All language subtitles for 02 - Identify relationships using XY scatter charts

- [Instructor] One common goal

of performing business data

analysis is to discover relationships between values.

For example, you might own a store and want to determine

whether individuals who come to the store

from farther away are more likely to spend money

once we get there.

If you've collected that data,

you can summarize it visually using what is known

as an XY scatter chart.

In this movie,

I will show you how to create one.

In the exercise files collection,

you will find an Excel workbook called, 20_02_XYScatter.

And that's an Excel workbook

that contains the data that I will use in this movie.

As you can see,

I have two columns of data.

In column A,

I have the distance a customer traveled.

And in column B,

I have the amount that customer spent.

So you can see that in row 2,

a customer that traveled one mile spent $35.

And there was another within one mile who spent $13.

And if we moved down the data set,

which is sorted by distance,

then we can see that it does appear

that the farther away someone started from the store,

that is the more they travel to get there,

the more they're likely to spend.

But let's see what it looks like

in an XY scatter chart.

To create your chart,

click any cell in your data set,

then go to the Insert tab.

And in the Charts group,

click the Insert Scatter (X,Y) or Bubble Chart button.

And then at the top in the Scatter group,

just click the first chart subtype.

When you do,

Excel creates an XY scatter chart.

And you can see that there is a fairly strong relationship

between distance traveled and amount spent.

You can see distance on the horizontal or X axis

and amount spent on the Y or vertical axis.

There is a definite upward trend,

although you can also see

that one individual who traveled 45 miles only spent $35.

But in general,

the farther away someone started from your store,

the more they spend when they get there.

So it's important to remember

that an XY scatter chart only works

if you have two sets of numerical data

that are matched as pairs.

If you have, say,

months of the year,

then an XY scatter chart is probably not your best bet,

because months are categorical data

as opposed to numerical.