• We are pleased to announce that the winner of our Feedback Prize Draw for the Winter 2024-25 session and winning £150 of gift vouchers is Zhao Liang Tay. Congratulations to Zhao Liang. If you fancy winning £150 worth of gift vouchers (from a major UK store) for the Summer 2025 exam sitting for just a few minutes of your time throughout the session, please see our website at https://www.acted.co.uk/further-info.html?pat=feedback#feedback-prize for more information on how you can make sure your name is included in the draw at the end of the session.
  • Please be advised that the SP1, SP5 and SP7 X1 deadline is the 14th July and not the 17th June as first stated. Please accept out apologies for any confusion caused.

Contingency Tables

S

sfischer

Member
In the example 12.21, we combine 2 groups because character present has a value or 3.5 and 1.9 in the 2 groups we combine (both <5). Would we combine them if only one value was <5? If we didn't combine them would the test be still valid (in this case) - I thought we were only concerned if >20% of the Ei were <5? Could we arbitrarily decide to group say 21-25 and 26-30 and the test would still be valid? Sorry 3 questions for the price of 1 there just trying to get a full understanding of when to combine and when not to.
Thanks.
 
Examples 12.18 and 12.19 seem to indicate that we should combine groups when any ei is <5. I'll be going through past papers in coming weeks - it would be good to know if anyone else has followed the 20% "conservative" approach?

Tim
 
Apologies - I thought I had answered this question!

In the example 12.21, we combine 2 groups because character present has a value or 3.5 and 1.9 in the 2 groups we combine (both <5). Would we combine them if only one value was <5?

You'd certainly need to combine the one which was less than 5 but you could choose which group you'd combine it with.

If we didn't combine them would the test be still valid (in this case) - I thought we were only concerned if >20% of the Ei were <5?

There are 8 cells and two of them (ie 25%) are less than 5 so that is >20% of them.

Could we arbitrarily decide to group say 21-25 and 26-30 and the test would still be valid?

Yup - the test just compares numbers in the groups - doesn't matter wherre they're from.
 
Thanks for that. 2 out of 8=25%...Ok missed the simple maths there. But on your response to the first part - eg. if I only had 1 out of the 8 <5, I would still need to combine it - where does the >20% rule come in if we need to combine all values <5 anyway?
 
Thanks for that. 2 out of 8=25%...Ok missed the simple maths there. But on your response to the first part - eg. if I only had 1 out of the 8 <5, I would still need to combine it - where does the >20% rule come in if we need to combine all values <5 anyway?

There's two rules:

the easy-to-remember-but-harsher-than-it-needs-to-be "combine if <5" rule

the harder-to-remember-but-not-so-harsh "combine if more than 20% <5 or if any are <1" rule

the second is more accurate - but the first is a nice easy to remember rule.

In the exam use whichever you like.
 
Back
Top