Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Statistics > Research Skills > Flashcards

Research Skills Flashcards

1
Q

What is a true experimental design

A

Pre test/post test control group designs ensures that groups are indeed comparable before the experimental manipulation is administered

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

What is a Solomon four group design

A

Ensures that groups are indeed comparable before the experimental manipulation was administered AND that protesting hasn’t affected performance

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

What is a confounding variable

A

Variable other than our IV that could have caused the group means to be different
Statistically related/correlated to the IV

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

What is a between group design

A

Independent measures

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

What is a within groups design

A

Repeated measures

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

What are some disadvantages of experimental methods

A

Experimenter effects
Participants know they’re being watched
Can be fairly low in external validity (generalisability)
Not everything can be examined in a lab setting either

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

What is a quasi experimental design

A

Similar to experimental designs but lacks random assignment
Sometimes there’s no control group either
It’s more naturalistic but less control
High in external low in internal

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

What is one group post test design in quasi experimental design

A

Meaning there’s no pre test so it ain’t really the best design

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

What is a one group pre test post test designs in quasi experimental design

A

No control group to compare to

Can tell us about improvements or worsening though

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

What is an interrupted time series design in quasi experimental design

A

Only one sample from when you take measurements from on at least 3 different occasions before and after treatment

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

What is a non equivalent control groups (necg) design in quasi experimental design

A

Structured like normal (pre test post test) but lacks random assignment therefore hard to compare

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

Define participants attrition

A

Participant drop outs

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

What is a cross sectional design

A

Collect data at one time point from participants in different conditions such as age cohorts

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

What is a sequential design

A

Select samples from a particular condition eg specific age cohort such as 18 year olds but study them at different centuries

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

Define internal validity

A

The extent to which you can make a cause and effect statement

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Define selection threat

A

Meaning there’s no random assignment so there may be pre existing differences between your groups that could impact your IV

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Define maturation effect

A

Changes in people as the result of passing of time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Define testing effects

A

Umbrella term for practice effects and fatigue effects

Also Hawthorne effect

19
Q

Define history effect

A

Any changes in the world outside that affect one group but not the other

20
Q

Define statistical regression towards the mean

A

Only a problem if you’re looking at extreme scorers (outliers)

21
Q

Define instrumental effects

A

Any changes in instruments used in your test

Even changes in people such as interviewer changes

22
Q

Define compensatory rivalry

A

Problem with between groups where control group are jealous of experimental group

23
Q

Define external validity

A

Extent to which your findings can be generalised

24
Q

Define multiple treatment interference

A

Difficulty with repeated measures - effect you see when people are exposed to a series of treatments

25
Q

Define interaction of selection and treatment

A

Occurs when you’re looking at a unique sample so unique you can’t generalise behind them

26
Q

Define reactive arrangements

A

Behaviours you see in this artificial setting may not be the same in the real world

27
Q

Define interaction of testing and treatment

A

Occurs in pre test post test design

Coz of pre test your participants reaction to treatment may be different

28
Q

What is the sign for the null hypothesis

A

M1 = m2

29
Q

What is the sign for the alternative hypothesis

A

M1 =/ m2

This is wah we test with inferential statistics

30
Q

What is another term for a significance value

A

Alpha level

31
Q

What is a type 1 error

A

Reject the null hypothesis when it is in fact true
Eg you make an error in accepting the experimental hypothesis but your finding is due to chance
Reduce this error by using more stringent significance levels

32
Q

What is a type 2 error

A

When we accept the null hypothesis when it was in fact false
Eg researcher failed to pick up on a significant result but there was actually one
This error is not under the control of the researcher
Prevent this by ensuring hypothesis is strong enough to see a difference
Large sample size helps in overcoming this error

33
Q

How do you work out a z score value

A

SD

X MINUS MEAN DIVIDED BY STANDARD DEVIATION

34
Q

What is the equation for SE

A

STANDARD DEVIATION DIVIDED BY SQUARE ROOT OF N

Standard error is typically smaller than the population SD

35
Q

In probability what is the and rule

A

When you want the probability of two or more things happening you multiply their probabilities together
Events must be independent of the other

36
Q

What is the or rule in probability

A

If you want one outcome or another outcome then you’ll add their probabilities together
Events must be mutually exclusive, they must not be able to happen at the same time as each other

37
Q

What is another term for the normal distribution

A

Gaussian distribution

38
Q

What is the same value in a normal distribution

A

Mean median and mode

39
Q

Define kurtosis

A

Describe the shape of the distribution

40
Q

What are some assumptions of non parametric tests

A

Skewed data
Make no or few assumptions about the shape of distribution
Often used with small samples

41
Q

Where is the mass of the distribution concentrated in a negative (left skew)

A

To the right of the figure

Mean and median are smaller than the mode in this case

42
Q

Where is the mass of distribution of data focused on in a positive skew (right skew)

A

Left of figure

In this case mean and median are larger than the mode

43
Q

How do you work out a significance skewness value

A

Skewness value/SE of skewness
A value equal to or greater than 1.96 indicates a significant skew
If it is significantly skewed use a non parametric test

44
Q

What are some assumptions of when to use a Mann Whitney test

A

Skewed
Ranks
Group sizes differ considerably

Statistics (1 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions