POPM 3240 Lecture 8: Statistical Analyses of Epidemiological Data
24 Feb 2019
School
Department
Course
Professor
Document Summary
Estimate how commonly something occurs or explore differences in risk of disease between groups. Demonstrate statistical association to know whether observed differences are real. Different samples give different information about the population so need to know probability of what we are seeing is the truth and not just random chance. On average (if samples are representative) should get the right answer. Limitations: know the average but not the distribution (wide or narrow) Central limit theorem (what is the possible range of values) Variance s2 which describes the overall variability around the mean (all directions) Limitations of the clt: need a large sample size, need to know standard deviation of the population. This is often unknown, so we use the standard deviation of the sample to calculate the standard error of the mean = s / (n)1/2. Because we are using a sample, out distribution won"t be normal; it is shorter and wider and called a t-distribution.
