| Summary: | Time to event data (survival data) is data of length of time until the event
occurs. If the event time is affected by other independent variables, regression
analysis can be used to analyze the effects of those independent variables. One of
some kinds of regression analysis that can be used is additive hazard regression
with Lin and Ying model.
In Lin and Ying additive hazard model, the regression coefficients are
constants, time-independent. The method that can be used to estimate regression
coefficients in this model is similar with maximum partial likelihood method in
Cox regression. The estimation of regression coefficients can be obtained from
score equation which is obtained from mimicing the score equation from Cox
model. Score equation of Cox model is the derrivative of the partial likelihood.
In this paper, additive hazard regression analysis with Lin and Ying model
is used to analyze some variables that affect the failure of medication of TBC
patients in Puskesmas Mantang, Lombok Tengah. Risk Differences are also
computed to explain each of the effects of independent variables. It is also
presented here the alternative method, hazard regression analysis with Aalen
model, which uses the graph of cumulative regression functions to interprete the
effects of independent variables. It can be seen that additive hazard regression
with Lin and Ying model has advantage in the interpretation of the effects of
independent variables, compared to additive hazard regression with Aalen model
|
|---|