Complete the following steps if your data are in a column of the worksheet:
From the drop-down list, select One or more samples, each in a column.
Enter the column of data that you want to analyze. The column must contain two distinct values, such as True and False.
If the column is numeric, Minitab uses the higher value to represent the event (also called success). If the column contains text, Minitab uses the word that is second in alphabetical order to represent the event. To change the value Minitab uses as the event, go to Change the display order of text values in Minitab output.
Click in the empty field under the data arrangement list to see the available data columns for your chart.
In this worksheet, Purchase indicates whether a household made a purchase after receiving an advertisement. Because it is second in alphabetical order, Minitab uses Yes as the event.
Complete the following steps if you know the number of events and trials, and do not have actual sample data in the worksheet.
From the drop-down list, select Summarized data.
In Number of events, enter the number of successes. For example, if you want to determine the proportion of defective parts, the number of events would equal the number of defective parts.
In Number of trials, enter the total number of observations. For example, if you want to determine the proportion of defective parts, the number of trials would equal the total number of parts that you sampled.
Perform hypothesis test
If you want to calculate a p-value to determine whether the mean differs from a hypothesized mean, you must perform a hypothesis test.
Use a hypothesis test to determine whether the population proportion (denoted as ρ), differs significantly from the hypothesized value (denoted as ρ0) that you specify. If you don't perform the test, Minitab still displays a confidence interval, which is a range of values that is likely to include the population proportion. For more information, go to What is a hypothesis test?.
The Hypothesized proportion defines your null hypothesis (H0: ρ = ρ0). Think of this value as a target value or a reference value. For example, an analyst enters 0.043 to determine whether the proportion of customers that respond to a direct-mail offer is different from 4.3% (H0: p = 0.043).