Brainscape's Knowledge GenomeTM

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


See full index

A-level Psychology > RM - Statistical tests > Flashcards

RM - Statistical tests Flashcards

1
Q

What are the 2 types of statistics?

A

Descriptive statistics and inferential statistics.

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

What are inferential tests used by scientists to work out?

A

The probabilities of certain results so we can decide whether to accept or reject a null hypothesis.

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

What are the types of tests divided into?

A

Parametric and non-parametric tests.

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

Which are preferred, parametric or non-parametric tests and why?

A

Parametric because they are more powerful.

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

What is nominal data?

A

Discrete categories.

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

What is ordinal data?

A

Discrete categories in order.

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

What is interval data?

A

Subdivided categories.

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

What is ratio data?

A

No categories.

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

What is a table of critical values?

A

The table in which you check your results.

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

What type of hypothesis would you use a one-tailed test for?

A

A directional hypothesis.

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

What type of hypothesis would you use a two-tailed test for?

A

A non-directional hypothesis.

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

What is a level of significance?

A

% confidence in result validity (=/<0.05).

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

What does N stand for in stats tests?

A

Number of ppts.

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

What are degrees of freedom?

A

Number of values that can change (Df).

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

What are type-one errors?

A

False positive.

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

What are type-two errors?

A

False negative (nothing happened but really something did happen).

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

What are levels of measurement (N/O/I/R)?

A

Types of data.

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

What are the levels of measurement?

A

Nominal
Ordinal
Interval
Ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What are the criteria for parametric tests?

A
  • The level of measurement is interval or better.
  • The data are drawn from a population that has a normal distribution.
  • The variances of the two samples are not significantly different.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What does the level of measurement have to be for a parametric test to be used?

A

It has to be interval or better.

Are the intervals between the data truly equal interval?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What does the distribution of the data have to be for a parametric test to be used?

A

The data are drawn from a population that has a normal distribution.

22
Q

What do the variances of the two samples have to be like for a parametric test to be used?

A

The variances of the two samples are not significantly different.

23
Q

What does it mean that the data has to be drawn from a population that has a normal distribution as a criteria for parametric tests?

A

It is not the sample that must be normally distributed but the population.

A normal distribution is when most items cluster around the mean with an equal number of items above and below the mean.

24
Q

What does it mean that the variances of the two samples are not significantly different as a criteria for parametric tests?

A

The variance is a measure of how spread out a set of data is around the mean.

It is the square of the standard deviation.

25
Q

How do you decide whether the criteria for parametric test of level of measurement being interval or better is met?

A

Are the data in categories (nominal) or ordered in some way (ordinal) = non-parametric statistics.

Are the intervals between the data truly equal interval = parametric statistics.

26
Q

How do you decide whether the criteria for parametric test of the data being drawn from a population that has a normal distribution is met?

A

We expect many physical and psychological characteristics to be normally distributed, such as height, shoe sizes, IQ and friendliness.

Therefore you can justify the use of a parametric test by saying that the characteristic measured us assumed to be normal.

You could also check the distribution of scores to see if they are skewed or not.

27
Q

How do you decide whether the criteria for parametric test of the variances of the two samples are not significantly different is met?

A

In the case of repeated measures (related samples) any difference in the variances should not distort the result (Coolican, 1996).

For independent groups you can check the variances. The variance of one sample should not be more than four times the variance of the other.

28
Q

What do parametric tests make calculations using?

A

The mean and standard deviation of a data set.

29
Q

What do non-parametric tests make calculations using?

A

Ranked data.

30
Q

Why are parametric tests more ‘powerful’ than non-parametric tests?

A

Parametric statistical tests make calculations using the mean and standard deviation of a data set, whereas non-parametric tests use ranked data, thus losing some of the detail.

31
Q

What can parametric tests do that non-parametric tests can’t?

A

The end result is that parametric tests can detect significance in some situation where non-parametric tests can’t.

32
Q

How many values for N are there in studies using an independent groups design?

A

2 as there is one for each group of ppts.

NA and NB.

33
Q

How can you tell whether a test is significant?

A

It is stated underneath each table.

Also, if there is an R (in the name of the test for example), then the calculated value should be greater than the critical value (e.g. for Spearman’s, Pearson’s, Chi-squared and related and unrelated t-test). If there is no R (e.g. sign test, Mann-Whitney and Wilcoxon), then the calculate value should be no less than the critical value.

34
Q

Calculated value

A

The value of a test statistic calculated for a particular data set.

35
Q

Critical value

A

In a statistical test the value of the test statistic that must be reached to show significance.

36
Q

Degrees of freedom

A

The number of values that are free to vary given that the overall total values are known.

37
Q

Levels of measurement

A

Refers to the different ways of measuring items or psychological variables; the lower levels are less precise.

38
Q

One-tailed test

A

Form of test used with a directional hypothesis.

39
Q

Significance

A

A statistical term indicating that the research findings are sufficiently strong to enable a researcher to reject the null hypothesis under test and accept the research hypothesis.

40
Q

Statistical test

A

Procedures for drawing logical conclusions (inferences) about the population from which samples are drawn.

41
Q

Test statistic

A

The name given to the value calculated using a statistical test. For each test this value has a specific name such as S for the sign test.

42
Q

Two-tailed test

A

Form of test used with a non-directional hypothesis.

43
Q

What are the non-parametric tests of difference?

A

Wilcoxon test for related designs.

Mann-Whitney test for unrelated designs.

44
Q

What is the non-parametric test of difference for related designs?

A

Wilcoxon test.

45
Q

What is the non-parametric test of difference for unrelated designs?

A

Mann-Whitney test.

46
Q

What are the parametric tests of difference?

A

Related T-test.

Unrelated T-test.

47
Q

What is the parametric test of difference for related designs?

A

Related T-test.

48
Q

What is the parametric test of difference for unrelated designs?

A

Unrelated T-test.

49
Q

What is the non-parametric test of correlation?

A

Spearman’s Rho.

50
Q

What is the parametric test of correlation?

A

Pearson’s R.

51
Q

What test can be used for both finding a difference and a finding a correlation?

A

Chi-squared test.

A-level Psychology (55 decks)

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