# NURS341 Lecture Notes - Lecture 4: Null Hypothesis, Effect Size, Selection Bias

## Document Summary

If the sample is representative of the population, we can draw inferences from the sample about the population: bigger sample = the closer the mean and sd matched to the population. Inferential statistics allow researchers to make inferences about a population based on a sample. In order to make these inferences, researchers use the central limit theorem. Many say you need at least a sample size of 30: the sample should be randomly selected from the population of a finite variance. Two types of sampling: probability, simple random. Everyone in the sample has a chance of being selected. Randomly select the number of participants required. Population must be accessible so often not feasible: systematic sampling. Population must be accessible: stratified sampling. Divide population into subpopulations depending on variables of interest and then randomly sample from them: you know what proportion of people are in select groups, and you choose from different strata.