You are Here: Home >< Maths

# Student's t-test HELP watch

1. I need to use the student's t-test in Biology but I don't remember anything from stats (despite getting some 95% in the stats exam last year). Also, I've never actually done the student's t-test. I just need help analysing the value I got.

I'm comparing heart rate before and after exercise, so I need to use the paired test. Here's what I have so far:

Set A is HR before, set B is HR after exercise.

Mean of A = 72.53
Mean of B = 97.53
Mean difference = -25
Standard deviation of differences = 12.489996
t value = 7.75

Unfortunately, I have no idea how to write the two hypotheses, what a p-value is, or how to prove that the difference is significant.

I've been trying to do this for over five hours and I'm very close to crying. I can't find anything relevant online, and everything is explained in a way that I just don't understand. Please help! Thank you.
2. (Original post by JustJusty)
I need to use the student's t-test in Biology but I don't remember anything from stats (despite getting some 95% in the stats exam last year). Also, I've never actually done the student's t-test. I just need help analysing the value I got.

I'm comparing heart rate before and after exercise, so I need to use the paired test. Here's what I have so far:

Set A is HR before, set B is HR after exercise.

Mean of A = 72.53
Mean of B = 97.53
Mean difference = -25
Standard deviation of differences = 12.489996
t value = 7.75

Unfortunately, I have no idea how to write the two hypotheses, what a p-value is, or how to prove that the difference is significant.

I've been trying to do this for over five hours and I'm very close to crying. I can't find anything relevant online, and everything is explained in a way that I just don't understand. Please help! Thank you.
Your hypothesis is usually given to you, if not it'll be related to your independent and dependent variables. Yours is probably something like "exercise has an effect on heart rate", and your null hypothesis would be exercise has no effect on heart rate.

A p-value is a probability value that indicates how likely your null hypothesis being true is. Generally, for bio, if p<0.05 you can say at the 95% (1-0.05)confidence level that your null hypothesis is incorrect, and hence there is a significant and probably non-coincidental difference between your two data sets (after exercise and before exercise).

Edit: I've done this PAG earlier and my bio teacher said I should have used an unpaired t-test, because all the data should come from the same individual for paired. Most of the Internet seems to disagree, but idk, food for thought.
3. (Original post by JustJusty)
I need to use the student's t-test in Biology but I don't remember anything from stats (despite getting some 95% in the stats exam last year). Also, I've never actually done the student's t-test. I just need help analysing the value I got.

I'm comparing heart rate before and after exercise, so I need to use the paired test. Here's what I have so far:

Set A is HR before, set B is HR after exercise.

Mean of A = 72.53
Mean of B = 97.53
Mean difference = -25
Standard deviation of differences = 12.489996
t value = 7.75

Unfortunately, I have no idea how to write the two hypotheses, what a p-value is, or how to prove that the difference is significant.
As you are comparing heart rate before and after exercise, your null hypothesis is going to be informally something like:

H0: After exercise, heart rate is the same as before exercise.

We need to turn that into something more formal that is amenable to a statistical test. The obvious thing to do is to phrase it in terms of the mean heart rates before and after of the cohort.

H0: The mean heart rate of my cohort after exercise shows no difference to mean heart rate before exercise.

If you want to be very picky, as we're using a paired test, we could write it in the form:

H0: The mean difference between heart rate before and after exercise is zero.

You've then done all the calculations to come up with the value of a t-statistic. What you need to do now is to look up that t-value in statistical tables to get the p-value. The p-value is the probability of obtaining such a large t-value purely by chance - and we reject the null hypothesis (and infer that heart rates are different) if p is sufficiently small (usually p < 0.05 is the convention).

For actually calculating your p-value, it's by far the easiest to let some software do it for you: do you have access to stat software or to a calculator with stats built in?

TSR Support Team

We have a brilliant team of more than 60 Support Team members looking after discussions on The Student Room, helping to make it a fun, safe and useful place to hang out.

This forum is supported by:
Updated: January 15, 2017
Today on TSR

### Congratulations to Harry and Meghan!

But did you bother to watch?

Poll
Useful resources

### Maths Forum posting guidelines

Not sure where to post? Read the updated guidelines here

### How to use LaTex

Writing equations the easy way

### Study habits of A* students

Top tips from students who have already aced their exams