1/14
Vocabulary flashcards detailing key formulas, terminology, design principles, and concepts related to independent and paired-samples t-tests.
Between-subjects design
An experimental research design where each participant is assigned to only one condition or group and provides a single score.
Independent samples t-test
A statistical hypothesis test used to determine whether the difference between the means of two separate, unrelated groups is unlikely to have arisen by chance.
Mean (xˉ)
A measure of central tendency calculated by summing all individual scores in a sample and dividing by the total number of observations: xˉ=N∑i=1Nxi.
Sum of squares
The total obtained by subtracting the group mean from each individual raw score, squaring each resulting deviation score, and summing them up: ∑i=1N(xi−xˉ)2.
Sample variance (s2)
A measure of data dispersion calculated by dividing the sum of squared differences from the mean by N−1: s2=N−1∑i=1N(xi−xˉ)2.
Pooled standard deviation (sp)
A combined measure of spread that weights together the variances of both groups into a single value, defined for equal group sizes as: sp=2sgroup12+sgroup22.
Independent t-statistic (equal group sizes formula)
The test statistic calculated as the difference between two sample means divided by the pooled standard deviation scaled by sample size: t=spN2xˉ1−xˉ2.
Core logic of the t-test
A ratio comparing the observed difference between group means against the overall variability or spread of the scores.
Degrees of freedom (df)
The number of independent pieces of information that go into estimating a statistical parameter.
Degrees of freedom for an independent samples t-test
Calculated as df=(N1+N2)−2, where two degrees of freedom are lost because two sample means are calculated to estimate variance.
Degrees of freedom for a paired samples (dependent) t-test
Calculated as df=N−1, where one degree of freedom is lost because only one mean difference (xˉdiff) is estimated.
Standard error of the difference (SEdiff) in a paired t-test
The standard deviation of difference scores divided by the square root of the total number of participants: SEdiff=Nsdiff.
Stress induction procedure (Dr Andreas Jarvstad study)
An experimental manipulation where participants are instructed to recount a traumatic event in great detail to elicit a stressed psychological state.
Relaxed state induction procedure (Dr Andreas Jarvstad study)
An experimental manipulation where participants are instructed to recount a pleasant but not exciting event to establish a baseline relaxed state.
Levene's Test for Equality of Variances
An inferential statistical test reported in SPSS output to verify whether the assumption of equal population variances between two independent groups is met.