StatCrunch: Creating Split and Stacked Bar Plots Video Lecture | Statcrunch Tutorials for Beginners - Data & Analytics

In this video, you will learn
to create split and stacked bar
plots using StatCrunch.
The data set I am
using is called Two
Categorical Variables.
This is just a toy data set that
contains two columns of data.
The var1 column
contains 10 values--
the value of B in 4 rows and
the value of A in 6 rows.
The var2 column contains
10 values as well--
the value of C in 6 rows and
the value of D in 4 rows.
Let's begin by creating a
split bar plot-- also known
as a side-by-side bar
plot-- with the data
in the var1 column
classified with the data
in the var2 column.
To do so, under the graph menu
choose bar plot with data.
We are going to select
the var1 column,
and in the group by
box, we'll choose var2.
Click compute.
The resulting bar plot
shows the unique values
of the var1 column, which
are A and B on the x-axis,
and the legend
indicates the frequency
of the pairings of
the var2 columns,
C and D. The C values
are shown in blue
and the D values
are shown in red.
Now, let's adjust our bar
plot to stack the bars.
To do so, under the
options menu, choose edit.
This takes us back to
the original window
where we built our bar plot.
In this window,
StatCrunch allows the user
to customize their bar plots.
In the box labeled
grouping options,
I'm going to change it from
split bars to stack bars.
I'll click compute,
and now you notice
that the red bars are stacked
on top of the blue bars.
Now I want to adjust my bar
plot to show relative frequency,
or percent, on the y-axis.
Back under options
in the type box,
I'm going to change
it to a percent.
Click compute again,
and now you can
see that the graph
shows in percents.
For example, 40% of the data
fell into the A-C pairing.
Lastly, StatCrunch can
also normalize the values
relative to the total
within a category.
This will display a plot
that shows the percentage
breakdown of C and D values
within each of the A and B
categories.
Back under options.
First, in the grouping
options-- to do this,
I need to change it
back to split bars.
And then in the type box,
I'm going to change it
to percent within a category.
I'll click compute.
Now the resulting bar plot
shows that 2/3 or 66.6%
of the A values are paired with
the C values, and 1/3 or 33.3%
are paired with the D values.
The plot also shows a
50-50 split between C and D
pairings for the B values.