In: Statistics and Probability
Given are five observations for two variables, x and y. xi 1 2 3 4 5 yi 4 7 6 12 14 a. Using the following equation: 12.32a.jpg Estimate the standard deviation of ŷ* when x = 3. b. Using the following expression: 12.32b.jpg Develop a 95% confidence interval for the expected value of y when x = 3. c. Using the following equation: 12.32c.jpg Estimate the standard deviation of an individual value of y when x = 3. d. Using the following expression: 12.32d.jpg Develop a 95% prediction interval for y when x = 3.
X | Y | (x-x̅)² | (y-ȳ)² | (x-x̅)(y-ȳ) |
1 | 4 | 4.000 | 21.160 | 9.200 |
2 | 7 | 1.000 | 2.560 | 1.600 |
3 | 6 | 0.000 | 6.760 | 0.000 |
4 | 12 | 1.000 | 11.560 | 3.400 |
5 | 14 | 4.00 | 29.160 | 10.80 |
ΣX | ΣY | Σ(x-x̅)² | Σ(y-ȳ)² | Σ(x-x̅)(y-ȳ) | |
total sum | 15 | 43 | 10.000 | 71.20 | 25.000 |
mean | 3.00 | 8.60 | SSxx | SSyy | SSxy |
sample size , n = 5
here, x̅ = Σx / n= 3.00 ,
ȳ = Σy/n = 8.60
SSxx = Σ(x-x̅)² = 10.0000
SSxy= Σ(x-x̅)(y-ȳ) = 25.0
estimated slope , ß1 = SSxy/SSxx =
25.0 / 10.000 =
2.5000
intercept, ß0 = y̅-ß1* x̄ =
1.1000
so, regression line is Ŷ =
1.1000 + 2.5000 *x
SSE= (SSxx * SSyy - SS²xy)/SSxx =
8.700
std error ,Se = √(SSE/(n-2)) =
1.70294
-----------------------------------
a)
x=3
X̅ = 3.00
Σ(x-x̅)² =Sxx 10.0
standard dev of y^ , S(ŷ)=Se*√(1/n+(X-X̅)²/Sxx) = 0.762
b)
Sample Size , n= 5
Degrees of Freedom,df=n-2 = 3
critical t Value=tα/2 = 3.182 [excel
function: =t.inv.2t(α/2,df) ]
margin of error,E=t*Std error=t* S(ŷ) =
3.1824 * 0.7616 =
2.4237
Confidence Lower Limit=Ŷ +E = 8.600
- 2.4237 = 6.176
Confidence Upper Limit=Ŷ +E = 8.600
+ 2.4237 = 11.024
c)
standard dev, S(ŷ)=Se*√(1+1/n+(X-X̅)²/Sxx)
= 1.8655
d)
margin of error,E=t*std error=t*S(ŷ)=
3.1824 * 1.87 =
5.9368
Prediction Interval Lower Limit=Ŷ -E =
8.600 - 5.937 =
2.6632
Prediction Interval Upper Limit=Ŷ +E =
8.600 + 5.937 =
14.5368