AP Stats test chapter 4

laws of probability

larger = more info

margin error

set bounds for likely error

sampling variability

natural difference between different samples

under coverage

some of the population can’t participate

non response

some don’t respond

response bias

systemic pattern ex: lying on a survey

wording of questions

strong wording could influence answers

population

group we want info abt

census

collects data from every individual

sample

subset of people that data is collected form (helps make an inference about the population)

sample survey

uses an organized plan to choose a sample that represents a specific population

convenience sample

easy to reach

voluntary response sample

responding to open invite

random sampling

chance process to find sample

simple random sampling (SRS) of size n

every individual in the popualtion has an equal chance of getting chosen

systemic random sample

sampling through intervals

strata-stratafied random sampling

classify population into groups of similar individuals choose a SRS in each stratum combine to form sample

cluster sample

the population is divided into natural groups (called clusters), and then entire clusters are randomly selected. After that, all individuals within the chosen clusters are included in the sample.

matched pairs design

this is an experimental design that has similar subjects/the same subject go thorough treatment and not go through treatment to compare the effect of the treatment. Chance used to decide which unit in the pair receives treatment

randomized block design

experimental design that divides the population into blocks and randomly assigns within the block, finally compares both blocks

placebo effect

When participants in an experiment respond to a treatment simply because they believe they are receiving it, not because the treatment itself has any real effect.

researcher bias

When the expectations or beliefs of the researcher influence the outcome of a study (often unintentionally).

lack of realism

limits our ability to apply the conclusions of an experiment to the settings of greatest interest (Association is not strong or consistent)

statistically significant

an observed effect so large that it would rarely occur by chance can imply causation, range would be set during the planning process

randomized comparative experiment

ability to treat all subjects the same in every way expect for the actual treatments

double blind

neither the subject nor the research/those who interact with them knows who has received treatment

explanatory variable

• The variable that is changed or categorized to explain differences in another variable.

• Think of it as the cause or input.

• Example: In a study of how study time affects test scores, study time is the explanatory variable.

response variable

• Response Variable (Dependent Variable)

  • The variable that is measured to see how it changes based on the explanatory variable.

  • Think of it as the effect or outcome.

  • Example: In the same study, the test score is the response variable.

control group

gets an inactive treatment or baseline treatment

completely randomized design

treatment is assigned to all experimental units by chance