Basis of Segmentation in Univariate Analysis of Excel

In the previous lecture, you got glimpses of segmented univariate analysis. Now, let’s go deeper into the segmentation process, which can be divided into four parts:

1. Take raw data

2. Group it by dimensions

3. Summarise using a relevant metric such as mean, median, etc.

4. Compare the aggregated metric across groups/categories

Let's see how Anand explains the segmentation process.

Note: At 2:42, to get the 'Count of Maths%' do the following.

1. Click on the already created pivot table of 'Average of Maths%'.
2. On the right, you will see 'PivotTable Fields', drag and drop the field 'Maths..' to values.
3. Go to values, then click on the drop-down box with label 'Count of Maths..' (Once you drag 'Maths..' field to values, it converts automatically to 'Count of Maths..'), select 'Value Field Settings..' and choose the type of calculation as 'Max'.

To summarise, the standard process of segmented univariate analysis is as follows:

• Take raw data

• Group by dimensions

• Summarise using a relevant metric like mean, median, etc.

• Compare the aggregated metric across groups/categories

With this, you have now performed segmented univariate analysis on a few variables, but what if you have a large number of variables in your data set? How would you go about analysing and explaining the results of hundreds of categorical variables to your client? Let’s see what such a table would look like in the next lecture.