Understanding 95% Confidence Interval & Total Width <2.0

Click For Summary
SUMMARY

The discussion focuses on determining the least number of tests required to achieve a 95% confidence interval for a normally distributed memory test result, with a total width of less than 2.0. The total width is defined as the difference between the upper and lower bounds of the confidence interval, specifically represented as 2a, where a must be less than 1. The solution involves using the Z-score corresponding to a 95% confidence level and solving for the sample size n using the formula P(mew-1 < X < mew+1) = 0.95.

PREREQUISITES
  • Understanding of normal distribution and Z-scores
  • Knowledge of confidence intervals and their calculations
  • Familiarity with statistical notation (e.g., mew, X)
  • Basic algebra for solving equations
NEXT STEPS
  • Learn how to calculate Z-scores for different confidence levels
  • Study the concept of sample size determination in statistics
  • Explore the implications of confidence intervals in hypothesis testing
  • Review the properties of normal distributions and their applications
USEFUL FOR

Statisticians, data analysts, students in statistics courses, and anyone involved in designing experiments or interpreting statistical results.

inv
Messages
46
Reaction score
0
[Solved]Is a stats question,just need some clarity on it-"total width of less than 2.

Homework Statement


Hi.The result of a memory test is known to be normally distributed with mean mew and standard deviation 1.0. It's required to have a 95% confidence interval for mew with a total width of less than 2.0.Find the least possible number of tests needed to achieve this.*The "total width of less than 2.0" mean what?


Homework Equations


?


The Attempt at a Solution


P(Z<2.0)=0.95
(X-mew)/(1.9/n^.5)<2.0,where X=the mean
mew<2.0
I'm stuck here,I'm sure something is wrong with it.So pls explain the thing with the * above?
 
Last edited:
Physics news on Phys.org
inv said:

Homework Statement


Hi.The result of a memory test is known to be normally distributed with mean mew and standard deviation 1.0. It's required to have a 95% confidence interval for mew with a total width of less than 2.0.Find the least possible number of tests needed to achieve this.*The "total width of less than 2.0" mean what?
Any confidence interval for the true mean is of the form [a,b]. The "total width" is b-a. In particular, if you take the interval to be symmetric about mew (since the normal distribution is symmetric about its mean) then you want [mew- a,mew+ a] with "total width"= 2a< 2 or a< 1.

Homework Equations


?


The Attempt at a Solution


P(Z<2.0)=0.95
(X-mew)/(1.9/n^.5)<2.0,where X=the mean
mew<2.0
I'm stuck here,I'm sure something is wrong with it.So pls explain the thing with the * above?
No, You want P(mew-1< X< mew+1)= 0.95. (X-mew)/(1.9/n^.5) with X= mew+ 1 gives z= 1/(1.9/n^.5)= n^.5/1.9. Look up the z score that gives .95/2 = .475 (for a table that uses only positive values) and then solve for n.
 
Thx.Problem solved~The End~
 

Similar threads

  • · Replies 3 ·
Replies
3
Views
1K
  • · Replies 22 ·
Replies
22
Views
3K
  • · Replies 2 ·
Replies
2
Views
8K
  • · Replies 11 ·
Replies
11
Views
3K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 1 ·
Replies
1
Views
14K
Replies
4
Views
2K