Stats

Extraneous Variables

Variables other than the explanatory variable that may affect the response variable.

Confounding Variable

An extraneous variable associated with both the explanatory and response variables, making cause-and-effect difficult to determine.

Random Sampling

Using a chance process to determine which members of a population are selected for a sample.

Simple Random Sample (SRS)

A sample where every possible group of n individuals has an equal chance of being selected.

Choosing an SRS with a Random Number Generator

Label every member, randomly generate the needed labels, then select the corresponding individuals.

Strata

Groups within a population whose members share characteristics related to the response variable.

Stratified Random Sample

Divide the population into strata, take an SRS from each stratum, and combine the samples.

Clusters

Groups of population members located near each other.

Cluster Random Sample

Randomly select entire clusters and include every individual in the selected clusters.

Systematic Random Sample

Randomly choose a starting point, then select every kth individual after it.

Components of an Investigative Question

Identify the variables, population/parameters, and type of conclusion or inference that can be made.

Control Group

A group that provides a baseline for comparing the effects of other treatments.

Placebo

A treatment with no active ingredient that otherwise resembles the real treatment.

Placebo Effect

When subjects respond to a treatment simply because they believe they are receiving treatment.

Double-Blind Experiment

Neither the subjects nor the people measuring the response know which treatment subjects receive.

Single-Blind Experiment

Either the subjects OR the people measuring responses do not know which treatment subjects receive.

Random Assignment

Using chance to assign experimental units to treatments.

Purpose of Random Assignment

Creates roughly equivalent treatment groups and allows cause-and-effect conclusions.

Bias

A study design is biased when its method systematically tends to overestimate or underestimate a population value.

Convenience Sample

A sample made up of population members who are easiest to reach.

Voluntary Response Sample

A sample of people who choose themselves to participate by responding to an invitation.

Undercoverage

Some members of the population are less likely or unable to be selected.

Nonresponse

A selected individual cannot be contacted or refuses to participate.

Response Bias

Survey responses systematically differ from the truth in the same direction.

Completely Randomized Design

Experimental units are assigned to treatments completely at random.

Matched Pairs Design

Similar units are paired and treatments randomly assigned within pairs, or each unit receives both treatments in random order.

Replication

Assigning multiple experimental units to each treatment.

Scope of Inference: Generalizing to a Larger Population

Results can be generalized to a population when subjects were randomly sampled from that population.

Scope of Inference: Cause-and-Effect

Cause-and-effect conclusions are possible when treatments are randomly assigned and the difference is statistically significant.

Direct Control

Keeping extraneous variables the same for all experimental units.

Block

A group of experimental units known before the experiment to be similar in a way related to the response.

Blocking Variable

The variable used to separate experimental units into blocks.

Randomized Block Design

Divide units into blocks, then randomly assign treatments separately within each block.

Marginal Relative Frequency

The proportion with a specific value of one categorical variable, ignoring the other variable.

Joint Relative Frequency

The proportion with a specific value for BOTH categorical variables.

Conditional Relative Frequency

The proportion with a specific value of one variable among individuals sharing a specified value of another variable.