Experimental and Sampling Design Flashcards

Flashcards containing key statistical vocabulary terms and definitions regarding experimental design principles and sampling design methods.

Observational Study

A study where outcomes are observed without imposing any treatment on the subjects.

Experiment

A study where a treatment is actively imposed on units in order to observe the response.

Experimental Unit

The single individual (person, animal, plant, etc.) to which different treatments are assigned.

Factor

The explanatory variable in an experiment.

Level

A specific value assigned to a factor.

Response Variable

The variable that is measured in an experiment or study.

Treatment

A specific experimental condition applied to experimental units.

Control Group

A group used to compare the factor against; can receive a placebo or the current/old item.

Placebo

A dummy treatment that can have no physical effect.

Blinding

A method used so that experimental units do not know which treatment they are receiving.

Double Blind

An experimental setup where neither the experimental units nor the evaluator know which treatment a subject received.

Completely Randomized Design

An experimental design in which all experimental units are allocated at random among all treatment groups.

Randomized Block Design

An experimental design where units are grouped into homogeneous blocks on a variable that affects the response and then randomly assigned to treatments.

Matched Pairs Design

A special type of block design where units are paired according to similar characteristics and assigned to treatments, or where each individual unit performs both treatments in a random order.

Confounding Variable

An unaccounted-for variable that affects the response, often resulting from an experimenter mistake.

Bias

A systematic error in measuring an estimate that favors certain outcomes.

Population

The entire group of individuals about whom information is desired.

Census

A complete count of an entire population.

Sample

A part of the population that is actually examined in order to gather information and generalize to the population.

Sampling Design

The method used to choose a sample from a population.

Sampling Frame

A list of every individual in the population.

Simple Random Sample (SRS)

A sample consisting of $n$ individuals chosen such that every individual and every set of $n$ individuals has an equal chance of being selected.

Stratified Random Sample

A sample produced by dividing the population into homogeneous groups called strata and taking Simple Random Samples (SRSs) from each stratum.

Systematic Random Sample

A sampling method where individuals are selected following a systematic approach after randomly choosing a starting point.

Cluster Sample

A sampling method based on location where locations are randomly selected and all individuals at those locations are sampled.

Voluntary Response Bias

Bias resulting from self-selection, occurring when people choose whether to respond, typically attracting individuals with strong opinions.

Convenience Sampling

A sampling method that asks individuals who are easy to reach, producing biased results.

Undercoverage

A source of bias that occurs when some groups of the population are left out of the sampling process.

Nonresponse Bias

Bias that occurs when an individual chosen for the sample cannot be contacted or refuses to cooperate.

Response Bias

Bias that occurs when the behavior of the respondent or interviewer causes incorrect or inaccurate answers.