Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
40 views

Can Get The Most Creative, As Long As You Can Test The Hypotheses in Feasible Ways

Uploaded by

Thanh Phu Tran
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
40 views

Can Get The Most Creative, As Long As You Can Test The Hypotheses in Feasible Ways

Uploaded by

Thanh Phu Tran
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Can get the most creative, as long as you can test the hypotheses in feasible ways

STEP 1: DEFINE YOUR HYPOTHESES

Remember to state the hypothesis statement to the interviewer


STEP 2: BREAKING IT DOWN

 Break the hypothesis down into those other hypotheses that need to be true for that one to be
true
 Need to do that because you need simple hypotheses to test, can’t test the complicated ones =>
simple enough? Not need to break it down
 How to know if the hypothesis is simple enough? => Again, it is simple if you can test it straight
away
 Breakdown might not be 100% MECE but the closer to that, the better. You might not test all of
the simple hypotheses that you come up with, but you need to at least show to the interviewer
that you have a plan of what you’re gonna do if you need even more certainty
 Quick vs. exhaustive test:
- Quick test -> pick the 1 or 2 most important ones and controversial ones in your breakdown
(main to the hypothesis)

Get back to the example case:


STEP 3: GATHER AND PROCESS DATA

Indicative tests (don’t necessarily prove the hypothesis is true or false but show that it is more likely to be
true or false) vs. conclusive tests (data actually prove or very very close to prove the hypothesis)

You might also like