Statistical Testing and Probability Flashcards

1
Q

What is statistical testing

A

It is a method used to see if a hypothesis should be accepted or rejected

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

Why do we use statistical testing (2 reasons)

A

.they work out the probability of whether a particular set of data could have imply occurred by chance
.find a difference between 2 soles but we want to know if the difference is big enough for it be be significant

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

What information do you need to know to determine what statistical test to use

A

3 D’s:
.level of Data (nominal,ordinal or interval)
.type of Design (related or unrelated)
.test if Difference or correlation

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

What experimental designs are ‘related’ designs

A

Repeated measures or matched pairs

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

What experimental designs are ‘unrelated’ designs

A

Independent group or single participant

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

What is the mnemonic for determining which statistical test to use

A

Simon Cowell Wants More Singers Receiving Unanimous Praise

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

What does the mnemonic correspond to for the statistical tests

A

Sign tests, Chi squared, Wilcoxon, Mann whitney, Spearman’s rho, Related T, Unrelated T and Pearsons

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

When do we use the sign test

A

When it is a test of difference and related design and when the data is nominal

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

What is the sign test

A

It is a calculation used to determine whether a difference is statistically significant

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

What is the first step for the sign test

A

Put the pairs of related data into the table (going to be already done for you most times)

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

What is the second step of the sign test

A

Subtract the values in the pair and label it with their + if it is a positive number or a - if it is a negative number

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

What is step 3 of the sign test

A

Count how many - and + there are and the one which has a lower number is the S value

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

What is step 4 of the sign test

A

Compare the calculated value (S) with the critical value

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

What criteria’s do you need to follow to find the critical value from the critical value table

A

.One or two tailed hypothesis?
.How many total participants? (Take away those who have no difference)
.What level of probability are you using?

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

What is a one tailed hypothesis

A

A directional hypothesis

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

What is a two tailed hypothesis

A

non directional hypothesis

17
Q

What level of probability is always used (unless said otherwise in question)

18
Q

What do you use when comparing the S and CV and determining whether the hypothesis is significant

A

The statement below the critical value table

19
Q

What other 2 probability values may be used by psychologists

A

0.1 or 0.01

20
Q

Why is 0.05 the probability level that psychologists work at

A

Because they need to be 95% sure of their research and so that errors are reduced but also so that the data isn’t too strict that it leads to more type 2 error

21
Q

What type of error is more likely to be cause because of 0.1 probability level

22
Q

What type of error is more likely to be cause because of 0.01 probability level

23
Q

What is a type 1 error

A

When the investigator rejects a hypothesis or data but it is actually right (false positive)

24
Q

What is a type 2 error

A

When the investigator thinks a hypothesis or data is true but it is actually false (false negative)

25
What is a null hypothesis
A hypothesis that states that there is no relationship between the 2 variables
26
Do you have to know how to calculate the other stats test other than sign tests
No
27
What do you have to know about the other stats tests
Know when to use them and compare critical and calculated value and state if its significant
28
When do you use wilcoxon
Test of differences, related designs and ordinal data
29
When do we use Mann Whitney
Test of difference, unrelated design and ordinal data
30
When do we use spearman’s rho
Correlation and ordinal data
31
When do we use chi squared
Test of difference, unrelated design and nominal data
32
When to use Pearsons r
Correlation and interval data
33
When to use T tests (related and unrelated)
Test of difference, corresponding design and interval data
34
When is 0.01 probability level used
When the researcher needs to be more confident and eliminate as much chance of uncertainty as possible. Also mainly when there is a human cost such as drug testing, you want to be more careful and be 99.99% sure