2 Right Censoring and Kaplan-Meier Estimator - NCSU Statistics
2 Right Censoring and Kaplan-Meier Estimator - NCSU Statistics
2 Right Censoring and Kaplan-Meier Estimator - NCSU Statistics
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
CHAPTER 2 ST 745, Daowen Zhang<br />
<strong>Censoring</strong> <strong>and</strong> differential follow-up create certain difficulties in the analysis for such data<br />
as is illustrated by the following example taken from a clinical trial of 146 patients treated after<br />
they had a myocardial infarction (MI).<br />
The data have been grouped into one year intervals <strong>and</strong> all time is measured in terms of<br />
patient time.<br />
Table 2.1: Data from a clinical trial on myocardial infarction (MI)<br />
Number alive <strong>and</strong> under<br />
Year since observation at beginning Number dying Number censored<br />
entry into study of interval during interval or withdrawn<br />
[0, 1) 146 27 3<br />
[1, 2) 116 18 10<br />
[2, 3) 88 21 10<br />
[3, 4) 57 9 3<br />
[4, 5) 45 1 3<br />
[5, 6) 41 2 11<br />
[6, 7) 28 3 5<br />
[7, 8) 20 1 8<br />
[8, 9) 11 2 1<br />
[9, 10) 8 2 6<br />
Question: Estimate the 5 year survival rate, i.e., S(5) = P [T ≥ 5].<br />
Two naive <strong>and</strong> incorrect answers are given by<br />
1. � F (5) = P [T