Tired of seeing ads? Click here to upgrade to Elite Membership!


Mathematics Forum

Reply  New Topic New Poll Mathematics -> Statistics
Control Panel | search | Email to a Friend
Log In! | Register

Author Message / Information
Dimebagd






Quote | Reply |


NEED STATS HELP ASAP.
posted on: 12/13/2006 2:40:09 AM

Hey i am strugling with some questions... someone help please!!!

1) 22000 male physicians participated in an experiment to determine if aspirin helps to reduce the risk of a heart attack. Half took aspirin according to the Expt. plan and the other half took a placebo. After three years researchers determined that 104 of those that took aspirin and 189 of those that took a placebo had suffered heart attacks. Compute and interpret the p-value of a test to determine whether these results indicate that aspirin is effective in reducing the incidence of heart attacks. What conditions must be met to make your answer beleavable??..

PLEASE HELP ME!!

THANKS!
mathgeek




Quote | Reply |


NEED STATS HELP ASAP.
replied on: 3/15/2007 10:16:20 AM

I am sure that this is entirely too late, but the short answer is that there is no difference between the two groups.

I calculated a z-score of -0.944 and so at any reasonable level of confidence (alpha <= 0.1), the z-score always falls in the acceptance region.

Without a particular alpha, it is impossible to determine the p-score for this cutoff.
Pythagoras




Quote | Reply |


NEED STATS HELP ASAP.
replied on: 3/17/2007 10:32:01 AM

So, what is a "z-score"?

(this might inspire me to move a little bit)



mathgeek




Quote | Reply |


NEED STATS HELP ASAP.
replied on: 3/29/2007 10:53:45 AM

Proportion questions are usually binomially distributed. But if the sample size generating those proportions are large enough, we can assume a "normal" distribution. . . you know, a bell curve shape.

The z-score is a conversion, of sorts. We take the information from the proportion and convert it into an equivalent score on the normal distribution. Then we can use the properties of the normal distribution to make inferences about the original proportion.

There are different types of z-score conversions for different kinds of situations. This is called hypothesis testing. You can look it up in Wikipedia for more information.
LinkBot





Gamers Wanted is looking for people to write game reviews and post news,
if your interested please visit Gamers Wanted About Us Page




 



Contact Administrator (must be logged in)


Tired of seeing ads? Click here to upgrade to Elite Membership!


ChatArea.com Help & News Forums | Terms of Use | Contact ChatArea.com | Advertising

Powered By ChatArea.com - Get your free Society today! © Copyright 2003 Wewp!