Statistical terminology

Question 1

α (Alpha) definition

Answer 1

Significance of a statistical test.
α (Alpha) is the probability of making a Type 1 error

Question 2

Type 1 error definition

Answer 2

Rejecting the null hypothesis when the null hypothesis is true. I.e. finding a difference when there is none (or it occurs by chance alone)

Question 3

p value

Answer 3

the probability of obtaining the observed values if the null hypothesis is true. P value is compared to the preset alpha value (preset level of significance). Does not confirm that the difference is true, only the probability that the difference has occurred by chance.

Question 4

β (Beta) definition

Answer 4

β (Beta): power of a statistical test.
This is the probability of making a type 2 error.

Question 5

Type 2 error

Answer 5

This is the probability of accepting the null hypothesis when the alternative hypothesis is true i.e. not accepting a difference when there is one.
This is the study power, which is determined by the sample size, effect size and variance.

Question 6

Power definition

Answer 6

Power = 1- β
which equates to the probability of correctly rejecting the null hypothesis (finding a difference when there truly is one). Typically set at 0.8

Question 7

Sample size

Answer 7

the number of subjects required in a study to determine an effect with a predetermined alpha and power value

Question 7

95% confidence interval definition

Answer 7

Describes the values between which there is a 95% chance that the true population value lies. When the confidence intervals for two samples overlap, there is no statistically significant difference.