In this study the effect of socioeconomi c, demographic and biological va riables on infantrnsurvival is in vestigated using data li'om "'fhe .limma in f~I1 t survival differential longitudinalrnstud y"' conducted in 46 urban and 64 ru ral ' kebe les' in South-West Ethi op ia during Septemberrn1992 and October 1994. The study uses 7,851 singleton and 89 twin infants. Matched pairrnanalysis is used to assess the survival experience between twins, and parametric regressionrnmodel is used to ,examine the association between infant mortality and socioeconomic,rndemographic and bio logica l va riables. Data analyses wcre made using STATA 10 and SI'SS 16.rnThe result of the matehcd pair analysis showed that, thc hazard ratcs for thc lirst and thernsecond born twins are different at 5% leve l of significance. The Kaplan-Meier survi valrnestimate far the first born twi ns is 0.7143 (95% CI: 0.6069 to 0.7971) and ror the second bornrnIrntwins is 0.5634 (95% CI: 0.4523 to 0.6604).rnIn regard to the survival of singleton in fants , the result of Kaplan-Meier estimator shows thatrnthe survival probability is 0.9 12 with standard error or 0.0033. That is, infant mortality rate orrnabout 88 deaths per 1000 live birth s.rnDirferent parametric regression models were fitted to select the s ignificant factors afreet ingrninfant mortality in South-West Eth iopia. Almost all the models considered provided good fitrnl'or the data but log-no rma l regression model was round to be the best fit l'or the data.rnIlased on the result br the final log-normal regression model, in fant mortality was significantlyrn(p < 0.05) associated with birth weight, sex of the infant, mother's education, lamily size andrnmarita l status and the interaction between ethnie ity and place of res idence.