ST332 & ST409: Medical Statistics 2022-2023 Assignment 2
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
ST332 & ST409: Medical Statistics 2022-2023
Assignment 2 – Individual Project
Deadline: 13:00 Friday 17th March 2023
Background & Dataset
The dataset liver .RData contains the survival times of patients who have recently undergone treatment for liver cancer. Follow-up was for a maximum of 50 months. In addition to standard care, some of the patients were ran- domly assigned a new treatment - selective internal radiation therapy (SIRT) for treating inoperable liver tumors and in which radioactive beads are in- serted into the liver. The dataset contains the survival time of the patients in months (time) along with a censoring indicator (dead; 0=alive, 1=dead), age (years), treat; 0=standard care (SC), 1=standard care + SIRT (SIRT) and stage; 0, 1 & 2 - 2 denotes a worse stage of cancer at treatment initiation.
Questions
1. Produce a Kaplan-Meier plot showing the patients in the SC group and the SIRT group separately together with a suitable legend. [5]
2. Perform a Log-Rank Test to assess whether there is a difference in survival between the SC and SIRT treatment groups [5]
3. Report the median survival and 95% CI and the Restricted Mean Survival Time (RMST) [restricted to 50 months] and 95% CI for the two groups separately, together with the difference in RMST and a 95% CI. [5]
4. Fit a log-Normal AFT model to the survival data for the two treatment groups, and report the parameter estimates and 95% CIs, including the Acceleration Factor (AF) and 95% CI and write a sentence interpreting the AF results for a clinician. [5]
5. Produce a plot of the fitted survival curves from Q4 superimposed on the Kaplan-Meier curves for the same patients and comment. [5]
6. Fit a Cox Proportional Hazards regression model to the survival data for the two treatment groups, and report the Hazard Ratio (HR) and 95% CI for treat and write a sentence interpreting the HR results for a clinician. [5]
7. What other covariates need to be included in the Cox PH model in Q6? Report the HRs for all covariates in your ”final” model together with 95% CIs & P-values and write a sentence interpreting the HR results for a clinician. [5]
8. For your ”final” model in Q7 perform a test of proportional hazards for all covariates and interpret your results. [5]
9. Produce a plot of Schoenfield residuals for each covariate in your ”fi- nal” model in Q7 and interpret them. [5]
10. For your ”final” model in Q7 include an interaction term for treat with log(time) and interpret the results. [5]
Your solutions should not include any R code or pasted output from the console – marks will be deducted for this. It is expected that your solutions will be professionally presented (e.g. using LATEXor R Markdown) and submitted as a single pdf document which should not exceed 6 pages. Note no appendices are allowed.
2023-03-05