Collecting Data (Unit 3)

Valid Statistical Question (3.1)

Data that varies & has multiple answers.

Population (3.1)

Entire group of individuals we want info about.

Census (3.1)

Collects data from every individual in the population.

Sample (3.1)

Subset of individuals in the population from which we collect data.

Observational Study (3.1)

Observes individuals, but doesn’t influence responses 

• Used to decide, compare, or examine groups

Experiment (3.1)

Deliberately imposes some treatment & measure responses

• Only option for cause & effect data

Convenience Sample (3.2)

Individuals who are easy to reach

Voluntary Response Sample (3.2)

People choose to be in sample by responding to general invitation (A.K.A. self-selected sample)

Random Sample (3.2)

Chance process used to find members. Best way to sample.

Bias (3.2)

Consistently underestimates or overestimates the value you want to know.

Simple Random Sample (SRS) (3.3)

Of size, n, every group of n individuals has an equal chance to be a sample.

Sampling Variability (3.3)

Different random samples of the same size from the same population produce different estimates.

Margin of Error (3.4)

Describes how far, at most, we expect estimate to vary from the true population value (mean or proportion). 

Margin of Error Equation (3.4)

2 * S.D. ~ Margin of Error (M.O.E.)

Undercoverage (3.5)

When some members of the population are less likely to be chosen or can’t be chosen for the sample.

• Leads to bias when other parts of the population are not taken into account.

Non-Response (3.5)

An individual chosen for the sample can’t be contacted or refuses to participate.

• Leads to bias when those who can’t be contacted or won’t participate would respond differently to those who do participate.

Response Bias (3.5)

A consistent pattern of inaccurate responses to a survey question.

• Leads to a bias as a result of untruthfulness or misunderstandings. 

Response Variable (3.6)

Measures an outcome of a study

Explanatory Variable (3.6)

Helps predict/explain changes in a response variable.

Confounding (3.6)

Two variables are associated in a way that their effects on a response variable cannot be distinguished from each other.

Treatment (3.6)

A specific condition applied to individuals in an experiment.

Experimental Units (3.6)

Smallest collection of individuals to which treatments are randomly assigned.

Subjects (3.6)

Experimental units that are human beings.

Control Group (3.6)

Group used to provide baseline for comparing effects of other treatments.

• Depending on an experiment’s purpose, it may be given an inactive or active treatment.

Placebo Effect (3.6)

Describes that some subjects in an experiment will respond favorably to any treatment, even inactive treatment.

Placebo (3.6)

Treatment with no active ingredient, but is otherwise like other treatments.

Double-Blind Experiment (3.6)

Neither subjects nor those who interact with them & measure the response variable know which treatment a subject received.

Single-Blind Experiment (3.6)

Either subjects don’t know which. treatment they’re receiving or people who interact w/ them & measure the response variable don’t know which subjects are receiving which treatment.