In: Statistics and Probability
The researchers suggest that there are occupational differences in mean testosterone level. Medical doctors and university professors are two of the occupational groups for which means and standard deviations are recorded and listed in the following table.
Group | Sample size | Mean | StDev |
---|---|---|---|
MD | n1=6n1=6 | x¯1=11.21x¯1=11.21 | s1=3.73s1=3.73 |
Prof | n2=5n2=5 | x¯2=11.6x¯2=11.6 | s2=2.14s2=2.14 |
Let us denote:
Case 1: Assume that the population standard deviations
are unequal, i.e. σ1≠σ2σ1≠σ2.
What is the standard error of the difference in sample mean
x¯1−x¯2x¯1−x¯2? i.e. s.e.(x¯1−x¯2)=s.e.(x¯1−x¯2)= [answer to 4
decimal places]
Tries 0/5 |
Which of the following options gives the formula for 95%
confidence interval for μ1−μ2μ1−μ2?
−0.39∓1.86×s.e.(x¯1−x¯2)−0.39∓1.86×s.e.(x¯1−x¯2)
−0.39∓3.36×s.e.(x¯1−x¯2)−0.39∓3.36×s.e.(x¯1−x¯2)
−0.39∓2.9×s.e.(x¯1−x¯2)−0.39∓2.9×s.e.(x¯1−x¯2)
−0.39∓2.31×s.e.(x¯1−x¯2)−0.39∓2.31×s.e.(x¯1−x¯2)
−0.39∓1.4×s.e.(x¯1−x¯2)−0.39∓1.4×s.e.(x¯1−x¯2)
Tries 0/3 |
Are there significant difference between mean testosterone
levels of medical doctors and university professors?
no, because x¯1=x¯2x¯1=x¯2
yes, because x¯1≠x¯2x¯1≠x¯2
yes, because the entire 95% confidence interval for μ1−μ2μ1−μ2 does
not contain 0
no, because the 95% confidence interval for μ1−μ2μ1−μ2 contains
0
Tries 0/3 |
Case 2: Now assume that the population standard
deviations are equal, i.e. σ1=σ2σ1=σ2.
Compute the pooled standard deviation, spooledspooled [answer
to 4 decimal places]
Tries 0/5 |
Which of the following options gives the formula for 95%
confidence interval for μ1−μ2μ1−μ2 for pooled situation?
−0.39∓1.38×1.8922−0.39∓1.38×1.8922
−0.39∓3.25×1.8922−0.39∓3.25×1.8922
−0.39∓2.26×1.8922−0.39∓2.26×1.8922
−0.39∓1.83×1.8922−0.39∓1.83×1.8922
−0.39∓2.82×1.8922−0.39∓2.82×1.8922
Tries 0/3 |
What is the margin of error of the 95% pooled confidence interval of μ1−μ2μ1−μ2? [answer to 4 decimal places]
Tries 0/5 |
case I
Sample #1 ---->
mean of sample 1, x̅1= 11.21
standard deviation of sample 1, s1 =
3.73
size of sample 1, n1= 6
Sample #2 ---->
mean of sample 2, x̅2= 11.600
standard deviation of sample 2, s2 =
2.14
size of sample 2, n2= 5
difference in sample means = x̅1-x̅2 =
11.210 - 11.6000 =
-0.3900
std error , SE = √(s1²/n1+s2²/n2) =
1.7985
----------------
t-critical value = t α/2 = 2.31
confidence interval given by , difference of means ± critical value*s.e
−0.39 ∓ 2.31×s.e.(x¯1−x¯2)
------------------
no, because the 95% confidence interval for μ1−μ2 contains 0
================================================================================
Case II
pooled std dev , Sp= √([(n1 - 1)s1² + (n2 -
1)s2²]/(n1+n2-2)) = 3.1249
---------------
Degree of freedom, DF= n1+n2-2 =
9
t-critical value = t α/2 = 2.2622
std error , SE = Sp*√(1/n1+1/n2) =
1.8922
confidence interval is
−0.39∓2.26×1.8922
=======================================
margin of error, E = t*SE = 2.2622
* 1.8922 = 4.2804