![]() ![]() The method can determine survival risk factors without assuming parametric associations. In 2008, introduced Random Survival Forests (RSF), a fully non parametric ensemble tree based method for analysis of right censored survival data. ![]() ![]() To deal with these limitations, nonparametric survival trees and forests have recently become useful alternatives. In addition, Cox PH model does not take in to account the missing predictors, non-linearity of exponential factors and interdependence among observations. One such assumption is that the hazard ratio between any two observations is proportional over time. However, the method makes assumptions which are not easily satisfied. Other than being semi-parametric, Cox PH model is also popular due to its ability to produce adequately good regression coefficient estimates, survival curves and hazard ratios of interest for a wide variety of data occurrence. The Cox model estimates survival by evaluating various explanatory variables all at once. One of the most commonly used semi-parametric method in analysis of time to event data is the Cox Proportional Hazard (PH) method. Introduction In survival analysis, censored survival data are frequently predicted using semi-parametric methods. Hence, the age of the child and the siblings’ information are identified as some of the key determinants of U5CM.ġ. Using Balanced Random Survival Forests (BRSF) with Bs.gradient splitting rule, the identified determinants of U5CM are V207 (sum of deceased daughters), V219 (sum total of living children) and B8 (age of the child). According to our analysis, we settle on Bs.gradient splitting method which still has a high concordance index of 0.86 and smaller error rate of 0.028. ![]() Some of the variables in the data were found to violate the PH assumption making the use of log-rank splitting rule not optimal. However, optimality of log-rank is achieved when the hazard is proportional over time. In conclusion, the results from the analysis presented in this paper show the superiority of log-rank splitting rule. The model with log-rank splitting rule recorded the highest concordance of 0.916 followed by Bs.gradient with a concordance of 0.864 while log-rank score resulted in a concordance of 0.799. Respective selected variables were fitted in the Cox Aalen’s model for prediction while model selection was carried out using concordance index. The balanced data was integrated in RSF for variable selection while applying the three specified splitting rules. The data used was balanced using Random Under-sampling method. To achieve this we used various split rules, namely: log-rank, log-rank score and Bs.gradient splitting rules. This study aimed at handling the problem of non proportional hazard assumptions that characterize covariates of survival regression models. KDHS (2014) data is characterized by high dimensionality, high imbalance and violation of Proportional Hazard (PH) assumptions among other statistical challenges. This study used the Kenya Demographic and Health Survey (KDHS) data (2014) to understand the determinants of U5CM. The Sustainable Development Goals target of 25 deaths per 1000 live births has not yet been achieved in many Low and Middle Income Countries (LMIC). Under Five Child Mortality (U5CM) remains a major health problem in the developing world. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |