https://community.jmp.com/t5/Discussions/JMP-95-Confidence-interval-calculation-and-The-Kaplan-Meier/m-p/399895#M65095 <P>It is possible that the upper confidence interval is missing. Actually, both ends can be missing. Or even the median estimate itself can be missing. All depend on your data.</P> <P>To understand the reason, I will try something plain, but the wording may be less rigorous.</P> <P>Suppose we have three distinct event times at 1, 2, and 3. First two are failures, and the last one is a censored observation.</P> <P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="peng_liu_0-1625853274228.png" style="width: 400px;"><img src="https://community.jmp.com/t5/image/serverpage/image-id/34052i7DF7C411336A1E2B/image-size/medium?v=v2&amp;px=400" role="button" title="peng_liu_0-1625853274228.png" alt="peng_liu_0-1625853274228.png" /></span></P> <P>And here is the report.</P> <P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="peng_liu_3-1625853811894.png" style="width: 400px;"><img src="https://community.jmp.com/t5/image/serverpage/image-id/34056i79D9EB04DE90FFBC/image-size/medium?v=v2&amp;px=400" role="button" title="peng_liu_3-1625853811894.png" alt="peng_liu_3-1625853811894.png" /></span></P> <P>The estimate of the median is time = 2, at which the estimate of the survival probability is 0.3333, which is less than 0.6667 (larger than 0.5) at time = 1. So the upper end of the confidence interval should be some time point after 2 and at which the survival probability estimate is even less and satisfies the condition described by the paper below. However, there does not exist even a single such time point after time = 2. Time = 2 is the last failed observation</P> <P>The rigorous explanation can be found in this paper:</P> <DIV id="apa_text" class="citation__copy" data-v-6a38eceb="">Brookmeyer, R., &amp; Crowley, J. (1982). A Confidence Interval for the Median Survival Time. <I>Biometrics,</I> <I>38</I>(1), 29-41. doi:10.2307/2530286</DIV> Fri, 09 Jul 2021 18:28:17 GMT peng_liu 2021-07-09T18:28:17Z https://community.jmp.com/t5/Discussions/JMP-95-Confidence-interval-calculation-and-The-Kaplan-Meier/m-p/399470#M65034 <P><U>Hi,</U></P><P><U>Why the upper 95% value not calculated for my survival analysis data?</U></P><P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Neeraj_0-1625688439328.png" style="width: 400px;"><img src="https://community.jmp.com/t5/image/serverpage/image-id/34027i190B19B0B967595A/image-size/medium?v=v2&amp;px=400" role="button" title="Neeraj_0-1625688439328.png" alt="Neeraj_0-1625688439328.png" /></span></P><P>&nbsp;</P><P>Thanks</P><P>Neeraj&nbsp;</P> Sun, 11 Jun 2023 11:15:59 GMT https://community.jmp.com/t5/Discussions/JMP-95-Confidence-interval-calculation-and-The-Kaplan-Meier/m-p/399470#M65034 Neeraj 2023-06-11T11:15:59Z https://community.jmp.com/t5/Discussions/JMP-95-Confidence-interval-calculation-and-The-Kaplan-Meier/m-p/399895#M65095 <P>It is possible that the upper confidence interval is missing. Actually, both ends can be missing. Or even the median estimate itself can be missing. All depend on your data.</P> <P>To understand the reason, I will try something plain, but the wording may be less rigorous.</P> <P>Suppose we have three distinct event times at 1, 2, and 3. First two are failures, and the last one is a censored observation.</P> <P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="peng_liu_0-1625853274228.png" style="width: 400px;"><img src="https://community.jmp.com/t5/image/serverpage/image-id/34052i7DF7C411336A1E2B/image-size/medium?v=v2&amp;px=400" role="button" title="peng_liu_0-1625853274228.png" alt="peng_liu_0-1625853274228.png" /></span></P> <P>And here is the report.</P> <P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="peng_liu_3-1625853811894.png" style="width: 400px;"><img src="https://community.jmp.com/t5/image/serverpage/image-id/34056i79D9EB04DE90FFBC/image-size/medium?v=v2&amp;px=400" role="button" title="peng_liu_3-1625853811894.png" alt="peng_liu_3-1625853811894.png" /></span></P> <P>The estimate of the median is time = 2, at which the estimate of the survival probability is 0.3333, which is less than 0.6667 (larger than 0.5) at time = 1. So the upper end of the confidence interval should be some time point after 2 and at which the survival probability estimate is even less and satisfies the condition described by the paper below. However, there does not exist even a single such time point after time = 2. Time = 2 is the last failed observation</P> <P>The rigorous explanation can be found in this paper:</P> <DIV id="apa_text" class="citation__copy" data-v-6a38eceb="">Brookmeyer, R., &amp; Crowley, J. (1982). A Confidence Interval for the Median Survival Time. <I>Biometrics,</I> <I>38</I>(1), 29-41. doi:10.2307/2530286</DIV> Fri, 09 Jul 2021 18:28:17 GMT https://community.jmp.com/t5/Discussions/JMP-95-Confidence-interval-calculation-and-The-Kaplan-Meier/m-p/399895#M65095 peng_liu 2021-07-09T18:28:17Z