First- and Second-Order Partial Correlations
For Four Intercorrelated Variables:

This page will calculate the first- and second-order partial correlations for four intercorrelated variables, W, X, Y, and Z.

To proceed, enter the values of rWX , rWY , and so forth, into the designated cells below, then click the «Calculate» button. A negative value of r should be preceded by a minus sign: e.g., -.76. Do not enter a plus sign; all entered values are assumed to be positive unless preceded by "-". Values of r2 will calculated and entered automatically.

If you enter a value of N (providing N>9), the program will also calculate the values of t along with the associated two-tailed probability values. For the original correlations, df=N—2; for the first-order partials, df=N—3; and for the second-order partials, df=N—4.

[Optional]  N = 
Original Correlations
r
r2
t
P
WWX




WY




WZ




XY




XZ




YZ




       
      All P values are non-directional (two-tailed).
1st Order Partial Correlations
r
r2
t
P
WX.Y




WX.Z




WY.X




WY.Z




WZ.X




WZ.Y




XY.W




XY.Z




XZ.W




XZ.Y




YZ.W




YZ.X






2nd Order Partial Correlations
r
r2
t
P
WX.YZ




WY.XZ




WZ.XY




XY.WZ




XZ.WY




YZ.WX









Home Click this link only if you did not arrive here via the VassarStats main page.

©Richard Lowry 2001-
All rights reserved.