Statscraft 0.15.0, release v0.15.0
POWER PARTIALCORR
Power or sample size of a test of one partial correlation against a hypothesized value.
Syntax
POWER PARTIALCORR /PARAMETERS [TEST=NONDIRECTIONAL | DIRECTIONAL] [SIGNIFICANCE=0.05]
PARTIALOUT=k N=n | POWER=powers [NULL=0] ALTERNATIVE=r
[/PLOT [N[(low high)]] [PARTIALOUT] [NULL] [ALTERNATIVE] [DIFF]
[N_XAXIS[(low high)] DIFF_YAXIS] [N_YAXIS[(low high)] DIFF_XAXIS]
[NULL_XAXIS ALTERNATIVE_YAXIS] [NULL_YAXIS ALTERNATIVE_XAXIS] [VROTATE(10)] [HROTATE(325)]].
Needs no data. As POWER PEARSON ONESAMPLE with the bias adjustment, for the correlation of two
variables with PARTIALOUT others (a whole number, 0 or more) held fixed: each of them costs one
degree of freedom, so the standard error of z is 1 / sqrt(N - 3 - k) and N must exceed k + 3.
PLOT adds PARTIALOUT, power over the number held fixed (from 0 to N - 4).
Example
POWER PARTIALCORR /PARAMETERS PARTIALOUT=4 ALTERNATIVE=0.3 NULL=0.05 N=120
/PLOT PARTIALOUT N_XAXIS DIFF_YAXIS.
statscraft help POWER PARTIALCORR prints the same text in the terminal. All commands