# statics PPMC Q

Watch
Announcements

Page 1 of 1

Go to first unread

Skip to page:

r=0.7628 and the calculated value from sampel size was 0.7155

As 0.7155<0.7628 is there insufficient evidence to reject H0 so insufficient evidence to prove correlation is postive?

As 0.7155<0.7628 is there insufficient evidence to reject H0 so insufficient evidence to prove correlation is postive?

Last edited by shreya_2003; 1 month ago

0

reply

Report

#2

(Original post by

r=0.7628 and the calculated value from sampel size was 0.7155

As 0.7155<0.7628 is there insufficient evidence to reject H0 so insufficient evidence to prove correlation is postive?

**shreya_2003**)r=0.7628 and the calculated value from sampel size was 0.7155

As 0.7155<0.7628 is there insufficient evidence to reject H0 so insufficient evidence to prove correlation is postive?

0

reply

(Original post by

How did you get those two numbers?

**mqb2766**)How did you get those two numbers?

0

reply

Report

#4

(Original post by

i got the r value from putting the table into the porudct moment function. And the other one from using sample size of 10 and 0.01% sig level in the formula booklet.

**shreya_2003**)i got the r value from putting the table into the porudct moment function. And the other one from using sample size of 10 and 0.01% sig level in the formula booklet.

It does help to see your working when posting a question.

0

reply

(Original post by

What is hypothesis test did you do, one tailed or two tailed?

It does help to see your working when posting a question.

**mqb2766**)What is hypothesis test did you do, one tailed or two tailed?

It does help to see your working when posting a question.

r was 0.7628

One tailed

Ho: p=0

H1: p>0

Value from formula booklet 0.7155<0.7628 therefore insufficient evidence to reject Ho and no evidence correlation coefficient is positive.

0

reply

Report

#6

(Original post by

my bad ill type it out

r was 0.7628

One tailed

Ho: p=0

H1: p>0

Value from formula booklet 0.7155<0.7628 therefore insufficient evidence to reject Ho and no evidence correlation coefficient is positive.

**shreya_2003**)my bad ill type it out

r was 0.7628

One tailed

Ho: p=0

H1: p>0

Value from formula booklet 0.7155<0.7628 therefore insufficient evidence to reject Ho and no evidence correlation coefficient is positive.

Im assuming 0.76 is from the data and 0.71 is the critical region from the hypothesis?

Edit in #3, you mean 1% significance, not 0.01%?

Last edited by mqb2766; 1 month ago

0

reply

(Original post by

Ive not checked the values, but they look ok at a glance. However, is your final conclusion correct? If the data correlation was 1, 0.9, 0.8, 0.7, what would you conclude?

Im assuming 0.76 is from the data and 0.71 is the critical region from the hypothesis?

**mqb2766**)Ive not checked the values, but they look ok at a glance. However, is your final conclusion correct? If the data correlation was 1, 0.9, 0.8, 0.7, what would you conclude?

Im assuming 0.76 is from the data and 0.71 is the critical region from the hypothesis?

0

reply

Report

#8

(Original post by

The crit region is the 0.76 so the 0.71 doesnt fall in it so you would dont reject it?

**shreya_2003**)The crit region is the 0.76 so the 0.71 doesnt fall in it so you would dont reject it?

Last edited by mqb2766; 1 month ago

0

reply

(Original post by

Before I check it, which number is the answer to part c)?

**mqb2766**)Before I check it, which number is the answer to part c)?

0

reply

Report

#10

(Original post by

0.7628

**shreya_2003**)0.7628

The critical region boundary is ~0.71.

The pmcc value is ~0.76 so ...

0

reply

(Original post by

But thats the oppoosite to what you said in the previous post.

The critical region boundary is ~0.71.

The pmcc value is ~0.76 so ...

**mqb2766**)But thats the oppoosite to what you said in the previous post.

The critical region boundary is ~0.71.

The pmcc value is ~0.76 so ...

The pmcc is the 0.7628 and the other value is what you called the critical boundary is the 0.71

0

reply

Report

#12

(Original post by

im not sure what the names go by bc i only know it by r (product moment correlation) and the other as sample size value. I made it more confusing i apologise.

The pmcc is the 0.7628 and the other value is what you called the critical boundary is the 0.71

**shreya_2003**)im not sure what the names go by bc i only know it by r (product moment correlation) and the other as sample size value. I made it more confusing i apologise.

The pmcc is the 0.7628 and the other value is what you called the critical boundary is the 0.71

0

reply

(Original post by

I agree with that (no need to apologise), so what do you conclude? If the pmcc was 1, what would you conclude? Similarly for 0.9, 0.8, 0.7 say.

**mqb2766**)I agree with that (no need to apologise), so what do you conclude? If the pmcc was 1, what would you conclude? Similarly for 0.9, 0.8, 0.7 say.

0

reply

Report

#14

(Original post by

I said that there was insufficient evidence to reject the Ho as it doesnt lie in the region.

**shreya_2003**)I said that there was insufficient evidence to reject the Ho as it doesnt lie in the region.

Similarly for 0.9,0.8,0.7?

Last edited by mqb2766; 1 month ago

0

reply

(Original post by

Ill try for the last time, what would you conclude if the pmcc was 1? Is there sufficient evidence for a positive correlation?

Similarly for 0.9,0.8,0.7?

**mqb2766**)Ill try for the last time, what would you conclude if the pmcc was 1? Is there sufficient evidence for a positive correlation?

Similarly for 0.9,0.8,0.7?

0

reply

Report

#16

(Original post by

Oh yes bc the closer to 1 the more postive correlation it has.

**shreya_2003**)Oh yes bc the closer to 1 the more postive correlation it has.

0

reply

(Original post by

So what do you conclude about this question?

**mqb2766**)So what do you conclude about this question?

0

reply

Report

#18

(Original post by

that there is positive correlation?

**shreya_2003**)that there is positive correlation?

Note they've picked a 0.76 correlation here because a single tail test gives a p value 0.005, where as a two tail test gives a p-value > 0.01. So using the wrong test (one tail or two tail) will change the conclusion and hence get the question part right/wrong. They're deliberately using a pmcc just inside the critical region (close to the boundary) to get this.

https://www.statstutor.ac.uk/resourc...d/pearsons.pdf[img=16x16]chrome-extension://gmpljdlgcdkljlppaekciacdmdlhfeon/images/beside-link-icon.svg[/img]

Is decent and its good to get some pictures in your head about what typical data looks like. Just google

positive correlation null hypothesis

and get it straight.

Last edited by mqb2766; 1 month ago

0

reply

(Original post by

Of course. Its really important to understand what the null hypothesis is and what the critical boundary/region corresponds to. The null hypothesis is that there is no (positive) correlation between the variables so pmcc<=0. This means that (weak) correlations < 0.71 (n=10) will not be strong enough to disprove this. For (strong) correlations > 0.71, there is enough evidence to support the fact that it is non-zero (posiitve). Obviously a correation =1 is the extreme case.

Note they've picked a 0.76 correlation here because a single tail test gives a p value 0.005, where as a two tail test gives a p-value > 0.01. So using the wrong test (one tail or two tail) will change the conclusion and hence get the question part right/wrong. They're deliberately using a pmcc just inside the critical region (close to the boundary) to get this.

https://www.statstutor.ac.uk/resourc...d/pearsons.pdf[img=16x16]chrome-extension://gmpljdlgcdkljlppaekciacdmdlhfeon/images/beside-link-icon.svg[/img]

Is decent and its good to get some pictures in your head about what typical data looks like. Just google

positive correlation null hypothesis

and get it straight.

**mqb2766**)Of course. Its really important to understand what the null hypothesis is and what the critical boundary/region corresponds to. The null hypothesis is that there is no (positive) correlation between the variables so pmcc<=0. This means that (weak) correlations < 0.71 (n=10) will not be strong enough to disprove this. For (strong) correlations > 0.71, there is enough evidence to support the fact that it is non-zero (posiitve). Obviously a correation =1 is the extreme case.

Note they've picked a 0.76 correlation here because a single tail test gives a p value 0.005, where as a two tail test gives a p-value > 0.01. So using the wrong test (one tail or two tail) will change the conclusion and hence get the question part right/wrong. They're deliberately using a pmcc just inside the critical region (close to the boundary) to get this.

https://www.statstutor.ac.uk/resourc...d/pearsons.pdf[img=16x16]chrome-extension://gmpljdlgcdkljlppaekciacdmdlhfeon/images/beside-link-icon.svg[/img]

Is decent and its good to get some pictures in your head about what typical data looks like. Just google

positive correlation null hypothesis

and get it straight.

0

reply

X

Page 1 of 1

Go to first unread

Skip to page:

### Quick Reply

Back

to top

to top