Search
Search titles only
By:
Search titles only
By:
Home
Forums
New posts
Search forums
What's new
New posts
New profile posts
Latest activity
Members
Current visitors
New profile posts
Search profile posts
Log in
Register
Search
Search titles only
By:
Search titles only
By:
New posts
Search forums
Menu
Install the app
Install
Reply to Thread
Guest, we'd love to know what you think about the forum! Take the
Diabetes Forum Survey 2024 »
Home
Forums
Diabetes Discussion
Diabetes Discussions
Statins - good or bad - what does the research say?
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Message
<blockquote data-quote="Oldvatr" data-source="post: 1021889" data-attributes="member: 196898"><p>As I see it the ASCOT team are using a Peto (2x2) analysis model, where 4 sets of results are tested to see if there is any interaction between them. The Null hypothesis is that there is in effect no interaction between them , and this is usually when P<0.0001. A P value of 0.05 would show that there is significant interaction between the groups i.e. the Null Hypothesis should be rejected. So it would appear that there is significant interaction between the hypertension trial and the avorastatin/ placebo trial. Since the P=0.05 is applied to the extended LLA monitoring, it shows that there is significant cross contamination between the Avorastatin and Placebo groups. which is mentioned in the report text. This further weakens the claims made in the final outcome /conclusion section. I worked in the Aerospace business, where Peto is used regularly. It was not a tool I used myself, but I had to audit reports from other authors and needed a certain level of understanding of statistics. I am by no means an expert, but I have a knack of being able to sniff out 'mistakes'. By the way, the formula for relative risk is as follows (from a textbook):</p><p>For a single stratum relative risk is defined as follows:</p><p>...............................Exposed......Non-Exposed(</p><p>OUTCOME: Cases:....a...................b</p><p>Non-cases:..................c...................d</p><p></p><p>Relative risk = [a/(a+c)] / [b/(b+d)]</p><p>It would have helped if the report had given a description of how they achieved the 36% figure, since it does not seem to be born out by the actual results (abcd).</p><p></p><p>Perhaps someone from ASCOT will reply here to answer these questions for us.</p></blockquote><p></p>
[QUOTE="Oldvatr, post: 1021889, member: 196898"] As I see it the ASCOT team are using a Peto (2x2) analysis model, where 4 sets of results are tested to see if there is any interaction between them. The Null hypothesis is that there is in effect no interaction between them , and this is usually when P<0.0001. A P value of 0.05 would show that there is significant interaction between the groups i.e. the Null Hypothesis should be rejected. So it would appear that there is significant interaction between the hypertension trial and the avorastatin/ placebo trial. Since the P=0.05 is applied to the extended LLA monitoring, it shows that there is significant cross contamination between the Avorastatin and Placebo groups. which is mentioned in the report text. This further weakens the claims made in the final outcome /conclusion section. I worked in the Aerospace business, where Peto is used regularly. It was not a tool I used myself, but I had to audit reports from other authors and needed a certain level of understanding of statistics. I am by no means an expert, but I have a knack of being able to sniff out 'mistakes'. By the way, the formula for relative risk is as follows (from a textbook): For a single stratum relative risk is defined as follows: ...............................Exposed......Non-Exposed( OUTCOME: Cases:....a...................b Non-cases:..................c...................d Relative risk = [a/(a+c)] / [b/(b+d)] It would have helped if the report had given a description of how they achieved the 36% figure, since it does not seem to be born out by the actual results (abcd). Perhaps someone from ASCOT will reply here to answer these questions for us. [/QUOTE]
Verification
Post Reply
Home
Forums
Diabetes Discussion
Diabetes Discussions
Statins - good or bad - what does the research say?
Top
Bottom
Find support, ask questions and share your experiences. Ad free.
Join the community »
This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies.
Accept
Learn More.…