1348
Comment:
|
1580
|
Deletions are marked like this. | Additions are marked like this. |
Line 18: | Line 18: |
Cohen's d = $$\frac{\mbox{2t}}{\sqrt{\mbox{df}}} | Cohen's d = $$\frac{\mbox{2t}}{\sqrt{\mbox{df}}} (1) |
Line 24: | Line 24: |
$$\mbox{Cohen's d} = \sqrt{\mbox{2}} \frac{\sqrt{\mbox{F}}}{\sqrt{\mbox{n}}} | $$\mbox{Cohen's d} = \sqrt{\mbox{2}} \frac{\sqrt{\mbox{F}}}{\sqrt{\mbox{n}}} (2) |
Line 28: | Line 28: |
Equation (1) is a special case of (2) since t equals $$\sqrt{F}$$ and df is made equal to 2n. |
|
Line 35: | Line 37: |
__Reference__ | __References__ Abelson, RP and Prentice, DA (1997) Contrast tests of interaction hypotheses. ''Psychological Methods'' '''2(4)''' 315-328. |
How do I convert a t-statistic into an effect size?
One sample t
Since $$\frac{\sqrt{\mbox{n}} \mbox{mean}}{\mbox{sd}}$$ = t
Cohen's d = $$\frac{t}{\sqrt{n}}$$
Two sample t
Rosenthal (1994) states for sample sizes $$\mbox{n}_text{1}$$, $$\mbox{n}_text{2}$$,
Cohen's d = $$\frac{t(\mbox{n}_text{1}+\mbox{n}_text{2})}{\sqrt{\mbox{df}}\sqrt{\mbox{n}_text{1}}\sqrt{\mbox{n}_text{2}} }$$
When $$\mbox{n}_text{1}$$ = $$\mbox{n}_text{2}$$
Cohen's d = $$\frac{\mbox{2t}}{\sqrt{\mbox{df}}} (1)
2 way interaction
Abelson and Prentice (1997) suggest a way of converting a F statistic from a two-way interaction into Cohen's d:
$$\mbox{Cohen's d} = \sqrt{\mbox{2}} \frac{\sqrt{\mbox{F}}}{\sqrt{\mbox{n}}} (2)
where n is the assumed equal number of observations for each combination of the two factors. If these are unequal then we use the [http://en.wikipedia.org/wiki/Harmonic_mean harmonic mean] of the sample sizes.
Equation (1) is a special case of (2) since t equals $$\sqrt{F}$$ and df is made equal to 2n.
Pearson Correlation
Rosenthal (1994) also gives a conversion formula to turn a t-statistic into a correlation
Correlation = $$\sqrt{\frac{\mbox{t}text{2}}{\mbox{t}text{2} + \mbox{df}}$$
References
Abelson, RP and Prentice, DA (1997) Contrast tests of interaction hypotheses. Psychological Methods 2(4) 315-328.
Rosenthal, R. (1994) Parametric measures of effect size. In H. Cooper and L.V. Hedges (Eds.). The handbook of research synthesis. New York: Russell Sage Foundation.