Stop 05 · Data Analysis for Business AnalystsTopics · 1/10

Data Analysis Fundamentals for BAs

In short

'I feel customers hate the new checkout' starts an argument. 'Checkout drop-offs went from 20% to 35% after the change' ends one. Basic data skills make your recommendations hard to ignore.

Using data to validate assumptions, measure impact, and support recommendations — a BA doesn't need to be a data scientist, but comfort with basic analysis dramatically strengthens the credibility of their work.

The purple blob stands at a chai stall making tally marks in a notebook beside rows of tea cups.

Think of it like this

The chai stall owner who counted

A chai stall owner was sure evenings were his busiest time. For one week he made a tally mark for every cup sold. Mornings beat evenings easily. He moved his best helper to the morning shift. Same stall, better decision, just from counting.

Watch it happen

How a BA answers a question with data

Question

Get data

Clean

Analyse

1/5Start with a specific question: 'Did the new checkout increase drop-offs?' Not 'look at the data'.

The big ideas

What you need to know

Question first

Every analysis starts with a decision someone needs to make. Without it you'll drown in numbers that don't matter.

Compare to something

A number alone means little. Compare it to last month, another city or a target to see if it's good or bad.

Correlation isn't cause

Two numbers rising together doesn't mean one causes the other. Look for other explanations before claiming a cause.

So what?

End every analysis with what it means and what to do. Stakeholders want a recommendation, not a spreadsheet.

Save yourself the pain

Common mistakes

Oops

Opening the data and 'seeing what turns up'.

Do this instead

Write the question and what answer would change the decision before opening any file.

Oops

Presenting ten charts to show how hard you worked.

Do this instead

Lead with the one finding that matters. Keep the rest in an appendix for anyone who asks.

Your mission

Count something real

~30 min

Quick check

Ice cream sales and sunburn cases rise together every summer. What's the best conclusion?

Go deeper

1Identify a claim you've seen made without supporting data and consider how you'd validate it.
2Learn the difference between a vanity number and one that actually supports a decision.
3Practice framing a business question as a specific, answerable data question.