Power & statistics + statistics revision presentation

Question 1

Power

Answer 1

The probability of making a correct decision (to reject the null hypothesis) when the null hypothesis is false
The probability that a test of significance will pick up on an effect that is present

Question 2

If results are due to chance…

Answer 2

Then the null hypothesis must be accepted (although there may be a difference in two data set, the difference is too small to be significant and therefore is due to chance)

Question 3

When is the null hypothesis rejected?

Answer 3

The probability that the results are due to chance is less than 5%

Question 4

Measures of central tendency

Answer 4

Mode, median, mean

Question 5

Levels of data

Answer 5

Nominal, ordinal, interval, ratio (lowest to highest)

Question 6

Nominal

Answer 6

Categorial, most non numerical data.

Question 7

Bimodal

Answer 7

When there are two equally frequent responses

Question 8

Ordinal

Answer 8

Ranked data (something is ‘first’ or ‘second’ – when a number does not have a numeric value)
(should use median rather than the mean)

Question 9

Interval

Answer 9

Interval data uses equal units (can use mean and standard deviation)

Question 10

Ratio

Answer 10

Ratio data has an absolute zero (most commonly used + use mean and standard deviation)

Question 11

Dispersion

Answer 11

Tells us how consistent or different the data is (spread of data)

Question 12

Semi-interquartile range

Answer 12

Eliminates all outliers and focuses on the central set of data (eliminates lowest and highest quartile of the data – (Q3-Q1)/2)

Question 13

Standard deviation

Answer 13

The average difference between each data point and the mean

Question 14

Inferential statistics

Answer 14

The concept of significance

Question 15

Errors when calculating the significance

Answer 15

1. Reject null hypothesis but the null hypothesis is true
2. Retain the null hypothesis but the null hypothesis is false

Question 16

Mann Whitney U

Answer 16

Used when you have an independent samples design

Question 17

Wilcoxon signed ranks

Answer 17

Used when you have a repeated measures design

Question 18

T test

Answer 18

High in power, used only if you think your data lacks outliers and does not have a significant skew

Question 19

Anova

Answer 19

Analysis or variance – used to determine whether there are any statistically significant differences between the means or two or more independent groups

Question 20

Conclusion

Answer 20

1. A statement with the p value and what that means for your null hypothesis
2. An explanation of what this means in the context of the IV and DV that was investigated