Two Variances: Power Calculation Parameters - Quick Tab

Select the Quick tab of the Two Variances: Power Calculation Parameters dialog box to access options to establish the basic parameters for analyzing power for the F-test on two variances.

Fixed Parameters

The entries in the boxes under Fixed Parameters establish the fixed, or baseline, parameters for subsequent power calculations and graphs. Parameters that are not varied explicitly as the dependent (X-axis) variables in a graphical analysis will be set equal to these values.

Var1

In the Var1 box, enter the population variance assumed to hold in the first population being tested. Alternatively, if a 1 is entered in the Var2 field, it can stand for the ratio of the two variances.

Var2.  In the Var2 box, enter the population variance assumed to hold in the second population being tested. Keep in mind that the power of this test depends only on the ratio of the two variances, rather than the specific value of either one. So alternatively, enter 1 (the default value) in this field, and enter the assumed ratio of the two variances in the Var1 field.

Df1

In the Df1 box, enter the number of degrees of freedom for the first group in the analysis. If the hypothesis test is based on a single group, this value is N - 1. However, the single variance test can be based on more than one independent sample being used to estimate the same population variance.  In that case, the degrees of freedom are N_tot - J, where N_tot is the total of all the sample sizes, and J is the number of groups in the set of samples.

Df2

In the Df2 box, enter the number of degrees of freedom for the second group in the analysis.  

Alpha

In the Alpha box, enter the type I error rate (α) used in determining the critical value for the F-statistic.

Type of Hypothesis

Use the option buttons under Type of Hypothesis to determine the type of null hypothesis tested by the F-statistic.

2-tailed (Var1 = Var2)

Select the 2-tailed (Var1 = Var2) option button to use the null and alternative hypotheses of the form

H₀: σ₁² = σ₂²    H₁: σ₁² ¹s₂²

1-tailed (Var1 <= Var2)

Select the 1-tailed (Var1 <= Var2) option button to use the null and alternative hypotheses of the form

H₀: σ₁² ≤ σ₂²    H₁: σ₁² > σ₂²

1-tailed (Var1 >= Var2)

Select the 1-tailed (Var1 >= Var2) option button to use the null and alternative hypotheses of the form

H₀: σ₁² ³ s₂²    H₁: σ₁² < s₂²