Dr. Nancy Pfenning

April 2002

After starting MINITAB, you'll see a **Session window** above
and a **worksheet **below. The Session window displays
non-graphical output such as tables of statistics and character
graphs. A worksheet is where we enter, name, view, and edit data. At
any point, the session or worksheet window (whichever is currently
active) may be printed by clicking on the print icon (third from left
at top of screen) and clicking on **OK**.

The menu bar across the top contains the main menus: File, Edit, Manip, Calc, Stat, Graph, Editor, Window, and Help. Beneath the menu bar is the Toolbar which provides shortcuts for several important actions.

In the instructions that follow, text to be typed will be underlined. Menu instructions will be set in boldface type with the entries separated by pointers.

Each data set is stored in a **column**, designated by a
"C" followed by a number. For example, C1 stands for Column
1. The column designations are displayed along the top of the
worksheet. The numbers at the left of the worksheet represent
positions within a column and are referred to as **rows**. Each
rectangle occurring at the intersection of a column and a row is
called a **cell**. It can hold one observation.

The **active cell** has the worksheet cursor inside it and a
dark rectangle around it. To enter or change an observation in a
cell, we first make the cell active and then type the value.

Directly below each column label in the worksheet is a cell optionally used for naming the column. To name the column, we click on this cell and type the desired name.

**Example A**: Suppose we want to store heights, in inches, of
female recitation members [64, 65, 61, 70, 65, 66, ...] into column C1
and name the column ‘FHTS'. Just click in the name cell for this
column, type __FHTS__, and press the "Enter" key. Then
type __64__, Enter, __65__, Enter, __61__, Enter, and so
on.

**Example B**: To store male heights, name column C2
"MHTS" and enter those data values in this column.

**Example C:** For sample size, mean, median, 5% trimmed mean,
standard deviation, minimum, maximum, and quartiles of female height
data,

- Choose
**Stat>Basic Statistics>Display Descriptive Statistics**... - Specify FHTS in the
**Variables**text box (instead of typing it directly, you may double-click on FHTS in the box on the left) - Click
**OK**

For histogram(**D**), stemplot(**E**), and boxplot(**F**)
of female height data,

**Example D:**

- Choose
**Graph>Histogram**... - Specify FHTS in the
**X**text box for**Graph 1** - Click
**OK**

**Example E**:

- Choose
**Graph>Stem-and-Leaf**... - Specify FHTS in the
**Variables**text box - Click
**OK**

**Example F:**

- Choose
**Graph>Boxplot**... - Specify FHTS in the
**Y**text box for**Graph 1** - Click
**OK**

**Example G**: To combine and sort female and male recitation members'
heights,

- Choose
**Manip>Stack>Stack Columns** - Specify FHTS and MHTS with a space between them as columns to be stacked.
Click the
**Column of current worksheet**button and type HTS in this box (Click**OK**) - Choose
**Manip>Sort** - Specify HTS as column to be sorted, specify SORTEDHTS in the
**Store sorted columns in:**box, and HTS in the**Sort by column**box - Click
**OK**

** Example H** Suppose all heights were entered in a single column
HTS, and genders (M or F) were entered in the column SEX. To compare heights
of students in the two gender groups,

- Choose
**Manip>Unstack** - Specify HTS for "Unstack the data in" and SEX for "Using subscripts in". By default, the unstacked columns HTS_M and HTS_F will be stored in a new worksheet.
- Click
**OK** - Obtain desired descriptive statistics and displays for the various groups.

- Choose
**Graph>Boxplot** - Specify HTS as the measurement variable Y and SEX as the categorical variable X.
- Click
**OK**

Now suppose heights of males and females have been unstacked into two columns HTS_M and HTS_F. To produce side-by-side boxplots of male and female heights,

- Choose
**Stat>Basic Statistics>2-Sample t**. - Select
**Samples in different columns**. Specify HTS_M as the First column and HTS_F as the Second column. - Click on the
**Graphs...**box. - Check the box for boxplots of data.
- Click
**OK** - Click
**OK**

For more than two side-by-side boxplots when the data are unstacked, see the ANOVA example.

**Example J** We can use MINITAB to take a random sample of, say,
10 heights from those in a data column.

- Choose
**Calc>Random Data>Sample From Columns** - Type
__10__in the box to specify how many rows, and after "from column(s)" type__HTS__. - After "Store samples in:" type the name of an empty column, such as
__C25__. Do not check the "sample with replacement" box. - Click
**OK**

Note: for independent samples (such as for two-sample t or ANOVA),
perform the above steps twice. To sample pairs of values (such as for
paired t or regression), two columns ** of equal length **
can be specified (eg. MOMAGE and DADAGE)
and then two empty columns must be specified for storage.

**Example K**: We can also use MINITAB to randomly select 5 from 100
names in a hard-copy list. Assume the names are listed alphabetically, where
the first name corresponds to the number 1 and the last corresponds to the
number 100.

- Choose
**Calc>Make Patterned Data>Simple Set of Numbers...** - Type
__NUMBERS__in the**Store Patterned Data**text box - Click in the
**From first value**text box and type__1__ - Click in the
**To last value**text box and type__100__ - Click
**OK** - Choose
**Calc>Random Data>Sample From Columns...** - Type
__5__in the small text box after**Sample** - Click in the
**Sample...rows from columns**text box and specify NUMBERS - Click in the
**Store sample in**text box and type SAMPLE - Click
**OK**

Note: Confidence intervals are automatically provided in the output for a hypothesis test, but it will not be the standard confidence interval unless the two-sided alternative has been selected.

**Example L: ** Assume heights (in inches) of female recitation
members to be a random sample taken from heights of all female college
students, whose mean height is unknown [actually, it is about 65] and
standard deviation is 2.5. Use sample heights to obtain a 90%
confidence interval for population mean height.

- Choose
**Stat>Basic Statistics>1-Sample Z...** - Specify FHTS in the
**Variables**text box - Select the
**Confidence interval**option button - Click in the
**Level**text box and type__90__ - Click in the
**Sigma**text box and type__2.5__ - Click
**OK**

**Example M**: Assume heights (in inches) of male recitation
members to be a random sample taken from heights of all male college
students, whose mean **and** standard deviation are unknown. Use
sample heights to obtain a 99% confidence interval for population mean
height.

- Choose
**Stat>Basic Statistics>1-Sample t...** - Specify MHTS in the
**Variables**text box - Select the
**Confidence interval**option button - Click in the
**Level**text box and type__99__ - Click
**OK**

**Example N**: Test the null hypothesis that heights (in inches)
of female recitation members are a random sample taken from a
population with mean 65 against the alternative that the mean is
different from 65. Assume population standard deviation to be
2.5. [If population standard deviation were **not** assumed to be
known, a **1-Sample t** test would be used, and **Sigma** would not
be specified.]

- Choose
**Stat>Basic Statistics>1-Sample Z...** - Specify FHTS in the
**Variables**text box - Select the
**Test mean**option button - Click in the
**Test mean**text box and type__65__ - Click the arrow button at the right of the
**Alternative**drop-down list box and select**not equal to** - Click in the
**Sigma**text box and type__2.5__ - Click
**OK**

**Example O**: Do sons tend to be taller than their fathers?
Test the null hypothesis that the difference: (heights of male
recitation members minus heights of their fathers) is zero vs. the
alternative that the difference is positive. First enter male
recitation members' heights in a column ‘SONS' and their
corresponding fathers' heights in a column ‘FATHERS'.

- Choose
**Stat>Basic Statistics>Paired t...** - Click in the
**First Sample**text box and specify SONS - Click in the
**Second Sample**text box and specify FATHERS - Click in the
**Options**button - Click in the
**Test Mean**text box and type__0__ - Click the arrow button at the right of the
**Alternative**drop-down list box and select**greater than** - Click
**OK** - Click
**OK**

**Example P**: Use MINITAB to verify that female heights are
significantly less than male heights. Procedure may or may not be pooled.

- Choose
**Stat>Basic Statistics>2-Sample t...** - Select the
**Samples in different columns**option button - Click in the
**First**text box and specify FHTS - Click in the
**Second**text box and specify MHTS - Click the arrow button at the right of the
**Alternative**drop-down list box and select**less than** - If sample standard deviations are close and you have reason to assume
equal population variances, you may select the
**Assume equal variances**check box, which carries out a pooled procedure. Otherwise, unselect it. - Click
**OK**

**Example Q**: Use MINITAB to examine the relationship between
heights of male recitation members and heights of their fathers; after
verifying the linearity of the scatterplot, find the correlation
**r** and the regression equation; produce a fitted line plot. Produce a
list of residual, a
histogram of residuals and a plot of residuals vs. the explanatory variable
(FATHERS). Obtain a confidence interval for
the mean height of all sons of 70-inch-tall fathers and a prediction
interval for an individual son of a 70-inch-tall father.

- Choose
**Graph>Plot** - Specify SONS in the
**Y**text box for**Graph 1** - Click in the
**X**text box for**Graph 1**and specify FATHERS - Click
**OK** - Choose
**Stat>Basic Statistics>Correlation...** - Specify FATHERS and SONS in the
**Variables**text box - Click
**OK.** - Choose
**Stat>Regression>Fitted Line Plot...** - Specify SONS in the
**Response**text box - Click in the
**Predictors**text box and specify FATHERS - Click
**OK.** - Choose
**Stat>Regression>Regression...** - Specify SONS in the
**Response**text box - Click in the
**Predictors**text box and specify FATHERS - Click on the
**Results...**box - Select
**In addition, the full table of fits and residuals** - Click
**OK.** - Click on the
**Graphs...**box - Check the
**Histogram of residuals**box - In the
**Residuals versus the variables**box, specify FATHERS - Click
**OK.** - Click
**OK.** - Choose
**Stat>Regression>Regression...** - Specify SONS in the
**Response**text box - Click in the
**Predictors**text box and specify FATHERS - Click in the
**Options...**button - Click in the
**Prediction intervals for new observations**text box and type__70__ - Click in the
**Confidence level**text box and type__95__ - Click
**OK** - Click
**OK.**

**Example R: **Use MINITAB to see if there is a significant
difference in mean heights of freshmen, sophomores, juniors, and
seniors in the class. Include side-by-side boxplots to display the data.

- First unstack heights according to year (see Example H).
- Choose
**Stat>ANOVA>Oneway (Unstacked)**... - Specify HTS_1, HTS_2, HTS_3, HTS_4 in the
**Responses**text box. - Click on the
**Graphs...**box - Check the box for
**Boxplots of data** - Click
**OK.** - Click
**OK**.

You may also compare mean responses of stacked data by specifying
HTS in the Response box and YEAR as the Factor variable, using
**Stat>ANOVA>Oneway...**.

**Example S:** Use MINITAB to do inference about the population
proportion of males/females. [The following only works for categorical
variables like SEX that have just 2 possibilities.]

- Choose
**Stat>Basic Statistics>1Proportion...** - Specify SEX for
**Samples in columns** - Click on
**Options**to test a proportion other than the default, .5, or to specify a one-sided alternative. - Click
**OK**.

**Example T: ** Use MINITAB to do inference about the population
proportion preferring a certain color. These steps may be followed if the
variable of interest has more than 2 possibilities.

- Choose
**Stat>Tables>Tally** - Specify COLOR in the
**Variables**box. - Click
**OK**. - Note the count in the color of interest (successes) and the total count N (trials).
- Choose
**Stat>Basic Statistics>1Proportion** - Activate the
**Summarized data**button. - Specify the numbers of trials and successes.
- Click on
**Options**to test a proportion other than the default, .5, or to specify a one-sided alternative. - Click
**OK**.

**Example U: ** Use MINITAB to check for a relationship between
gender and year at Pitt.

- Choose
**Stat>Tables>Cross Tabulation** - Specify SEX and YEAR as the classification variables.
- Check the
**Chi-Square analysis**box. - Click
**OK**.