If you are reading this post, you are either of the following.
-
Someone who is facing difficulties in interpreting the data. -
Someone who wants to improve the data interpretation/reading skills
In this post, I will give you 2 important tips which will change the way you approach any type of data. This will definitely help you in interpreting data like a pro.
“Our problems are not with the data itself, but arise from our interpretation of the data” – Bruce. H. Lipton
1. Perspective/Hypothesis
The importance of having a perspective before looking at the data is a bit under-rated in the real world. When I started my career in market research back in 2011, not having a perspective before looking at the data was one of my biggest mistakes. I used to get so lost in the data that I would forget what I was really looking for. I see this challenge with many new professionals in the industry which is why I am sharing my learnings over a period of time.
Now, as a first step before jumping into a data ask yourself what you are really looking for or what you are expecting the data to tell you?
For Example – You are about to look at the monthly car sales data and see if the trend is increasing/decreasing. Now, before jumping into the data you should have a perspective/view on the trend beforehand as well. Suppose, you have a view that the car sales would be declining because the economy is in bad shape.
Now with this perspective when you look at the data, you would immediately get your answer.
- If the data shows that the car sales are declining – you’ve successfully understood that data.
- But, supposing the data shows that car sales are increasing against your perspective. You will find a feeling on inquisitiveness inside you to find the underlying reason for this.
As a result, you will automatically start looking for answers and deep dive further.
This is just a simple example to explain the power of perspective before reading the data. This is applicable to any data you want to read.
2. Data Type
Many times we do the mistake of reading qualitative data quantitatively and vice versa. It is important to have clarity in the back of your mind whether you are looking at quantitative data or qualitative data. For the purpose of this post, I’m not going into details about these data types as these are wide topics to cover.
Knowing the data types reduces the chances of misinterpretation of the data.
For Example – Qualitative data can tell you exhaustively what are the various car segments available in the market. But, only Quantitative data will be able to tell you the size and growth of each of these segments.
When you are analyzing the Quantitative data, the concept of the Significance test plays a very important role. For example, the size of the hatchback segment in two independent populations comes out to be 25% to 26% respectively. Now, this may look like 1% more in 1 data set than other but it is not statistically significant to be able to confidently say that.
Similarly, in Qualitative data, if a particular segment size of the car seems bigger than others it only gives a hypothesis and not a conclusive picture.
These are small examples to explain how these data sets can be misinterpreted.
Following the above 2 points will definitely improve your data analyzing skills. these are also the 2 big mistakes that I did when I started my career and hence, wanted to share my learnings for the benefit of everyone.
If you found my post useful then do share it with your friends and colleagues. If you have any feedback/questions, you may leave a comment below. I will definitely reply.