Q-Q Plot to check the distribution of a random variable.

Akshay Choulwar
Sep 2, 2018 · 2 min read

In my previous article we have seen the what is gaussian distribution and it’s significance.I will recommend you to please check my article on gaussian distribution here .

If we have a data , then how should I check whether the given data is normally/gaussian distributed or not. After all it is always easy to interpret or find the observations from the data which is gaussian distributed.

So let’s go step by step and we will take the dataset of iris flowers and will check any one of the feature is gaussian distributed or not.Before going directly on example let’s understand the Q-Q Plot.

Quantile-Quantile Plot:

It is a technique to find out the distribution of a dataset but remember we can check any distribution from this technique.

To check the certain distribution of data X then we have to take another Y dataset which has distribution which we want to test.Now, in second step sort the X observattions and also Y observations and find out each percentile for both the observations and plot the Q-Q plot.

Quantile-Quantile Plot for measurements.

Here we can observe that for the given measurements which are uniformly distributed but we are checking it against normal distribution that is why plot between it’s quantiles are not straight hence given measurements distribution does not follows a Normal Distribution.

This Q-Q Plot also has a limitations if the given dataset has a less observations the it will not perform well in that case we have to apply other statistical tests.

I hope you liked my this post and please follow me on twitter for updates of new articles .

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade