X | Y | (x-x̅)² | (y-ȳ)² | (x-x̅)(y-ȳ) |
825 | 40 | 12996.00 | 74.225 | 982.154 |
830 | 42 | 11881.00 | 43.763 | 721.077 |
890 | 49 | 2401.00 | 0.148 | -18.846 |
895 | 46 | 1936.00 | 6.840 | 115.077 |
890 | 44 | 2401.00 | 21.302 | 226.154 |
910 | 48 | 841.00 | 0.379 | 17.846 |
915 | 46 | 576.00 | 6.840 | 62.769 |
960 | 43 | 441.00 | 31.533 | -117.923 |
990 | 53 | 2601.000 | 19.225 | 223.615 |
1010 | 52 | 5041.000 | 11.456 | 240.308 |
1012 | 54 | 5329.000 | 28.994 | 393.077 |
1030 | 57 | 8281.000 | 70.302 | 763.000 |
1050 | 58 | 12321.000 | 88.071 | 1041.692 |
ΣX | ΣY | Σ(x-x̅)² | Σ(y-ȳ)² | Σ(x-x̅)(y-ȳ) | |
total sum | 12207 | 632 | 67046.000 | 403.1 | 4650 |
mean | 939.00 | 48.62 | SSxx | SSyy | SSxy |
sample size , n = 13
here, x̅ = Σx / n= 939.00 ,
ȳ = Σy/n = 48.62
SSxx = Σ(x-x̅)² =
67046.000000
SSxy= Σ(x-x̅)(y-ȳ) = 4650.0
estimated slope , ß1 = SSxy/SSxx =
4650.0 / 67046.000
= 0.0694
intercept, ß0 = y̅-ß1* x̄ =
-16.5093
so, regression line is Ŷ =
-16.5093 + 0.069 *x
SSE= (SSxx * SSyy - SS²xy)/SSxx =
80.574
std error ,Se = √(SSE/(n-2)) =
2.70646
a)
confidence interval for intercept
α= 0.01
DF=n-2 = 11
t critical value=t α/2 = 3.1058 [excel
function: =t.inv.2t(α/2,df) ]
estimated std error of slope =Se(ßo) =
Se*√(1/n+x̅²/Sxx)=
9.8435
margin of error ,E= t*std error =
30.5719
lower confidence limit = ß̂o - E = -16.5093
- 30.5719 = -47.081
upper confidence limit= ß̂o + E = -16.5093
+ 30.5719 = 14.063
b)
confidence interval for slope
α= 0.01
t critical value= t α/2 =
3.106 [excel function: =t.inv.2t(α/2,df) ]
estimated std error of slope = Se/√Sxx =
2.70646 /√ 67046.00
= 0.010
margin of error ,E= t*std error = 3.106
* 0.010 = 0.032
estimated slope , ß^ = 0.0694
lower confidence limit = estimated slope - margin of error
= 0.0694 - 0.032
= 0.037
upper confidence limit=estimated slope + margin of error
= 0.0694 + 0.032
= 0.102
c)
Predicted Y at X= 876 is
Ŷ = -16.509 +
0.069 * 876 =
44.246
d)
X Value= 876
Confidence Level= 95%
Sample Size , n= 13
Degrees of Freedom,df=n-2 = 11
critical t Value=tα/2 = 2.201 [excel
function: =t.inv.2t(α/2,df) ]
X̅ = 939.00
Σ(x-x̅)² =Sxx 67046.0
Standard Error of the Estimate,Se= 2.71
Predicted Y at X= 876 is
Ŷ = -16.509 +
0.069 * 876 =
44.246
For Individual Response Y
standard error, S(ŷ)=Se*√(1+1/n+(X-X̅)²/Sxx) =
2.8848
margin of error,E=t*std error=t*S(ŷ)=
2.2010 * 2.88 =
6.3494
Prediction Interval Lower Limit=Ŷ -E =
44.246 - 6.3494 =
37.897
Prediction Interval Upper Limit=Ŷ +E =
44.246 + 6.3494 =
50.595
Show work please. An article in the Tappi Journal (March, 1986) presented data on green liquor NazS concentration (in grams per liter) and paper machine production (in shown as follows y 40 42 49...