Bøger af Steve Bicko Cygu

Using computational approaches utilizing large datasets to investigate public healthinformation is an important mechanism for institutions seeking to identify strategiesfor improving public health. The art in computational approaches, for examplein health research, is managing the trade-offs between the two perspectives:first, inference and s econd, p rediction. Many techniques from statistical methods(SM) and machine learning (ML) may, in principle, be used for both perspectives.However, SM has a well established focus on inference by building probabilisticmodels which allows us to determine a quantitative measure of confidence aboutthe magnitude of the effect. Simulation-based validation approaches can be usedin conjunction with SM to explicitly verify assumptions and redefine t he specifiedmodel, if n ecessary. On the other hand, ML uses general-purpose algorithmsto find p atterns t hat b est p redict t he o utcome and makes minimal assumptionsabout the data-generating process; and may be more effective in a number of situations.My work employs both SM- and ML- based computational approaches toinvestigate particular public health problems. Chapter One provides philosophicalbackground and compares the application of the two approaches in public health.Chapter Two describes and implements penalized Cox proportional hazard modelsfor time-varying covariates time-to-event data. Chapter Three applies traditionalsurvival models and machine learning algorithms to predict survival times of cancerpatients, while incorporating the information about the time-varying covariates.Chapter Four discusses and implements various approaches for computing predictionsand effects for generalized linear (mixed) models. Finally, Chapter Fiveimplements and compares various statistical models for handling univariate andmultivariate binary outcomes for water, sanitation and hygiene (WaSH) data.