Statistical Modeling of Lung Cancer: Answering Relative Questions

The objective of this paper is to perform parametric and nonparametric analysis to address some very important questions concerning lung cancer utilizing real lung cancer data: What is the probabilistic nature of mortality time in ex-smoker lung cancer patients and non-smoker lung cancer patients, for female, male, and the totality of female and male patients? Is there significant difference of mortality time between ex-smoker and non-smoker patients? For ex-smokers, are there any differences with respect to the key variables such as mortality time, cigarettes per day (CPD), and duration of smoking between female and male patients? For non-smokers, can we notice a difference in mortality time between female and male patients? Can we accurately predict mortality time given information on CPD, starting time and quitting time for a specific lung cancer patient who smokes? Thus best fitting probability distributions are identified and their parameters are estimated. Mean mortality times are compared between non-smokers and ex-smokers, female non-smokers and male non-smokers, and female ex-smokers and male ex-smokers. Important entities related to lung cancer mortality time, such as cigarettes per day (CPD), and duration of smoking (DUR), are compared between female and male ex-smoker lung cancer patients. Finally, a model is developed to predict the mortality time of ex-smokers with a high degree of accuracy.