# Tag Info

### Considering 96 observation for estimating the intercept (rule of thumb)

As I recall, that recommendation for 96 is to get a precise estimate of the intercept (log-odds at reference conditions) in a logistic regression model. If all you care about is how changes in ...
• 95.6k
1 vote

### Sample size calculation clinical trial

A percentage reduction can mean many things - it can mean effects for analyses of continuous outcomes on the logarithmic scale (like 70% off a sticker price). But because no standard deviation is ...
• 63.7k
1 vote
Accepted

### How to do a power analysis on density (count/area) data?

Overview Simulation is a good way to estimate power in situations that aren't covered by simple formulas. In your case, use your current data to estimate the characteristics of the data generating ...
• 95.6k

### How to do a power analysis on density (count/area) data?

The first step to start to do what you want is to fit an appropriate model to all the count data that you have for that species, over all years. Working with "densities" ignores the ...
• 95.6k

### Two-Way repeated measures ANOVA with multiple data points per measurement

Maybe not a complete answer, but a question, a comment, and some suggestions. Question: in order for your physicians to capture the medical history, they need some subjects (patients, real or ...
• 1,805
1 vote

### How to know what sample size (number of cells) is sufficient to determine what percentage of cells are above a threshold?

To validate the threshold for cell proliferation you have a tough road ahead. You need to show that if a cell count is below the threshold it doesn’t matter biologically how far below the threshold ...
• 95.7k

### small sample size (need some advice)

It sounds like you have two modeling strategies for the same binary outcome assessed two different ways: in the Cox model, you care about time to first occurrence of an event, in the logistic model, ...
• 63.7k
1 vote
Accepted

### discrete time model and Logistic regression

In reverse order: Question 2. The power of a survival model is a function of the number of events; that of logistic regression is a function of the number of cases in the minority class. In both ...
• 95.6k