Key Terms in Statistics: Sampling, Experiments, and Study Design

Voluntary Response Sample

Consists of people who choose themselves by responding to a general appeal.

Confounding Variable

In an observational study, provides an alternative explanation for the observed relationship between explanatory and response variables, reducing the possibility of concluding a causal relationship.

Statistics

Provides ways to answer specific questions from data with some guarantee that the answers are good ones.

Population

The entire group of individuals that we want information about.

Sample

A part of the population that we actually examine in order to gather information.

Convenience Sample

Chooses the individuals easiest to reach.

Simple Random Sample (SRS)

A sample of size n chosen so that every possible set of n individuals has an equal chance to be selected.

Probability Sample

Gives each member of the population a known chance greater than zero of being selected.

Strata

The division of the population into groups of similar individuals.

Stratified Sampling

Samples important groups within the population separately, then combines the samples.

Stratified Random Sample

Chooses a separate SRS in each stratum and combines the SRSs to form the full sample.

Multistage Sample

Selects successively smaller groups within the population in stages; each stage may use an SRS, stratified sample, or another sampling method.

Undercoverage

Occurs when some groups in the population are left out of the process of choosing the sample.

Nonresponse

Occurs when an individual chosen for the sample cannot be contacted or refuses to cooperate.

Wording of Questions

Can have the most influence on the answers given to a survey.

Sampling Frame

The list of individuals from which a sample is actually selected.

Bias

The design of a study that systematically favors certain outcomes.

Sampling Design

The method used to choose the sample from the population.

Observational Study

Observes individuals and measures variables of interest but does not attempt to influence the responses.

Experiment

A study in which a researcher assigns conditions or treatments to experimental units to explore an investigative question about a population.

Experimental Units

The individuals on which an experiment is performed.

Subjects

Experimental units that are human beings.

Treatment

A specific experimental condition applied to the experimental units.

Factors

The explanatory variables in an experiment.

Placebo

A dummy treatment that can have no physical effect.

Control Group

The group of subjects that receives a sham treatment.

Random Assignment

The use of chance to divide experimental units into groups.

Completely Randomized Design

All experimental units are allocated at random among all treatments.

Statistically Significant

An observed effect too large to attribute plausibly to chance.

Probability Model

A model used to calculate a theoretical answer.

Simulation

The imitation of chance behavior based on a model that accurately reflects the experiment under consideration.

Replication

Repeats each treatment on a large enough number of experimental units or subjects to allow systematic treatment effects to be seen.

Double-Blind Experiment

Neither the subjects nor the people who have contact with them know which treatment a subject received.

Lack of Realism

The subjects, treatments, or setting of an experiment may not realistically duplicate the conditions we actually want to study.

Block

A group of experimental units or subjects that are similar in ways expected to affect the response to treatments.

Randomized Block Design

Random assignment of experimental units to treatments is carried out separately within each block.

Matched Pairs Design

A common form of blocking used for comparing two treatments.

Survey

An observational study in which data are collected from humans using a standard set of questions.

Response Variable

An outcome measured on each experimental unit after the treatment has been administered.

Census

Consists of recording information from all items or individuals in a population.

Random Sample

Each member of the population is equally likely to be included.

Systematic Sample

The first member of the sample is chosen randomly, and the remaining members are chosen according to a well-defined pattern.

Representative Sample

A sample in which subgroups appear in approximately the same proportions as they do in the population.

Cluster Sample

The population is divided into clusters; entire clusters are randomly selected, and all members of the selected clusters are included.

Quota Sample

A nonrandom sample designed to match individual characteristics to known characteristics of the population.

Lurking Variable

A variable that affects the outcomes of a study but whose influence was not part of the investigation.

Control

Attempts to anticipate confounding variables in advance and control for them.

Holding Variables Constant

A researcher keeps variables not under study constant so they do not influence the outcomes.

Completely Randomized Design

Uses random allocation of subjects to treatment and control groups, administers treatments, and compares outcomes.

Double-Blind Design

Neither subjects nor those recording or evaluating responses know which treatment each subject receives, helping control for the placebo effect and researcher bias.

Block Design

The experimenter divides participants into similar subgroups called blocks and randomly assigns treatments within each block.

Matched Pairs Design

A special case of randomized block design for two treatments in which participants are grouped into similar pairs and randomly assigned to different treatments.

Randomized Pairs Comparison Design

Another name for a matched pairs design.

Sampling With Replacement

Each selected member is returned to the population before the next member is selected.