategies often require analysis of multivariate data. Methods based on linear models (factor analysis, sum of scores) are often problematic, due to (1) non-linear relationships between variables and underlying factors and (2) negative correlation between variables (due to, e.g., time constraints). Standard rank procedures (log-rank, Gehan, etc.) may have low power or exceed the level when applied to data with varying precision (e.g. discretized or censored).
Recently, a multivariate method based on the Marginal-Likelihood principle has been developed where (1) rank scores are computed by a scale invariant general procedure generated by the semi-ordering of (censored) data, (2) these rank scores are weighted by non-parametric 'Fisher information'-type weights, (3) the type of ties (exact/rounded) is considered when estimating the variance of the test statistic, and (4) some secondary/dependent variables may be selected to rank observations that cannot be ordered on the basis of the primary/independent variables alone (including a new alternative to isotonic regression).
We present recent applications of this method to efforts in describing and reducing the spread of HIV and Schistosomiasis.
SUSSER E et al. (1997) AJPH (in press); WITTKOWSKI KM (1988/92) JASA 83 : 1163/ 87 :258; - (1989) The Statistician 38 :93; TALAAT M et al.(1997) Conf Health Issues in the Middle East (in press)
EINSELE, H., EHNINGER, G., HEBART, H., WITTKOWSKI, K.M., SCHULER, U., JAHN, G., MACKES, P., HERTER, M., KLINGEBIEL, T., LÖFFLER, J., WAGNER, S., MÜLLER, C.A. (1995) Polymerase chain reaction monitoring reduces the incidence of cytomegalovirus disease and the duration and side effects of antiviral therapy after bone marrow transplantation. Blood(internet-link: "http://www.bloodjournal.org/") 86 :2815-2820
SUSSER, E.(internet-link: "http://cait.cpmc.columbia.edu/research/faculty/facu0330.html") , DESVARIEUX, M., WITTKOWSKI, K.M. (199?) Reporting sexual risk behavior for HIV: a practical risk index and a method for improving risk indices (in press)
TALAAT, M., WITTKOWSKI, K.M., HUSEIN, M.H., BARAKAT, R. A new Procedure to Access Individual Risk of Exposure to Cercariae from Multivariate Questionnaire Data. Conference on Health Issues in the Middle East, Ann Arbor, MI, 21.-23.03.97 (in press)
WITTKOWSKI, K.M. (1988) Friedman-type statistics and consistent multiple comparisons for unbalanced designs. Journal of the American Statistical Association 83 : 1163-1170
WITTKOWSKI, K.M. (1989) An asymptotic UMP sign test for discretized data. The Statistician 38 :93-6
WITTKOWSKI, K.M. (1992) An extension to Wittkowski. JASA 87 :258
WITTKOWSKI , K . M . Comparison of Hospitals Based on Objective Marginal-Likelihood Score Matrices for Multivariate Ordinal Data. Joint Statistical Meetings , Anaheim, CA, 1997-08-10..14
SUSSER,
E.(http://cait.cpmc.columbia.edu/research/faculty/facu0330.html)
XI International
Conference on AIDS(http://www.interchg.ubc.ca/aids11/homepage.html)
Blood(http://www.bloodjournal.org/)
SUSSER,
E.(http://cait.cpmc.columbia.edu/research/faculty/facu0330.html)