Week 7

Question 1

Explanatory Variable:

Answer 1

Variable we think influences another variable.

– Typically we use the label “x”

– Also called independent variable.

Question 2

Response Variable:

Answer 2

Variable that measures the outcome of a study

– Typically we use the label “y”

– Also called dependent variable

Question 3

Observational Study:

Answer 3

Observe differences in explanatory variables and try to determine if there is a difference in the response variable.

Question 4

Experiment:

Answer 4

Impose a difference in the explanatory variables and try to determine if there is a difference in the response variable.

Question 5

Subjects:

Answer 5

The individuals we study. (Also called participants)

-Typically referred to as experimental units if we are not studying humans

Question 6

Treatments:

Answer 6

Specific regimen or procedure assigned to subjects; different levels of an explanatory variable.

Question 7

Lurking (confounding) variables:

Answer 7

Variables that may influence the response but that often are not studied explicitly.

–Observation studies are vulnerable to the presence of these variables.

Question 8

Control:

Answer 8

Absence of treatment; some baseline or reference condition that is used for comparison (i.e. in a comparative experiment)

Question 9

Control group:

Answer 9

A group of subjects that have the same sources of variability as those receiving the treatment; they are similar to those in the treatment group prior to the start of the study and are treated identically to those in the treatment group except that they don’t receivethe active treatment.

Question 10

Placebo:

Answer 10

A fake treatment; something (e.g. a pill, a procedure) which seems like the treatment but is not

Question 11

Single‐blinding:

Answer 11

Someone involved in the experiment (either subjects or researchers) are not aware of which group a subject is assigned to

Question 12

Double‐blinding:

Answer 12

Neither subjects nor researchers aware of which group a subject is assigned to.

Question 13

Completely Randomized Design (CRD):

Answer 13

Each unit is randomly assigned to one treatment. This is the most basic type of experimental design.

Question 14

Matched Pairs Design:

Answer 14

Each unit receives two treatments. The units could be: 1. A single subject (each subject serves as their own control) Ex: Before and after effect of medicine for each subject 2. Two subjects that have been matched together (one receives the treatment and the other receives the control)

Question 15

Block Design:

Answer 15

Units are divided into similar groups called blocks, and each treatment is applied in each block.

Question 16

Blocks:

Answer 16

The groups in a block design; an expected source of variability. We would like to control for differences that will occur in these different groups, but these groups are not our primary interest

Question 17

Advantages of matched and block designs:

Answer 17

They both control for variation in the response that could be caused by the variables that you match or block on.