t test - one sample in Excel using the QI Macros

When to Use the t Test One Sample

A t test using one sample compares test data to a specific value. It helps determine if the sample is greater than, less than or equal to the value. Consider the following example.

Light Bulb Life - t Test Example

Watch this t Test One Sample in Excel Video

Let's say you want to know if the life of a light bulb is greater than 2,500 hours. So we develop a null hypothesis (H₀) that light bulb life is less than or equal to 2,500 hours and the alternate hypothesis (H_a) that bulb life is greater than 2,500 hours:

• H₀ <= 2,500 hours
• H_a > 2,500 hours

Now, conduct a test of light bulb life and enter the data into Excel:

Then, select the data with the mouse and click on the QI Macros Menu to select the one sample t test:

The QI Macros will prompt for a confidence level (default = 0.95) and test mean/average (in this case 2500):

The t test one sample macro will perform the calculations and interpret the results for you:

Note that cell A8 is 2364 hours, which is less than the target, but the average is 2837.

Interpreting the t test one sample results

Since the null hypothesis is that bulb life is less than or equal to 2500, this is a one-sided test. Therefore, use the one-tail values for your analysis.

Note: The two-sided values would apply if our null hypothesis was that:
H₀: mean = 2500 hours.)

Since the t statistic > t critical (4.904 > 1.76131) and p value < a ( 0.000116 < 0.05) , we can reject the null hypothesis that bulb life is less than or equal to 2500.

We can say that we are 95% confident that the bulb life is greater than 2,500 hours.

Customer Service- t test One Sample Example

Let's say you want to know if wait times in a branch bank are not greater than three minutes at a 95% confidence level:

• H₀ <= 3 minutes
• H_a > 3 minutes

Mystery shoppers routinely visit the branch and collect their wait time. This gives us the data we need to test the hypothesis:

The one-sided p value < a (.039776 is less than 0.05 (1-0.95)), so we must reject the null hypothesis that bank wait times are less than or equal to 3 minutes.

We can say that we are 95% confident that wait times are greater than 3 minutes.

Watch this t Test One Sample in Excel Video

The t test one sample test is just one of the tests included in the QI Macros Statistical Process Control software. Other tests include:

• t test two sample assuming equal variances
• t test two sample assuming unequal variances
• f test
• ANOVA - Analysis of Variance
• Overvew of all hypothesis tests in Excel

Download the FREE 30-day Evaluation copy of the QI Macros Excel SPC Software for Six Sigma