Experimental Design Flashcards

0
Q

Stratified sample

A

Group homogeneous groups then take a random sample from each group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
1
Q

Simple random sample

A

Randomly pick from everyone (need a list of everyone)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Cluster sample

A

Group by location then randomly select some locations and use everyone in that location

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Systematic sample

A

Pick a random place to start and sample every 4th person after that
(Don’t need sampling frame)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Completely randomized

A

Randomly assign treatments to experimental units

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Blocked design

A

Group experimental units into homogeneous groups them randomly treatments in each group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Matched pairs

A

Group two like experimental units together an have one do one treatment and one do the other
Have one do two treatments compare the results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Difference between experimental design and observational study

A

Experimental design you do something to the units and observation you don’t

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Increasing sampling size

A

Decreases variation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Randomization reduces

A

Bias, but it does not eliminate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Stratification reduces

A

Variation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is a confounding variable

A

Something that will effect results of experiment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Booking is a type of experimental design, it happens

A

Before you assign treatments

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Having more then one treatment group does not mean the experiment is

A

Blocked

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

The principles of design

A

Control randomization replication

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Placebo

A

Fake treatment (does nothing

16
Q

Blinding is when

A

Experimental unit doesn’t know

17
Q

Double blind is when

A

Experimenter and experiment unit do not now

18
Q

Well designed experiment only shows

A

Cause and effect

19
Q

Observational study and correlation does not

A

Show cause and effect

20
Q

In simple random sample

A

Every sample has same chance of being poked

21
Q

Types of bias

A
Voluntary response 
Non response 
Under Coverage
Convenience sampling 
Response bias
22
Q

What is an experimental unit

A

The single individual to which the treatments are assigned

23
Q

What is a factor

A

It is the explanatory variable

24
Q

What is a level

A

It is a specific value for the factor

25
Q

What is the response variable

A

It is what you measure

26
Q

Statistical advantage of stratified random over simple random is

A

It reduces variation

27
Q

The use of an extraneous variable to control the placebo effect is (important or not important in the design of the experiment)

A

Not important