stats sampling n bias

what is a population

all units with characteristics of interest, N

what is a census

entire population

what does Inference mean

process of drawing conclusions about a population on the basis of sample data

what is a sampling frame

the list of individuals from which the sample is drawn (individuals you can actually reach)

what is a sample

a partial collection of people drawn from a population (people we actually collect information from)

what is a sampling design

describes exactly how to choose a sample from the population

why do we want a representative sample

characteristics of sample are about the same as the characteristics of the population

how do we achieve a representative sample

• you need a large enough sample size ; - the population size does not matter

what is non-random sampling

• Each subject in the population does not have an equal chance of being selected into the sample ; - often results in an unrepresentative sample

What is random sampling?

everyone in the population has an equal chance of being selected into sample ; - ensures a representative sample

what causes a sampling error

• variability in sample ; - error associated with getting a sample ; - bias

what is bias

systematic error in the way the sample represents the population

what are the directions of bias

sample overestimates or underestimates the quantity of interest compared to the population

what are the sources of bias

1. undercoverage bias ; 2. response bias ; 3. non-response bias

what is undercoverage bias

underrepresenting or excluding an important part of the population

what is response bias

inaccurate responses that favours one side (intentional or unintentional)

what is non-response bias

differences between those who respond and those who don't (voluntary response)