|
Two-Sample Tests for Means dialog box |
|
Use this dialog box to carry hypothesis tests between the difference of two population means based on two independent, or naturally paired random samples. It is recommended you use the t-Test (t-distribution statistics) instead of the z-Test (normal distribution statistics) when the number of items in the samples is small, typically less than 30, or when the population variance is not known.
Refer to Two-Sample Tests for Population Means and to Statistical Inference, Decision Theory and Hypothesis Testing for additional information on this subject.
Input
Specifies the worksheet location of the input data for this operation.
Provides a reference to the extent of the data available in the currently active worksheet. Use this range as a guide for typing valid extents in the Input Range 1 and Input Range 2 boxes.
Type in this box the range of cells containing the data you want to use as input for this command (first set of input samples).
Type in this box the range of cells containing the data you want to use as input for this command (second set of input samples).
Check this box to indicate that the data specified by the Input Range 1 and Input Range 2 boxes is organized in rows as opposed to columns (the default).
Refer to Specifying Input Arguments for additional information on this subject.
 | Input to this operation is converted to a series of conjugated two-samples, which are then considered individually for the test. |
Output
Specifies the worksheet location for placing the results of this operation.
Select this option to place the results of this operation in a new document workbook.
Select this option to place the results of this operation in a new worksheet.
Select this option to place the results of this operation starting at the worksheet location specified in the box to the right of this option.
Refer to Specifying Output Locations for additional information on this subject.
Options
z-Test
Choose this option to carry the test using normal deviates. It is recommended you choose this option when the number of observations in each sample is relatively large, typically 30 or more, or the population variances are known.
t-Test
Choose this option to carry the test using t-deviates. It is recommended you choose this option when the number of observations in each sample is small, typically less than 30, and the population variances are not known.
Type in this box the population variance corresponding to the samples specified by the Input Range 1 box.
Type in this box the population variance corresponding to the samples specified by the Input Range 2 box.
Type in this box the hypothetical difference between the two population means.
Refer to Two-Sample Tests for Population Means for additional information on this subject.
Type in this box the significance level you want to assign to the test.
z-Test Options
Population Variances not Known
Check this box if the population variances are not known, the samples are large enough and you want to carry the test using normal deviates.
Refer to the z-Procedure for Unknown Variance for additional information on this subject.
t-Test Options
Select this option to carry a paired test between two dependent samples.
Refer to the Paired t-Test for additional information on this subject.
Assume Equal Variance (Pooled)
Select this option if you know the population variances to be equal.
| If you have no knowledge of the equality of the population variances, refer to the Two-Sample F-Test for Variances and to the Two-Sample F-Test for Variances dialog box for information on testing the equality of two population variances. |
Assume Unequal Variance (Nonpooled)
Select this option if you know the population variances not to be equal.
| If you have no knowledge of the equality of the population variances, refer to Two-Sample F-Test for Variances and to the Two-Sample F-Test for Variances dialog box for information on testing the equality of two population variances. |
Closes the dialog box and carries out this operation.
Closes the dialog box without carrying out this operation.
Sponsored
Try Predictive Systems Lab
Need Help?
Contact support