








USMLE Step 1 Forum USMLE Step 1 Discussion Forum: Let's talk about anything related to USMLE Step 1 exam 

Thread Tools  Search this Thread  Display Modes 
#1




Confidence Interval
The IQ scores are obtained from a sample of 100 patients diagnosed with various types of schizophrenia who completed a standard IQ test battery. An additional 20 patients had to be dropped from the sample because they lacked the functional capacity to complete two or more portions of the test. Four other patients refused to take the test battery when offered the opportunity. Results for the patients who completed the test battery gave an average IQ of 110 and a standard deviation of 20.
Using this information. Compute the 95% confidence interval for this estimate of the mean. A. 70 to 130 B. 70 to 150 C. 85 to 115 D. 90 to 130 E. 105 to 115 F. 106 to 114
__________________
One day i will infect these microbes and they will search for "AntiMEbiotic".... To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts. 
The above post was thanked by:  
Kabutar111 (08162012), venky2600 (08162012) 
#2




my answer
B. 70 to 150
Mean +/ 2SD 
#3




F
nice one
__________________
There is no shortcut to SUCCESS ,and there is no excuse for FALIURE  by Kabutar111 To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts. 


#4




yup you are right  the answer should be F. 106 to 114
I totally misread this question  somehow my mind read it "in which brackets 95% of patients will be" 
#5




why ??
why it is f ???
please anyone put the law you use to make calculations ??? 
#6




Quote:
Sent from my iPhone using Tapatalk
__________________
There is no shortcut to SUCCESS ,and there is no excuse for FALIURE  by Kabutar111 To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts. 
#7




Quote:
Sent from my iPhone using Tapatalk
__________________
There is no shortcut to SUCCESS ,and there is no excuse for FALIURE  by Kabutar111 To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts. 
#8




This is from Kaplan Qbank.
The right answer is F. 
#9




N100 (Answer F)
formula used
confidence interval= mean +_ Z(S/square root of sample no. (N) where Z= standard score, for 95% its 2(approx) and for 99% its 2.58 (2.5 or 2.6 for calculation purpose) S= standard deviation. In this question N would be 100 (as we don't exclude those who later on left the study for some or other purpose) 110+_ 2 (20/square root of 100) answer= 110 +_ 4 = 106  114. Now my question: So is it a general rule that we have to consider whole sample of people without considering people who left study or not. Won't it will be any kinda bias. May be "volunteer screwed my study kinda bias"
__________________
One day i will infect these microbes and they will search for "AntiMEbiotic".... To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts. 
#10




Quote:
To give a different example of this question, lets say we're testing a certain drug X for patients with multiple sclerosis. Out of 1000 people initially enrolled in the treatment arm of the trial, 400 drop out due to disabling, but nonlethal side effects(lets say severe malaise, body aches). Only 600 people finish the trial and at the end of the trial, the relapse rate in this population is found to be significantly lower than the control arm(standard of care). If you only consider the population that finished the study(what we call Perprotocol analysis) you'll be able to present data showing that the drug works and is actually a good one. BUT when you actually look at the everyone who participated(this is called Intention to Treat analysis), you'll find that people dropped out, and for a very significant reason!! This drug will probably not be prescribed by many physicians unless they have no choice. Bottomline is that data in a drug trial can be presented in a favourable way. Thats why its always important to look at the exact numbers, not just the %s given in an abstract. 
The above post was thanked by:  
Tags 
BiostatisticsEpidemiology, Step1Questions 
Thread Tools  Search this Thread 
Display Modes  

Similar Threads  
Thread  Thread Starter  Forum  Replies  Last Post 
The Zero value in Confidence interval?  tinhi  USMLE Step 1 Forum  5  07282014 06:52 AM 
95% confidence interval  Novobiocin  USMLE Step 2 CK Forum  4  07162012 07:33 AM 
Confidence Interval Question  Marikella  USMLE Step 1 Forum  6  07012012 01:35 AM 
confidence interval  laurier  USMLE Step 1 Forum  1  09222011 11:56 AM 
95% Confidence Interval  just_md  USMLE Step 1 Forum  3  05202010 04:10 AM 
