In: Statistics and Probability
Consider the data set:
|
For this data we do not know how T depends on L. We hope that T is proportional to some power of L. Transform data by taking Logarithms and do linear regression. Upon computing the regression round to one decimal.
1.What is the slope?
2.What is R2? Use two decimals
3.Predict the value of T when L = 4.7 Use one decimal
Result:
For this data we do not know how T depends on L. We hope that T is proportional to some power of L. Transform data by taking Logarithms and do linear regression. Upon computing the regression round to one decimal.
1.What is the slope?
Slope=3.1674
2.What is R2? Use two decimals
R square = 0.8432
84.32% of variance in T is explained by regression.
3.Predict the value of T when L = 4.7 Use one decimal
The regression line is T= 2.0671+3.1674*log(L)
When L= 4.7
Predicted T = 2.0671+3.1674*log(4.7) =4.195902755
= 4.2 ( one decimal)
Excel used for calculations:
Excel Addon Megastat used.
Menu used: correlation/Regression ---- Regression Analysis.
Regression Analysis |
|||||||
r² |
0.8432 |
n |
20 |
||||
r |
0.9183 |
k |
1 |
||||
Std. Error of Estimate |
0.3772 |
Dep. Var. |
T |
||||
Regression output |
confidence interval |
||||||
variables |
coefficients |
std. error |
t (df=18) |
p-value |
95% lower |
95% upper |
|
Intercept |
a = |
2.0671 |
0.132 |
15.710 |
0.0000 |
1.791 |
2.344 |
logL |
b = |
3.1674 |
0.322 |
9.840 |
0.0000 |
2.491 |
3.844 |
ANOVA table |
|||||||
Source |
SS |
df |
MS |
F |
p-value |
||
Regression |
13.777 |
1 |
13.777 |
96.82 |
0.0000 |
||
Residual |
2.561 |
18 |
0.142 |
||||
Total |
16.339 |
19 |