17.3.3.1 The Pair-Sample T-Test Dialog Box


Contents

Supporting Information

To open the Pair-Sample t-Test dialog box:


More information:

Recalculate

Recalculate

Controls recalculation of analysis results

  • None
  • Auto
  • Manual

For more information, see: Recalculating Analysis Results

Input

Pair-Sample t-Test supports Raw and Summarized Data two input data form.

Raw Enter column with range format. Each column contains response data from a level of factor variable.

For help with range controls, see: Specifying Your Input Data

  • 1st Data Range
The first sample column.
  • 2nd Data Range
The second sample column.
Summarized Data Enter value of mean difference, pooled standard deviation and sample size data for sample(s), in the form as "mean SD Sample Size" (space separated numbers)
You can calculate the mean difference by:
\[\bar{d}=\frac{1}{N}\sum_{i=1}^N d_i\]
Calculate the SD by:
\[s_d=\sqrt{\frac{1}{N-1}\sum_{i=1}^N(d_i-\bar{d})}\]
Sample Size
\(d_i\) is \(x_{1i}-x_{2i},for(i=1,2,...,N)\,\!\).


t-Test for Mean

Test Mean The hypothetical mean difference to be tested (usually 0).
Null Hypothesis The null hypothesis to be tested (usually Mean1 - Mean2 = 0).
Alternate Hypothesis Options:

Mean1-Mean2 <> Test Mean

Perform a two-tailed paired-sample t-test: Is the mean difference between the two datasets more or less than the hypothetical mean difference?

Mean1-Mean2 > Test Mean

Perform an upper-tailed paired-sample t-test: Is the mean difference greater than the hypothetical mean difference?

Mean1-Mean2 < Test Mean

Perform a lower-tailed paired-sample t-test: Is the mean difference less than the hypothetical mean difference?
Significance Level The significance level of the test.
Effect Size Calculate Cohen's d value to show the effect size which is the magnitude of the difference between actual mean1-mean2 and Test Mean.
Confidence Interval(s) Compute a confidence interval for the mean.

For computation details, see Algorithms: Paired Sample t-Test.

Confidence Level(s) in % Specify space-separated confidence levels, (1-\(\sigma\))%. Available when Confidence Interval(s) is selected.

Power Analysis

Unset Minimal Difference of Interest

Difference(s) for Specified Power When Minimal Difference of Interest is not set, this option is available.

Output the differences for the specified power levels. When this option is selected, the specified power levels setting will affect the power level in power curve.

Power Level(s) When check the Difference(s) for Specified Power option, you can enter the power levels separated by space in this edit box. Default power levels are 60%, 70%, 80% and 90%.

Set Minimal Difference of Interest

Minimal Difference of Interest Specify the minimum difference from the test mean you are interested in. Once you enter a value in this box, the Power Analysis graph will show the minimum sample size to detect this difference in the different powers.
Sample Size(s) for Specified Power When check the Minimal Difference of Interest option, this option is available.

Output the Sample Sizes for the specified power levels. When this option is selected, the specified power levels setting will affect the power level in power curve. If it is selected, it will use the default power levels.

Power Level(s) When check the Sample Size(s) for Specified Power option, you can enter the target power levels separated by space in this edit box. Default power levels are 60%, 70%, 80% and 90%.
Power Based on Test Data When specify the Minimal Difference of Interest, this option is available.

Compute the power for the sample size of the test data. (the probability of rejecting the null hypothesis when it is false).

Hypothetical Power When specify the Minimal Difference of Interest, this option is available.

Compute the power of the test at various sample sizes. When check this option, it will add corresponding curve to power curve.

Hypothetical Sample Size(s) When specify the Minimal Difference of Interest and Hypothetical Power is checked, this option is available.

Specify hypothetical sample size(s) for power computation.

Plots

Plot for Differences Check this box to plot the box chart and histogram for mean differences.
Probability Plot Plot a probability plot.
Box Chart Plot a box chart.

Note: When outlier(s) detected in the datasets, a footnote will show under the Box chart to note you to review their case. If you want to exclude the outliers, you can click the triangle button at the end of the footnote to mark outliers and recalculate.

Histogram Plot a histogram.
Arrange Plots of Same Type in One Graph Note that for histograms, the layers will be arranged vertically. For box charts, layers will be arranged horizontally. This box will be hidden if you chose Plot For Differences box.
Note: When input data form is Summarized Data, it will not output above plots.

Output

For help with the range controls, see: Output Results

Results Log Output

Select to output results to the Results Log.

Graphical Summary Report Create a summary graph report, including P value bar, effect size bar and difference distribution graph. The result tables will also been attached to the graph to show the statistical values.

The footnote after the summary graph will diagnose these statistical results.

Graphical Power Analysis Report Create a graphical power analysis report with power curve(s). The output table and power curves are according to the setting in the Power Analysis tab.
  • If no value has been set for Minimal Difference of Interest editbox, only the power curve of current sample size will be output; and the power at 60%, 70%, 80% and 90% (default value) will be tagged to show the difference at these power values.
  • If a difference value has been set for Minimal Difference of Interest editbox, the power curves will be output: power curves at around 60%, 70%, 80% and 90% (default value) and current sample size; and the sample size to detect the minimal difference will be listed.

A footnote will be added after the power curve graph to show you the diagnosis results of power analysis. A power value of 80% is usually considered sufficient.

Output Plot Data Specify a worksheet for output of plotted data (Origin generates tabular data when plots are created).
Output Results Specify the worksheet for output of test results.


Note:
  • When input data form is Summarized Data, Graphical Summary report will not be output.
  • When input data form is Raw, Masked Data and Bad Data(missing value) table will be in the report sheet.