Statistics Paper 2 Flashcards

1
Q

What is nominal data?

A

Categorised data with no ranking/order. Each value will have a name or label

Example: Gender, colours

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

What are strengths and weaknesses of nominal data?

A

S- Simplistic and easy to collect/organise as it involves basic categorisation
W- Does not provide any order and limits the types of statistical analyses that can be performed

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

What is ordinal data?

A

Data that is presented in rank order but does not specify the size of differences between ranks

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

What are strengths and weaknesses of ordinal data?

A

S- Provides order information
W- No quantitative differences so doesn’t indicate differences between ranks

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

What is interval/ratio data?

A

Quantitative measues of difference on a numerical scale
Interval: equal intervals, has no true zero point
Ratio: all properties of interval data with a true zero
Examples of interval- temperature
Examples of ratio-weight, height

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

What are strengths and weaknesses of interval/ratio data?

A

S-Rich statistic analysis
W-Assumption of equal intervals, which may be inaccurate

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

What are measures of central tendency?

A

General term for all calculations in quantitative data to find the mean, median and mode to discover patterns in data

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

What is the mean, mode and median?

A

Mean- the average
Mode-appears most often
Median- in the middle when all values are listed in order

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

What are strengths and weaknesses of using the mean?

A

S- Easy to calculated, includes all values
W- Infuenced by outliers

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

What are strengths and weaknesses of using the median?

A

S-Easily identifiable and less effected by outliers
W- May have lots of numbers to order so is time consuming. Not representative of all values

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

What are strengths and weaknesses of using the mode?

A

S- Easy to calculate
W- There may be multiple modes

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

What is a normal distribution?

A

Symmetrical, bell-shaped distribution where most of the data points cluster around the mean. The mean, median and mode are located at the centre and are equal.

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

What is a positively skewed distribution?

A

Asymmetrical, concentrated on the left. The mean is greater than the median, which is greater than the mode

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

What is a negatively skewed distribution?

A

Asymmetrical, concentrated on the right. The mean is less than the median, which is less than the mode

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

What are measures of dispersion?

A

General term for any measure of a spread of data

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

What is the range and what are its strength/weaknesses?

A

Range- Subtract lowest from highest +1
S- Useful for a quick, basic measure
W- Data may look misleading if there is an anomoly

17
Q

What is standard deviation and what are its strength/weaknesses?

A

SD- How much each score deviates from the mean. The larger the sd, the greater the spread
S- Accurate idea of distribution, representative of groups variation, useful for comparing variability

18
Q

What are inferential statistics?

A

Determining whether results are due to chance. The sign test, probability and significance, type I/II errors

19
Q

What significance level do pyschologists commonly use and why?

A

p<0.05 because it is used when high levels of significance are not needed and allows for the null hypothesis to be 5% or more true to be accepted. The stringent level is 1% used for levels of high confidence like in medical scenarios.

20
Q

What is a parametric test?

A

Making assumptions about the data’s underlying distribution assuming a normal distribution. Assumptions include: distribution, equal variances and data is interval/ratio

21
Q

What are the strengths and weaknesses of a parametric test?

A

S- More powerful than non-parametric when assumptions are met, allows for more detailed inferences about population parameters
W- Not suitable when data does not meet assumptions

22
Q

What is a non-parametric test?

A

Making fewer assumptions about the data’s distribution, can be used with ordinal data.
Assumptions: few or none/ordinal data

23
Q

What are the strengths and weaknesses of a non-parametric test?

A

S- More flexible with fewer assumptions about the data
W- Less powerful than parametric tests, limited in the detail they can provide about population parameters

24
Q

What is the saying for the statistical tests?

A

Carrots Should Come
Mashes With Suede
Under Roast Potatoes

25
Q

What do each of the acronyms in the statistical test mean?

A

Chi^2, Sign Test, Chi^2
Mann Whitney U, Wilcoxon Test, Spearmans Rho
Unrelated t-test, Related t-test, Pearsons Product Moment

26
Q

What are each of the factors it could fit into?

A

Nominal, ordinal or interval data
Difference or correlational
If difference, independent or repeated measures?

27
Q

What are the steps to finding the critical value/calculated value in significance?

A

-Compare test statistic to critical value
-Look at significance levels
-Degrees of freedom/ sample size

28
Q

What is the rule for significance in stats?

A

If the test has an R in it, the calculated value has to be equal or greateRR than the critical value

29
Q

How do you write significance statements?

A
  1. State whether the calculated value is less or more than the critical value
    2.State whether the results are significant
    3.State whether the null is accepted or rejected
    4.Write out the relevant hypothesis
  2. Report the figures in brackets- calculated, critical value, number of participants, report if p was less or more than 0.05, one or two tailed
30
Q

What is a type I error?

A

False positive- The null hypothesis is rejected when it should be accepted

31
Q

What is a type II error?

A

False negative- The null hypothesis is accepted when it should be rejected

32
Q

How do you complete the sign test?

A

1) Convert results to nominal data, add + or - signs on the right
2)Add the + and - up
3) Use the smallest number
4)Look at if it is a one or two tailed study and how many participants there are- correlate this on the critical value chart
5)Find the number- if its less or equal to the calculated value, it is significant