APA STATISTICS ...................................................................................................................................... 2
Independent samples t-test ......................................................................................................................... 3
Cronbachs alpha - optional ................................................................................................................................ 3
Dependent samples t-test ........................................................................................................................... 5
Cronbachs alpha - optional ................................................................................................................................ 5
One sample t-test ....................................................................................................................................... 6
Cronbachs alpha - optional ................................................................................................................................ 6
One way ANOVA ...................................................................................................................................... 7
Cronbachs alpha - optional ................................................................................................................................ 7
Mean of groups.................................................................................................................................................... 7
Normality violated .............................................................................................................................................. 7
Homogeneity violated ........................................................................................................................................ 7
Overall ANOVA.................................................................................................................................................. 8
Planned contrast - optional ................................................................................................................................ 8
Post hoc – optional ............................................................................................................................................. 9
End note .............................................................................................................................................................. 9
Factorial (two-way) ANOVA.................................................................................................................... 10
Cronbachs alpha - optional .............................................................................................................................. 10
Mean of groups.................................................................................................................................................. 10
If assumptions are violated ............................................................................................................................... 10
Main effects ....................................................................................................................................................... 10
Interaction effect .............................................................................................................................................. 11
Simple effects .................................................................................................................................................... 11
End note ............................................................................................................................................................ 11
Bivariate correlation................................................................................................................................. 12
Cronbachs alpha - optional .............................................................................................................................. 12
Partial correlation .................................................................................................................................... 14
Regression (Linear) .................................................................................................................................. 15
Cronbachs alpha - optional .............................................................................................................................. 15
Chi-square ............................................................................................................................................... 16
Odds ratio .......................................................................................................................................................... 17
,APA STATISTICS
Writing
Do NOT put your answers fully in italic or bold.
Pay attention to italics: p =, r =, M =, SD =, F, etc.
Do not use variable names in the text, use normal language:
• NOT: emoji_happy
• BUT: a review with a happy emoji
Be parsimoniously (spaarzaam) in your answers, only answer what is asked. The
teachers/readers want to look at your answers as fast as possible.
Decimals
Always report everything with TWO decimals Except:
p = 3 decimals (.05) npartical = 3 decimals (.24)
0.01 vs. .01
• If a value can be more than 1 à x.xx (SD length, F, etc.)
• If a value cannot be more than 1à.xx (p, r, α, etc.)
• Thus: if a value can be greater than one, report the zero (0.78)
Mean and Standard deviation
The mean score of the variable was 4.27 (SD = 0.68).
Also reported as (M = 4.27, SD = 0.68) depending on context.
Confidence intervals ALWAYS REPORT IF THEY ARE GIVEN (not always
mentioned in this file)
Report confidence intervals as follows: 95% CI [3.90, 4.25]
Plural: 95% CIs [3.90, 4.25], [-2.43, -4.31], and [3.11, 4.29]
Assumption of Normality – if you do it always report also if not violated
The scores were not normally distributed (z-scoreskewness = 8.61, z-scorekurtosis = -0.71). It would
be
better to bootstrap and base the conclusion about significance on the bootstrapped confidence
interval instead of the p-value, but this is not included in the exam. Therefore, I know that I
have to interpret the p-value with caution.
Assumption of homogeneity – if you do it always report also if not violated
The assumption of homogeneity was met/not met (VR = xx.xx). and hat we look at the ‘equal
variances not assumed’ data in de table if not met (except for the Welch in Anova)
,Independent samples t-test
Cronbachs alpha - optional
xx VAR xx was measured with xx items (‘example question’) on a x-point scale (1 = xxx, 7 =
xxx). The mean of the scale was x.xx (SD = x.xx). and the reliability of the scale was
good/excellent, α = .xx.
a) Data are normally distributed:
To test xxhypothesisxx, an independent-samples t-test is performed. The assumption of
normality was met and the XX was normally distributed (z-score skewness/kurtosis = xx.xx
and xx.xx). *Homogeneity here if needed and that we look at the ‘equal variances not
assumed’ data in de table if not met* (VR = xx.xx). On average, xxvariablexx (M = x.xx, SD
= x.xx) was lower/higher than xxvariablexx (M = x.xx, SD = x.xx). This difference was/was
not significant (Mdif = xx.xx, t(xx) = xx.xx, p = .xxx, 95% CI [x.xx, x.xx]). The difference
represents a small/medium/large-sized effect d = x.xx.
b) Data are not normally distributed:
To test xxhypothesisxx, an independent-samples t-test is performed. The XX score was not
normally distributed (z-score skewness/kurtosis = xx.xx and xx.xx). It would be better to
bootstrap and base the conclusion about significance on the bootstrapped confidence
interval instead of the p-value, but this is not included in the exam. Therefore, I know
that I have to interpret the p-value with caution. *Homogeneity here if needed and that we
look at the ‘equal variances not assumed’ data in de table if not met* (VR = xx.xx). On
average, xxvariablexx (M = xx.xx, SD = xx.xx) was lower/higher than xxvariablesxx (M =
xx.xx, SD = xx.xx,. This difference was/was not significant (Mdif = xx.xx, t(xx) = xx.xx, p =
.xxx, 95% CI [x.xx, x.xx]). The difference represents a small/medium/large-sized effect d =
x.xx.
, Always end with relating your finding to the tested hypothesis:
In general, the data supports/this study supports the hypothesis that there is…
How →
Mdif = xx.xx, t(xx) = xx.xx, p = xxx
Mdif = mean difference, t(df) = t-value, p = Sig. 2-tailed