Psychology: Inferential statistics

Significant

Unlikely to have arisen by chance

Null hypothesis

there is no relationship between the variables

directional hypothesis

Previous research, one tailed

Non-directional hypothesis

No previous research, two tailed

Falsify

To be able to disprove the theory

Significance level/ P value

p less than or equal to .05

Type 1 error

false positive, rejecting null hypothesis that's true

Type 2 error

false negative, accepting a null hypothesis that's false

Nominal data

Data in categories

Ordinal data

Data ordered but doesn't have equal intervals

Interval data

Data based on numerical scales

Spearman's rho

Correlation, ordinal, related

Pearson's r

Correlation, interval, related, parametric

Chi-Squared

difference or association, nominal, independent groups

Sign test

Difference

Nominal

Related

Mann-Whitney U test

Difference, ordinal data, independent groups

Wilcoxon T test

Difference, ordinal data, repeated measures

Unrelated t-test

Difference, interval data, unrelated design, parametric

Related t-test

Difference, interval, related, parametric

parametric tests

Interval data, normally distributed, homogeneity of variance

observed value

Value calculated from a set of observations

Critical value

Value to be achieved for significance

degrees of freedom

Often number of participants in the study (N), used for parametric tests and chi-squared

One tailed test

directional hypothesis

Two tailed test

non-directional hypothesis

smallest value of either pluses or minuses

Value of s (sign test)

S must be equal to or less than critical value

Chi-squared, Mann whitney U test, Wilcoxon t test