Imstudying...
Badges: 12
Rep:
? You'll earn badges for being active around the site. Rep gems come when your posts are rated by other community members.
#1
Report Thread starter 3 years ago
#1
I am quite confused about what the significance level actually means. In biology, we are testing at 5% significance level. My teacher told me that if the the chi square value is lesser than the critical value, you can accept the null hypothesis with 95% confidence. However she did an addition part with probability and found that the chi squared value was between 50% and 30% in the non significant part of the chi squared table. And the explanation for this was that the probability of null hypothesis being wrong is between 30% and 50%. So how is it that you can accept the null hypothesis with 95% confidence and have probability of the null hypothesis being wrong between 30-50%? I find the idea conflicting.
Sorry for being so lengthy
0
reply
Imstudying...
Badges: 12
Rep:
? You'll earn badges for being active around the site. Rep gems come when your posts are rated by other community members.
#2
Report Thread starter 3 years ago
#2
bump
0
reply
macpatgh-Sheldon
Badges: 20
Rep:
? You'll earn badges for being active around the site. Rep gems come when your posts are rated by other community members.
#3
Report 3 years ago
#3
Hi Jane,

The null hypothesis (the word "null" means kinda "not applicable" or "non-existent", so normally your null hypothesis is stated in such a way that your experiment/research is trying to prove it wrong (sorry sounds a bit stupid, but hang on - let me finish, then it will make sense!).

For any significance test (not just chi-squared test) where you work out the p value, the p value is the PROBABILITY THAT YOUR NULL HYPOTHESIS IS INAPLLICABLE (OR KINDA INCORRECT) PURELY DUE TO CHANCE so if this probability is very low [e.g. < 0.05 i.e. 5%][or ideally even lower e.g. 0.002], THEN the opposite i.e. the probability that your null hypothesis is UNTRUE for sure is very high i.e. > 95% [100 - 5] [OR > 99.8% for the example in italics above].

So, since your null hypothesis was set [deliberately] to be THE OPPOSITE of what you were trying to prove, then with a very low p value, proving it [the null hypothesis] wrong means you have proved what you originally set out to prove [with a degree of certainty inversely proprtional to the p value].

Check out both the answers on this post, too [mine and other]:

https://www.thestudentroom.co.uk/sho...ND%20p%20value

If still stuck with anything, please feel free to ask.

M
1
reply
X

Quick Reply

Attached files
Write a reply...
Reply
new posts
Back
to top
Latest

Were exams easier or harder than you expected?

Easier (65)
27.78%
As I expected (73)
31.2%
Harder (88)
37.61%
Something else (tell us in the thread) (8)
3.42%

Watched Threads

View All