AP Statistics - Unit 4

population

entire group of individuals data is collected about

census

collects data from all individuals in a population

sample

subset of individuals in population from which data is collected

sample survey/choosing a sample

1. define population

2. define what is being measured

   1. decide sample method

convenience sample

choosing individual from population who are easy to reach

convenience sample issues

bias and underrepresentation

voluntary response sample

people who choose themselves by responding to a general invite

voluntary response issues

bias because of overrepresentation of individuals with strong opinions

random sampling

change process to find individuals of population to be in the sample

simple random sampling

every group of n individuals in a population has an equal chance to be selected

stratified random sample

break down population into strata (classifications by similarity) and SRS within each strata

cluster sampling

classify population into groups that are located near each other - all from some

inference

drawing conclusions from larger populations

type of error: under coverage

members of population cannot be chosen in a sample for any reason

type of error: non-response

when an individual chooses not to respond, be contacted, or participate

type of error: response bias

a pattern of incorrect responses

type of error: wording of questions

influences the type of answer

observational study

observes individuals and measures variables of interest; no influence on responses

experiment

deliberately imposes some treatment on individuals to measure their responses

treatment

what is applied in the experiment

1. principle of experimental design

Comparison of two+ treatments

2. principle of experimental design

random assignment

3. principle of experimental design

control and keep variables that might affect response for all groups

4. principle of experimental design

replication: have a larger group to replicate experiments

statistically significant

results have an observed effect so large that it can’t occur by change

blocking

assign treatment groups based on similar characteristics; sample to then create blocks

matched pairs design

compare two treatments on the same subject or two identical subjects; randomized of who gets treatment or order of treatment