Sample types

Basics

Possible errors

Experiment/Study

Things in a Experiment/Study

Choosing individuals who are easiest to reach results from

Convenience sample

the entire group of individuals about which we want information

Population

Sets bounds on the size of the likely error

Margin of Error

When individuals are observed but the variable of interest is not influenced.

Observational Study

A condition applied to individuals in an experiment

Treatment

People who choose themselves by responding to a general appeal

Voluntary Response Sample

The part of the population from which we collect information: draw conclusions about the entire populations

Sample

When some groups in the population are left out of the process of choosing the sample

Undercoverage

Imposes a treatment on individuals and their responses to treatments are recorded

Experiment

The individuals to which the treatments are applied

Experimental Units

Of size n consists of n individuals from population chosen in such a way that every set of n individuals has an equal chance to be in the sample selected

Simple Random Sample

a representative sample from a large and varied population

Sample survey

When an individual chosen for the sample can’t be contacted/refuses to participate

Nonresponse

Assigns experimental units to the treatments strictly by chance

Completely Randomized design

Can be an inactive treatment group, an active treatment group, or a group that receives no treatment

Control Group

Classify the population into groups of similar individuals (strata), then choose a separate SRS in each stratum and combine these SRS’s to form the full sample

Stratified Random Sample

Systematically favoring certain outcomes

Bias

When an individual gives the wrong response

Response bias

Blocking is used first to separate experimental units into groups based on some characteristics and then we proceed to randomly assign experimental units’ treatment within each block separately

Randomized Block Design

A group of individuals, that are known before the experiment, to be similar in some way

Block

Divide the population into smaller groups. Clusters should mirror the characteristics of the population. Then choose and SRS of the clusters.

Cluster sample

Drawing a conclusion about a population from what we know about the sample

Inference

When some subjects respond favorably to any treatment, even a placebo

Placebo effect

A common type of block design used when we want to compare 2 treatments

Matched-pair design

Both the subject and the person measuring the response are unaware of what treatment was assigned

Double Blind

Edit |
Print |
Download |
Share

JeopardyLabs