Determine whether a sample is a good fit for a statistical question or not.
What factors affect this?
Statistical question - a question that gives variability in its responses
Categorical data - quantitative data, based on categories using words, "What" type of questions
Numerical data - qualitative data, based on numbers, "How many" type of questions
Population - a group of people that is targeted for collecting data from a statistical question
Sample - a smaller group of people within the population that accurately represents the population
Bias - different types of bias will lead to the data being inaccurate for the population
Sample bias - collecting data from a sample that does not match the population
Leading question bias - phrasing a question in a way to elicit a specific response
Undercoverage/non response bias - not asking enough people or getting too few responses
Representative - data that accurately depicts the population based on the sample
Sampling method - a way that is used to select a sample, how is the sample chosen?
Random sample - the best way to reduce bias when choosing a sample