Maths Flashcards
What are measures of dispersion?
Descriptive statistics that aim to identify the spread of schools within a set of data
What does standard deviation tell us?
It tells us the average amount each score deviate from the mean score. It can be more useful than the range as all values are taken into account, therefore outliers have less of an effect on the measures of dispersion.
Three types of distribution on a
frequency - x graph
Normal distribution, positively skewed distribution, negatively skewed distribution
What does normal distribution tell us?
Most of the data is in the middle of the range
Mean = median = mode
What does a positively skewed distribution tell us?
Most of the data is at the lower end of the range
Mean > median > mode
What does negatively skewed distribution tell us?
Most of the data is at the higher end of the range
Mean < median < mode
What is inferential testing?
It is used to determine how significant a difference or correlation between variables is. It helps determine whether the results (affect on the DV) is due to variation in the IV or instead due to chance.
What is the most commonly used level of significance?
P < 0.05
Meaning there is less than 5% probability that the results are due to chance factors (95% confident)
What is the highest level of significance and what would it be used for?
P < 0.001
Meaning that is only 1% percent probability that the results are due to a chance factor. There is 99% confidence
Testing drugs
What are the two errors in statistical testing?
Type 1 and type 2
Type 1 error - When the researcher accepts the alternate hypothesis, but the null hypothesis is true (this usually happens when the level of significance is too lenient)
Type 2 error - when the researcher accepts the null hypothesis but the alternate hypothesis is true (this usually happens when the level of significance is too cautious)
TTFN - type two = false negative
How can you remember what the errors in statistical testing?
TTFN - type two = false negative
Wilcoxon Test - Conditions for use
- Ordinal data (must be able to rank from highest to lowest)
- Repeated measures design (same group in both conditions)
- Must be testing for the difference between 2 sets of data
Mann-Whitney U test - conditions for use
- Ordinal data (must be able to rank from highest to lowest)
- Independent groups design (where different people sit each condition)
- Must be testing for the difference between two sets of data
Mann-Whitney U test - conditions for use
- Ordinal data (must be able to rank from highest to lowest)
- Independent groups design (where different people sit each condition)
- Must be testing the difference between two sets of data
Why might somebody use the Wilcoxon test instead of the Mann-Whitney U test?
If the experiment used a repeated measures design
How would you set out an answer for the Wilcoxon test?
The T value of (3.5) is greater than the critical value of (2) when p<0.05 in a one tailed test, therefore the data does not have significance and then no hypothesis must be accepted. This means that…
How do you set out an answer for the Mann-Whitney U test?
The U value of (15) is greater than the critical value of (10) when p<0.05 in a one tailed test, therefore the data does not have any significance and they’re not hypothesis must be accepted. This means…
