|
Size: 535
Comment:
|
← Revision 10 as of 2014-09-04 11:57:34 ⇥
Size: 520
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 1: | Line 1: |
| The [attachment:prop1sn.xls spreadsheet] gives the power for inputted group proportions (which should sum to 1), Type I error and given power. The expected proportions are assume equal group sizes. | The [[attachment:prop1sn.xls|spreadsheet]] gives the total sample size required for inputted group proportions (which should sum to 1), Type I error and a given power. The expected proportions are assume equal group sizes. |
| Line 5: | Line 5: |
| $$\omega = \sqrt{ \sum_text{1}^text{no. groups} \frac{\mbox{(observed proportion - expected proportion)}^text{2}}{ \mbox{ expected proportion}}}$$ | \omega = Sqrt{ Sum (1 to no. groups) (observed proportion - expected proportion)^2 ^ / expected proportion |
The spreadsheet gives the total sample size required for inputted group proportions (which should sum to 1), Type I error and a given power. The expected proportions are assume equal group sizes.
The expected effect size, $$\omega$$, defined below is from Cohen (1977,1988, Chap 7).
\omega = Sqrt{ Sum (1 to no. groups) (observed proportion - expected proportion)2 / expected proportion
The thresholds 0.1, 0.3, 0.5 correspond to small, medium and large $$\omega$$ effect sizes.