2026-09-18T18:03:36Zhttps://univendspace.univen.ac.za/server/oai/request

oai:univendspace.univen.ac.za:11602/15522024-09-10T14:48:47Zcom_11602_1927com_11602_1914com_11602_1897com_11602_737col_11602_2138col_11602_738

Bere, A. Sigauke, C. Mabvuu, Coster 2020 2020-09-29T19:33:45Z 2020-09-29T19:33:45Z 2020-02-27 Mabvuu, Coster (2020) Variable selection in discrete survival models. University of Venda, South Africa.<http://hdl.handle.net/11602/1552>. http://hdl.handle.net/11602/1552 Mabvuu C. Variable selection in discrete survival models. []. , 2020 [cited yyyy month dd]. Available from: http://hdl.handle.net/11602/1552 Mabvuu, C. (2020). <i>Variable selection in discrete survival models</i>. (). . Retrieved from http://hdl.handle.net/11602/1552 Mabvuu, Coster. <i>"Variable selection in discrete survival models."</i> ., , 2020. http://hdl.handle.net/11602/1552 TY - Dissertation AU - Mabvuu, Coster AB - Selection of variables is vital in high dimensional statistical modelling as it aims to identify the right subset model. However, variable selection for discrete survival analysis poses many challenges due to a complicated data structure. Survival data might have unobserved heterogeneity leading to biased estimates when not taken into account. Conventional variable selection methods have stability problems. A simulation approach was used to assess and compare the performance of Least Absolute Shrinkage and Selection Operator (Lasso) and gradient boosting on discrete survival data. Parameter related mean squared errors (MSEs) and false positive rates suggest Lasso performs better than gradient boosting. Frailty models outperform discrete survival models that do not account for unobserved heterogeneity. The two methods were also applied on Zimbabwe Demographic Health Survey (ZDHS) 2016 data on age at first marriage and did not select exactly the same variables. Gradient boosting retained more variables into the model. Place of residence, highest educational level attained and age cohort are the major influential factors of age at first marriage in Zimbabwe based on Lasso. DA - 2020-02-27 DB - ResearchSpace DP - Univen KW - Boosting KW - Discrete-time hazard model KW - Lasso KW - Penalised variable selection methods KW - Unobservrd heterogeneity LK - https://univendspace.univen.ac.za PY - 2020 T1 - Variable selection in discrete survival models TI - Variable selection in discrete survival models UR - http://hdl.handle.net/11602/1552 ER - MSc (Statistics) Department of Statistics Selection of variables is vital in high dimensional statistical modelling as it aims to identify the right subset model. However, variable selection for discrete survival analysis poses many challenges due to a complicated data structure. Survival data might have unobserved heterogeneity leading to biased estimates when not taken into account. Conventional variable selection methods have stability problems. A simulation approach was used to assess and compare the performance of Least Absolute Shrinkage and Selection Operator (Lasso) and gradient boosting on discrete survival data. Parameter related mean squared errors (MSEs) and false positive rates suggest Lasso performs better than gradient boosting. Frailty models outperform discrete survival models that do not account for unobserved heterogeneity. The two methods were also applied on Zimbabwe Demographic Health Survey (ZDHS) 2016 data on age at first marriage and did not select exactly the same variables. Gradient boosting retained more variables into the model. Place of residence, highest educational level attained and age cohort are the major influential factors of age at first marriage in Zimbabwe based on Lasso. NRF 1 online resource (xviii, 83 leaves) en University of Venda Boosting UCTD Discrete-time hazard model Lasso Penalised variable selection methods Unobservrd heterogeneity 519.546 Survival analysis (Biometry) Biometry Failure time data analysis Variable selection in discrete survival models Dissertation open.access