Friday, June 28, 2013

Exploring Data - 1: Descriptive statistics using Excel

Excel might be one of the easiest way to get familiar with the raw data. Lets consider the US household income by state data set from here for 2009.

Before we start the tutorial make sure Analysis toolpack excel add-in is enabled. You can check it by File > Options > Add-ins.

Now make sure the data we need is in Excel file. Go to Data  >  Data Analysis.

As you click on Data Analysis you will get various options like below, select option "Descriptive statistics".

Enter details in the popup windows which includes input range (say column you want apply descriptive statistics) and selecting check box of Summary statistics. Simple way to select column is click on first cell in column and press "Ctr + Shift + Down arrow key". By default the output will be posted in new sheet but if you want you can have it in same sheet or new workbook as well. You can also find Kth smallest or largest element here.

Now click on OK and you will get descriptive statistics details about the variable (column) you have selected as below.

Note: This is NOT useful when you have huge amount of data. The variable "huge" depends on both your machine configuration and excel limitations.

No comments:

Post a Comment