Hands-On Machine Learning with Microsoft Excel by Julio Cesar Rodriguez Martino

Author:Julio Cesar Rodriguez Martino [Julio Cesar Rodriguez Martino]
Language: eng
Format: epub
Tags: COM018000 - COMPUTERS / Data Processing, COM089000 - COMPUTERS / Data Visualization, COM004000 - COMPUTERS / Intelligence (AI) and Semantics
Publisher: Packt
Published: 2019-04-30T17:00:11+00:00

Studying the Spearman's correlation

To calculate the Spearman's coefficient, we need to first rank the values of each variable, that is, the order of the values when we sort them from highest to lowest. Once we have the new table, we will calculate Pearson's ρ on it.

In a new sheet, we define the following formula in a cell:

=RANK.AVG(Data!A2;auto_mpg[mpg])

Here, we are asking Excel to write in that cell the ranking corresponding to the first cell of the mpg column in our data table, taking into account the full range of the column. We copy the formula to the cells on the right until we complete the number of columns of the data table (8 columns). It doesn't matter if you copy the formula to an extra cell – you will just get an error message since you are out of the data table range. In a similar way, we can copy the formulas to the remaining rows until we get to row 399 (the vertical range of the data table). We can even add a title to the new columns by using the following formula:

=CONCAT("Rank_";auto_mpg[[#Headers];[mpg]])

Then, we copy it to all the cells in the first row.

A sample of the table that we obtain is as follows:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.