AP STATS Unit 3 Test: VOCAB

census

collects data from every individual in a population, and is often very difficult to do

simple random sampling (SRS)

every group of size n has the same change of being selected (not just every individual having the same chance)

stratified (random) sampling

researcher breaks the population into groups/strata that are different, then takes an SRS from each group/strata that only represents that strata (age, race, income, row at a T. Swift concert, etc.).

cluster sampling

the pop. is already broken into groups that are similar, so researcher can randomly select one group/cluster and just take all the data from one group/cluster, and it should represent all groups (seminar rooms, 11th grade SAT test rooms in the same building, etc.)

systematic (random) sampling

every nth member is included (for ex., every 10th person in line)

what are some sources of bias?

convenience sample, voluntary response, non-response, undercoverage, response bias

convenience sample

including individuals that are easy to sample, at the expense of randomness

voluntary response

everyone is invited to respond, but only those who respond are counted (usually have a stronger opinion on the topic, etc.)

non-response

specific people are chosen for the survey, but some choose not to respond (ex. you’re selected and called by a marketing company, and you can choose whether you pick up the phone)

undercoverage

some members of the population cannot be chosen or are less likely to be chosen (ex. NHS does a survey on attendance policy by randomly sampling from students in the building on senior skip day, and they miss a group of students that might differ significantly in their opinion on attendance from those that attend on senior skip day)

response bias

pattern of inaccurate responses from wording of question, lying, interviewer, etc. (ex. question wording bias: knowing that nicotine vapes are addictive and may include chemicals that lead to cancer, are you in favor of or against legislation that requires public schools to educate students on vaping?)

observational study

No treatments are imposed. Since potential confounding variables aren’t controlled, causation cannot be determined.

strata

subdivision of population

sampling error/variability

our random sample will rarely or never perfectly represent a population because of the natural occurrence of variability in a random sample

What are the two types of observational study?

retrospective study = subjects are selected and then their past behavior is recorded

prospective study = subjects are selected and then collect data as events unfold in the future

experiment

Treatments are imposed. Through proper design and control, causation can be determined. Simply, it’s defined as people that are randomly chosen to do/take something.

experimental units

anything being experimented on (people usually called subjects/participants)

explanatory variable

the variable (x-axis) used to predict outcomes - a variable that’s changed, or observed to see its effect on another variable

factors

in an experiment, the variables that are manipulated (the same as the explanatory variable)

levels

the values the factors can take on in an experiment

treatments

the combos of levels of the factors - applied to the subjects in the experiment

response variable

the observed outcomes (y-axis) 

confounding variable

a variable that we didn’t control for that affects results. In observational studies, out textbook calls these variables we missed “lurking variables”.

What are the 4 basic principles of experimental design?

1) Comparison

2) Random Assignment

3) Control

4) Replication

blocking

an optional step in an experiment where similar individuals are grouped together, and then all treatments are randomly assigned within the groups (could block by gender, age, similar GPA’s, or even the special case of Matched Pairs like twins).

What are the three types of experimental design?

completely randomized, randomized block, and matched pairs

completely randomized design

basic type of experimental design, where subjects are randomly assigned to treatments. Can have multiple factors.

randomized block design

Divide subjects into subgroups (blocks) by a common characteristic (genger, age, etc.), and then randomly assign treatments inside each block

matched pairs design

a special type of Blocked Design where subjects can be naturally paired into blocks of 2, and are each randomly assigned one of two treatments (one twin gets the diet pill, the other twin gets the placebo; or two students with similar GPA’s, one uses a textbook and one an ebook). A person can be paired with themselves and receive both treatments.