Question about sample size calculation for a single arm long term followup study
I'm looking at a long term followup project and in the sample size consideration section it is described as such:
The total personyears of followup is approximately 9045 for the 1500 enrolled patients. This number of personyears of followup will provide 91% likelihood of seeing at least one event of interest, if the true rate per 15 years of exposure is at least 1:250.
I don't understand how the 91% likelihood is calculated. Can someone please explain?
Answer
 The questioner was satisfied and accepted the answer, or
 The answer was disputed, but the judge evaluated it as 100% correct.
1 Attachment

A followup question: it was mentioned "91% likelihood of seeing at least one event of interest", is "likelihood" or "probability" the appropriate term to use here?

In this context, I believe they are using the them interchangeably. In statistics, there is a technical difference in what we mean when we say likelihood versus probability, but in standard English usage they can be used interchangeably. So saying "the likelihood this coin lands on heads is 50%" and "the probability the coin lands on heads is 50%" has the same meaning. That seems to be the case here.


I agree that "probability" should be used here as it refers to the chance something will happen while "likelihood" is bound to the parameters of statistical model being examined. Thank you.
 answered
 59 views
 $5.00
Related Questions
 Probabilities
 Find a number for 𝛼 so f(x) is a valid probability density function
 CLT and probability
 Explain how the mean of discrete variables is $\mu = \sum[x P(x)]$
 Why is the ttest for two independent samples $\ t^* = \frac{(\bar{x}_1  \bar{x}_2)}{\sqrt{\frac{S_1^2}{n_1} + \frac{S_2^2}{n_2}}}$?
 Statistics tasks
 applied probability
 Introductory statistics, probability (standard distribution, binomial distribution)