Use Interval Plot to assess and compare confidence intervals of the means of groups. An interval plot shows a 95% confidence interval for the mean of each group. An interval plot works best when the sample size is at least 10 for each group. Usually, the larger the sample size, the smaller and more precise the confidence interval.

For information about data considerations, examples, and interpretation, go to Overview for Interval Plot.

Continuous variables

Enter one or more numeric columns that you want to graph.

Categorical variables (optional)

Enter up to five columns of categorical data that define the groups. The first variable is the outermost on the scale and the last variable is the innermost.

Layout

Choose one of the following layout options.

Separate graphs for each continuous variable
Creates a separate plot for each column in the Continuous variables field.
Overlay continuous variables
Columns in the Continuous variables field are overlaid on a single plot.

By variables

Enter one or more grouping variables in By variables to create a separate plot for each level of the grouping variables. The columns that you enter must be the same length as the columns in Continuous variables and Categorical variables. The y-scales for each variable are the same across the multiple plots.
Show all combinations

When you enter multiple By variables, Minitab enables the Show all combinations checkbox. Select this option to create a separate plot for each combination of groups created by the By variables. If you do not select this option, Minitab creates a plot for each group of each By variable.

For example, the first By variable has 2 groups, Male and Female, and the second By variable has 2 groups, Employed and Unemployed. If you select Show all combinations, Minitab creates 4 separate plots for the combinations of Male/Employed, Male/Unemployed, Female/Employed, and Female/Unemployed. If you do not select Show all combinations, Minitab creates 4 separate plots for Male, Female, Employed, and Unemployed.

Confidence interval

Specify the settings for the confidence interval.

Confidence level
Enter the level of confidence for the confidence interval. Usually, a confidence level of 95% works well. A 95% confidence level indicates that, if you take 100 random samples from the population, the confidence intervals for approximately 95 of the samples will contain the population parameter.
For a given set of data, a lower confidence level produces a narrower confidence interval, and a higher confidence level produces a wider confidence interval. The width of the interval also tends to decrease with larger sample sizes. Therefore, you may want to use a confidence level other than 95%, depending on your sample size.
  • If your sample size is small, a 95% confidence interval may be too wide to be useful. Using a lower confidence level, such as 90%, produces a narrower interval. However, the likelihood that the interval contains the population mean decreases.
  • If your sample size is large, consider using a higher confidence level, such as 99%. With a large sample, a 99% confidence level may still produce a reasonably narrow interval, while also increasing the likelihood that the interval contains the population mean.
Use Bonferroni method
Method for controlling the simultaneous confidence level for an entire set of confidence intervals. It is important to consider the simultaneous confidence level when you examine multiple confidence intervals because your chances that at least one of the confidence intervals does not contain the population parameter is greater for a set of intervals than for any single interval. To counter this higher error rate, the Bonferroni method adjusts the confidence level for each individual interval so that the resulting simultaneous confidence level is equal to the value you specify.
Two-sided
Use a two-sided confidence interval to estimate both likely lower and upper values for the mean.
Upper one-sided
Use a lower confidence bound to estimate a likely lower value for the mean.
Lower one-sided
Use an upper confidence bound to estimate a likely higher value for the mean.
Use pooled standard deviation
Select when you can assume all populations have equal variances.

Y-scale

Select how you want to display the y-scale.

Original units
Use the original units of measure for numeric variables.
Standardized units
Convert different units of measure to a standard unit to make numeric variables comparable.
Same Y-scale
Make the Y-scale the same across multiple graphs.

Variable display order

Minitab uses the terms "innermost" and "outermost" to indicate the relative position of the scales for multiple levels of groups displayed on a graph. For a horizontal scale, outermost refers to the scale at the bottom of the graph, and innermost refers to the scale farthest from the bottom, closest to the horizontal axis. For a vertical scale, outermost refers to the scale to the far left, and innermost refers to the scale closest to the vertical axis.

Choose one of the following options when you have multiple Y variables with groups.

Categorical variables first, Y's below
Graph variables are the outermost groups and the categorical variables are the innermost groups.
Y's first, categorical variables below
Graph variables are the innermost groups and the categorical variables are the outermost groups.