SVA Survival Analysis Assignment 2020 1STAT827/SVA Survival Analysis Module 1 1ENAG11008 – Professional and Sustainable Engineering PracticeICT284 Systems Analysis and DesignConduct a literature reviewENGIN 3202 GEOTECHNICAL ENGINEERINGMIS500 Foundations of Information SystemsCSE5DSS – Decision Support SystemsSupply Chain Analysis and DesignCORPORATE AWARD PROGRAMME

SOLUTION AT Australian Expert Writers

Assignment
Survival Analysis
2020
Due date: 11.55pm 20/04/ 2020
SVA Survival Analysis Assignment 2020 1
While this document has been written for BCA students, it applies equally to Macquarie
students. Please note you should include the page number in a header or footer on each page.
The following data set (framing2.dta) consists of data from the Framingham Heart study
http: //en.wikipedia.org/wiki/Framingham_Heart_Study, for male subjects only from start
of the study. The data has been modified slightly to preserve anonymity. We are interested in the
time from entry to death. I have included a limited selection of covariates to reduce the size of the
analysis.
Variable Description
randid
death
timedth
age
educ
Patient Identifier
Status at end of followup (0=Censored, 1=death)
Time from start of study to death or censoring (Years)
Age (Years)
Education level (1=0-11 years, 2=High School diploma,
3=Some college, 4=College degree+, 5=Unknown)
Previous coronary heart disease (CHD) (0=No, 1=Yes)
Systolic blood pressure (mm Hg)
prevchd
sysbp
Develop a parsimonious model for time from entry to death, using the covariates age, educ,
prevchd and sysbp, using the methods described in HL&M or some reasonable alternative. In
considering interactions only consider those with prevchd, and include interactions if they are
significant at the 0.1 level. Do not categories any of the continuous covariates for inclusion in
the Cox model. For your solution include:
a. Perform preliminary inspection of the data using graphs and tables. Comment.
b. Fit a model with all predictors and show that education level is not needed.
c. Using the model with all predictors other than education, show that no transformation
is required for either continuous predictor.
d. Check for interactions with previous CHD and include any that are significant at the 0.1
level i.e. some evidence.
e. Check the proportional hazards assumption, fix any problems and confirm that the model
satisfies proportional hazards. Note: If you don’t find a problem with prevchd stratify by it
and think why not.
f. Perform any diagnostic checks that haven’t already been performed and comment.
g. A table of estimates for your final model, suitable for publication. Include comments in
part (f).
h. Predicted survival curves for the final model, showing the effect of prevchd at ages 40 and
60 with other covariates at mean values. Obtain these using only one fitted model. Include
comments in part (f).
VA Survival Analysis Assignment 2020 2
i. A summary of the fitted model, referring to parts(d) and (e).
For parts (d) and (e) the results should be properly formatted, as suitable for a publication,
with no raw Stata output. For other parts there is no need to perform formatting, except that
graphs should indicate what they are plotting.
You should include your Stata code as an appendix. The best method is to place the code
in a do file, and then copy to your assignment when it is finalised.

Order from Australian Expert Writers
Best Australian Academic Writers

QUALITY: 100% ORIGINAL PAPERNO PLAGIARISM – CUSTOM PAPER

Assignment status: Already Solved By Our Experts

(USA, AUS, UK & CA Ph. D. Writers)

CLICK HERE TO GET A PROFESSIONAL WRITER TO WORK ON THIS PAPER AND OTHER SIMILAR PAPERS, GET A NON PLAGIARIZED PAPER FROM OUR EXPERTS

Order from Australian Expert Writers
Best Australian Academic Writers

QUALITY: 100% ORIGINAL PAPER – NO PLAGIARISM – CUSTOM PAPER

YOU MAY ALSO READ ...  OJ SIMPSON TRIAL: CASE STUDY ANALYSIS