Data Story

ART OF STATISTICAL THINKING

Thinking statistics involves the whole ART of learning from data. Data is a collection of facts – distinct pieces of information (numbers, words etc) with context. Statistical thinking just like every other thing starts with a problem, it’s important to rather say a clearly defined and practical real life problem. download (4)Next, you plan, plan again and after that plan some more – I can’t stress this enough. You can save yourself time, sweat and tears by just planning. Questions to ask: what kind of data is available?, how do I get this data? What methods are appropriate for solving this problem? (start with the simpler ones). Then, go ahead and solve the problem, start with cleaning up your data (I will soon write up a post about this),  explore your data – do plots, graphs, summaries etc (a picture is worth a thousand words), apply appropriate statistical technique/s to answer your question. Finally, interpret and give your practical conclusion in the setting of the real-world problem. When presenting results to a “non-quant” audience try as much as possible to avoid technical jargon. In summary:

  • STEP 1: State your practical question.
  • STEP 2: Plan your attempt to answer the question which includes access to data, methods, and strategies for exploring, organizing and describing data.
  • STEP 3: Answer the question using appropriate techniques.
  • STEP 4: Interpret and present results.
NOTE
If you spot a typo or any error in the post, please let me know in the comment section – so I can fix it.

One thought on “ART OF STATISTICAL THINKING

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s