The Student Room Group
Uni students - Complete our survey >>
Uni students - Complete our survey >>
Uni students - Complete our survey >>

Which stats test to use?

If i'm testing the difference between cricket's heart rates at 2 different temperatures, do i have to do a paired t test? I have 13 crickets that i will test under 2 different temperatures. I won't be able to tell the individual crickets apart so i'm a bit confused as to which test i should use.
Original post by daisychain_
If i'm testing the difference between cricket's heart rates at 2 different temperatures, do i have to do a paired t test? I have 13 crickets that i will test under 2 different temperatures. I won't be able to tell the individual crickets apart so i'm a bit confused as to which test i should use.


So you'll be looking at individual cricketers compared to themselves (repeated measures), and you'll be comparing two variables: heart rate (the dependent variable) and room temperature (the independent variable). And your independent variable has 2 levels (your 2 temperatures) - this means a paired t-test is the way to go!! Be sure to test for normality as well.

That's the general checklist you should go through when you're thinking of doing statistical tests:
Who am I studying? (Different groups? Same people under different conditions?)
How many dependent variables do I have?
How many independent variables do I have?
Are they parametric?

Posted from TSR Mobile
Original post by Hype en Ecosse
So you'll be looking at individual cricketers compared to themselves (repeated measures), and you'll be comparing two variables: heart rate (the dependent variable) and room temperature (the independent variable). And your independent variable has 2 levels (your 2 temperatures) - this means a paired t-test is the way to go!! Be sure to test for normality as well.

That's the general checklist you should go through when you're thinking of doing statistical tests:
Who am I studying? (Different groups? Same people under different conditions?)
How many dependent variables do I have?
How many independent variables do I have?
Are they parametric?

Posted from TSR Mobile


Thank you! So it doesn't matter that i won't be able to work out the heart rate differences for each individual cricket?
Original post by daisychain_
Thank you! So it doesn't matter that i won't be able to work out the heart rate differences for each individual cricket?


Not unless that's what you're looking for: t-tests aren't really meant to look for differences between individuals, but for groups instead! They look for the overall difference/trend/significance between two groups. :smile:

If you want an arithmetic difference, you can just find the mean for both temperatures, then take them away from each other. It's not as rigorous as a t-test, but it's useful data for eyeballing!

Posted from TSR Mobile
Original post by Hype en Ecosse
Not unless that's what you're looking for: t-tests aren't really meant to look for differences between individuals, but for groups instead! They look for the overall difference/trend/significance between two groups. :smile:

If you want an arithmetic difference, you can just find the mean for both temperatures, then take them away from each other. It's not as rigorous as a t-test, but it's useful data for eyeballing!

Posted from TSR Mobile


Brilliant, thank you for your help :smile:
Original post by daisychain_
Brilliant, thank you for your help :smile:


No problem, dude!

Posted from TSR Mobile
Original post by Hype en Ecosse
X


So sorry to quote you in again, but my teacher said that a paired t test won't work as I won't be able work out the differences in heart rate for each individual cricket at different temperatures, because I won't be able to tell each cricket apart. I don't know how to do a paired t test anyway, could you perhaps link me to any useful websites that explain how to work it out?

I don't know if I'll be able to do an unpaired test either because even if the crickets are from the same population they'll differ in size and genetics.

Would a Mann-Whitney U work?
Why cant you work out each individual cricket? Keep each in a separate box?
Original post by barrinalo
Why cant you work out each individual cricket? Keep each in a separate box?


I don't have much time to do that, but i don't know i might have to. :redface:

Quick Reply

Related discussions

Latest

Trending

Trending

Articles for you