Interpreting this Case Control Study! - USMLE Forums
USMLE Forums Logo
USMLE Forums         Your Reliable USMLE Online Community     Members     Posts
Home
USMLE Articles
USMLE News
USMLE Polls
USMLE Books
USMLE Apps
Go Back   USMLE Forums > USMLE Step 2 CK Forum

USMLE Step 2 CK Forum USMLE Step 2 CK Discussion Forum: Let's talk about anything related to USMLE Step 2 CK exam


Reply
 
Thread Tools Search this Thread Display Modes
  #1  
Old 05-31-2011
USMLE Forums Veteran
 
Steps History: Not yet
Posts: 200
Threads: 101
Thanked 197 Times in 65 Posts
Reputation: 220
Stats Interpreting this Case Control Study!

A case-control study is conducted to assess the risk for intussusception in infants under the age of 1 year who receive the rotavirus
vaccine. The medical records of all those who received the vaccine and those who did not receive the vaccine over a 6-month period are reviewed. Results show 125 cases per 100,000 infant-years for infants who received the vaccine compared to 45 cases per 100,000 infant-years for infants who did not receive the vaccine. The investigators conclude that the relative risk for intussusception is 1.9 times greater in infants who receive the rotavirus vaccine (95% confidence interval of 0.5–7.7 and p=0.39). Which of the following is the most accurate interpretation of these results?

A) The results do not show an association between rotavirus vaccine and intussusception, but they may be related
B) The results show sufficient statistical power to identify an association between rotavirus vaccine and intussusception
C) Rotavirus vaccine is associated with a 39% risk for intussusception
D) Rotavirus vaccine causes intussusception in 1.9% of infants
E) Rotavirus vaccine prevents 80 cases of intussusception per 100,000 infant-years


Reply With Quote Quick reply to this message



  #2  
Old 05-31-2011
Claus_CU's Avatar
USMLE Forums Addict
 
Steps History: 1 + CS
Posts: 113
Threads: 8
Thanked 89 Times in 61 Posts
Reputation: 99
Thumbs Up

The answer is A.

btw, the investigators shouldn't report RR, because this is a case control and not a cohort...in any case, the "best" answer is A.
Reply With Quote Quick reply to this message
  #3  
Old 05-31-2011
USMLE Forums Veteran
 
Steps History: 1+CK+CS
Posts: 244
Threads: 16
Thanked 200 Times in 86 Posts
Reputation: 210
Default

A) because the measure of association has a confidence interval that overlaps 1.

relative risks are reported in case control studies - they are inferred sometimes through measures such as incident density sampling, also relative risk approaches odds ratios at other times ( beyond the scope of usmle step 2 CK).

Anyway hope this helps
Reply With Quote Quick reply to this message
 
  #4  
Old 05-31-2011
Claus_CU's Avatar
USMLE Forums Addict
 
Steps History: 1 + CS
Posts: 113
Threads: 8
Thanked 89 Times in 61 Posts
Reputation: 99
Default

Quote:
Originally Posted by drarnab View Post
A) because the measure of association has a confidence interval that overlaps 1.

relative risks are reported in case control studies - they are inferred sometimes through measures such as incident density sampling, also relative risk approaches odds ratios at other times ( beyond the scope of usmle step 2 CK).

Anyway hope this helps
Actually you can't really get and RR from and OR using a case-control study (likelihood ratio function doesn't not work and gives a biased estimator). You could only approximate it, is the rate of the disease is rare...maybe in this case, but it's to see...but indeed, is beyond the scope of usmle step 2 CK
Reply With Quote Quick reply to this message
  #5  
Old 05-31-2011
USMLE Forums Veteran
 
Steps History: 1+CK+CS
Posts: 244
Threads: 16
Thanked 200 Times in 86 Posts
Reputation: 210
Default

Quote:
Originally Posted by Claus_CU View Post
Actually you can't really get and RR from and OR using a case-control study (likelihood ratio function doesn't not work and gives a biased estimator). You could only approximate it, is the rate of the disease is rare...maybe in this case, but it's to see...but indeed, is beyond the scope of usmle step 2 CK
This is just a reference : http://oem.bmj.com/content/61/12/e59.abstract

apologies if the thread is getting offtopic.
Reply With Quote Quick reply to this message
  #6  
Old 05-31-2011
bebix's Avatar
USMLE Forums Master
 
Steps History: 1+CK+CS+3
Posts: 1,357
Threads: 194
Thanked 3,268 Times in 881 Posts
Reputation: 3278
Default

the answer is A)
Reply With Quote Quick reply to this message
  #7  
Old 05-31-2011
Claus_CU's Avatar
USMLE Forums Addict
 
Steps History: 1 + CS
Posts: 113
Threads: 8
Thanked 89 Times in 61 Posts
Reputation: 99
Default

Quote:
Originally Posted by drarnab View Post
This is just a reference : http://oem.bmj.com/content/61/12/e59.abstract

apologies if the thread is getting offtopic.
let's follow this via pm
Reply With Quote Quick reply to this message
  #8  
Old 05-31-2011
mle guy's Avatar
USMLE Forums Veteran
 
Steps History: 1+CK+CS+3
Posts: 264
Threads: 16
Thanked 350 Times in 165 Posts
Reputation: 360
Default A

No association because:
1. CI 0.5-7.7 has the value "1"
2. p=0.39
Reply With Quote Quick reply to this message
The above post was thanked by:
benzo (06-03-2011), usmle3evana (11-27-2015)
  #9  
Old 06-01-2011
1TA2B's Avatar
USMLE Forums Guru
 
Steps History: CK Only
Posts: 475
Threads: 39
Thanked 353 Times in 169 Posts
Reputation: 376
Default

Quote:
Originally Posted by mle guy View Post
No association because:
1. CI 0.5-7.7 has the value "1"
2. p=0.39

Yes. A indeed. Statistically not significant difference between two groups! Also ditto to mle guy. Thanks.

This is an easy one because other statements don't make sense at all.
__________________
Skill+Hardwork+Preparation=Success
To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

Reply With Quote Quick reply to this message
The above post was thanked by:
docoftheworld (06-01-2011)
  #10  
Old 06-01-2011
docoftheworld's Avatar
USMLE Forums Veteran
 
Steps History: 1 + CS
Posts: 204
Threads: 56
Thanked 42 Times in 37 Posts
Reputation: 52
Send a message via Skype™ to docoftheworld
Default

what if we are given the CI only without p Value, and 1 wasnt within the CI, could we make inference without having the p? I had a question wherein everyone answered about the association (since CI doesnt include 1) although p wasnt presented, and one of the options was: we cant make inference based on given information (which i chose)

am i being too anal here?
Reply With Quote Quick reply to this message
  #11  
Old 06-01-2011
bebix's Avatar
USMLE Forums Master
 
Steps History: 1+CK+CS+3
Posts: 1,357
Threads: 194
Thanked 3,268 Times in 881 Posts
Reputation: 3278
Default

Quote:
Originally Posted by docoftheworld View Post
what if we are given the CI only without p Value, and 1 wasnt within the CI, could we make inference without having the p? I had a question wherein everyone answered about the association (since CI doesnt include 1) although p wasnt presented, and one of the options was: we cant make inference based on given information (which i chose)

am i being too anal here?
Remember, when you calculate a CI, you must use the Z score (or a t score) according to your level of confident. If you have a CI for RR/OR and the number 1 is included, is the same as having a p-value above your pre-set alpha (type I error). You donīt know the actual number of the p-value (e.g preset alpha = 0.05...the p-value could be 0.051 or 0.40), but you know that is greater than 0.05.
The same is true with this example:
95%RR[1.01, 1.02]
95%RR[5,7]
In both cases the p-value is less than 0.05, because the magic number 1 in not included...So there is an statistical association, but in case number one is VERY weak.
Reply With Quote Quick reply to this message
The above post was thanked by:
docoftheworld (06-01-2011)
  #12  
Old 06-01-2011
docoftheworld's Avatar
USMLE Forums Veteran
 
Steps History: 1 + CS
Posts: 204
Threads: 56
Thanked 42 Times in 37 Posts
Reputation: 52
Send a message via Skype™ to docoftheworld
Default

then whats use of including p value with CI then? if CI by itself is significant provided it doesnt include 1?
Reply With Quote Quick reply to this message
  #13  
Old 06-01-2011
bebix's Avatar
USMLE Forums Master
 
Steps History: 1+CK+CS+3
Posts: 1,357
Threads: 194
Thanked 3,268 Times in 881 Posts
Reputation: 3278
Default

Quote:
Originally Posted by docoftheworld View Post
then whats use of including p value with CI then? if CI by itself is significant provided it doesnt include 1?
Actually, you don't have to include the p-value...if you already reported the 95%CI...but only a p-value without a CI is not that informative (unless you provide the value of the SD & sample size or the SE).
For example, in the bmj, they "don't like" p-values that much...
this is a clasical articule:
p-value bmj.pdf
Reply With Quote Quick reply to this message
The above post was thanked by:
healer2b (06-01-2011)
  #14  
Old 06-01-2011
docoftheworld's Avatar
USMLE Forums Veteran
 
Steps History: 1 + CS
Posts: 204
Threads: 56
Thanked 42 Times in 37 Posts
Reputation: 52
Send a message via Skype™ to docoftheworld
Default

so are we saying here that a combination of CI that includes 1 and p that is less than 0.05 is impossible? (and vice versa; a CI that doesnt include 1 CANNOT have a p more than 0.05
Reply With Quote Quick reply to this message
  #15  
Old 06-01-2011
bebix's Avatar
USMLE Forums Master
 
Steps History: 1+CK+CS+3
Posts: 1,357
Threads: 194
Thanked 3,268 Times in 881 Posts
Reputation: 3278
Default

Quote:
Originally Posted by docoftheworld View Post
so are we saying here that a combination of CI that includes 1 and p that is less than 0.05 is impossible? (and vice versa; a CI that doesnt include 1 CANNOT have a p more than 0.05
X%CI for RR & OR = if the number 1 is included, the p-value MUST be above the preset alpha value
X%CI for difference between mean or proportions = in the number 0 is included, the p-value MUST be above the preset alpha value
Reply With Quote Quick reply to this message
The above post was thanked by:
benzo (06-03-2011), docoftheworld (06-01-2011)



  #16  
Old 06-01-2011
docoftheworld's Avatar
USMLE Forums Veteran
 
Steps History: 1 + CS
Posts: 204
Threads: 56
Thanked 42 Times in 37 Posts
Reputation: 52
Send a message via Skype™ to docoftheworld
Default

awesome bebix ... you rock
Reply With Quote Quick reply to this message



Reply

Tags
Biostatistics-Epidemiology, Step-2-Questions

Quick Reply
Message:
Options

Register Now

In order to be able to post messages on the USMLE Forums forums, you must first register.
Please enter your desired user name, your email address and other required details in the form below.
User Name:
Password
Please enter a password for your user account. Note that passwords are case-sensitive.
Password:
Confirm Password:
Email Address
Please enter a valid email address for yourself.
Email Address:
Medical School
Choose "---" if you don't want to tell. AMG for US & Canadian medical schools. IMG for all other medical schools.
USMLE Steps History
What steps finished! Example: 1+CK+CS+3 = Passed Step 1, Step 2 CK, Step 2 CS, and Step 3.

Choose "---" if you don't want to tell.

Favorite USMLE Books
What USMLE books you really think are useful. Leave blank if you don't want to tell.
Location
Where you live. Leave blank if you don't want to tell.

Log-in

Human Verification

In order to verify that you are a human and not a spam bot, please enter the answer into the following box below based on the instructions contained in the graphic.



Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes


Similar Threads
Thread Thread Starter Forum Replies Last Post
Treatment vs control, the interpretation of the p-value bebix USMLE Step 1 Forum 5 05-26-2011 06:18 AM
He believes he can control the weather! Hope2Pass USMLE Step 1 Forum 15 03-26-2011 07:24 PM
16 yr old girl asking for birth control pills khushboo USMLE Step 1 Forum 7 05-30-2010 11:11 PM
Phosphate Hormonal Control rasheed USMLE Step 1 Bits & Pieces 0 02-13-2010 05:27 PM
Case Control Study Design Question Hunter USMLE Step 1 Forum 2 12-15-2009 08:01 AM

RSS Feed
Find Us on Facebook
vBulletin Security provided by vBSecurity v2.2.2 (Pro) - vBulletin Mods & Addons Copyright © 2017 DragonByte Technologies Ltd.

USMLE® & other trade marks belong to their respective owners, read full disclaimer
USMLE Forums created under Creative Commons 3.0 License. (2009-2014)