dependent (response) variable independent (control) variable random error xy x1x1 y1y1 x2x2 y2y2...
DESCRIPTION
Estimator for : Estimator : Estimator for the Y value for given x: Estimators for parameters unbiased? Confidence intervals for the true parameters? Confidence interval for the Y(x) value: Estimate E(Y(x))? Hypothesis Testing? Quality of the model? Better model? (Sec. 11.2)TRANSCRIPT
xYDependent (response) Variable
Independent (control) Variable
Random Error
X Yx1 y1
x2 y2
… …xn yn
Raw Raw data:data:
nixY iii ,...,2,1 ,
Assumption:•i ‘s are independent normally distributed random variables with mean 0 and (common) variance 2.
Estimator for :xx
xy
SS
b̂
Estimator : xbYa ̂
Estimator for the Y value for given x: bxay ˆ
. ,
,1
,1
,1
1111
2
11
2
1
2
2
11
2
1
2
xbyaSS
b
yxn
yxyyxxS
yn
yyyS
xn
xxxS
xx
xy
n
ii
n
ii
n
iii
n
iiixy
n
ii
n
ii
n
iiyy
n
ii
n
ii
n
iixx
• Estimators for parameters unbiased?• Confidence intervals for the true
parameters?• Confidence interval for the Y(x) value:• Estimate E(Y(x))?• Hypothesis Testing?• Quality of the model? Better model?
(Sec. 11.2)
Air Velocity
x (cm/s)
Evaporation
Coefficient y
(mm2/s)20 0.1860 0.37
100 0.35140 0.78180 0.56220 0.75260 1.18300 1.36340 1.17380 1.65
• (Linear) relationship exists?• Linear relationship?• Prediction for x = 190 cm/s• Error?
x y x^2 y^2 xy 20 0.18 400 0.0324 3.6 60 0.37 3600 0.1369 22.2 100 0.35 10000 0.1225 35 140 0.78 19600 0.6084 109.2 180 0.56 32400 0.3136 100.8 220 0.75 48400 0.5625 165 260 1.18 67600 1.3924 306.8 300 1.36 90000 1.8496 408 340 1.17 115600 1.3689 397.8 380 1.65 144400 2.7225 627
Sum 2000 8.35 532000 9.1097 2175.4
Sxx 132000 Slope b0.00382
9Syy 2.13745 Intercept a 0.069242Sxy 505.4
xbxay 00383.00692.0ˆ
80.0)190(00383.00692.0)190(ˆ
y
nibxay iii ,...,2,1 ,ˆ Residuals:
Residual sum of squares (or Error Sum of Squares):
xx
xyyy
n
iii
n
ii S
SSbxaySSE
2
1
2
1
2ˆ
Estimator for 2:
22
nSSEse
Standard Error of the Estimate:
2nSSEse
xx
xy
SS
b ̂
Distribution of b (as a statistic):)2(~)(
ntSsb
xxe
• Confidence interval for the true population slope is
• To test the null hypothesis H0: = 0, use the statistic (with df = n – 2.)
• Only when the null hypothesis H0: = 0 is rejected, the independent variable x can be included in the model.
xxe Ssntb 1)2(2/
xxe
Ss
bt )( 0
Distribution of a (as a statistic):
• Confidence interval for the true population intercept is
• To test the null hypothesis H0: = 0, use the statistic (with df = n – 2.)
• Only when the null hypothesis H0: = 0 is rejected, the nonzero intercept can be included in the model.
xx
e Sx
nsnta
2
2/1)2(
20 )(
xnS
nSs
atxx
xx
e
xbYa ̂
)2(~)(2
ntxnS
nSsa
xx
xx
e
Inference about E[Y(x)] = Inference about E[Y(x)] = + + x, the mean of x, the mean of the response value for given x.the response value for given x.
.1
,2
2
xxSxx
nbxaVar
xbxaE
Confidence interval for E[Y(x)] is
xx
e Sxx
nstbxa
2
2/1
where t-distribution has df = n – 2.
To predict the “future” Y(x), we use the interval
xx
e Sxx
nstbxa
2
2/11
where t-distribution has df = n – 2.
Note:•Confidence interval for Y(x) is wider than the confidence interval for E[Y(x)];•Width of the confidence intervals for Y(x) and E[Y(x)] depend on the x value. (Limit of prediction.)
Excel Outputs:SUMMARY OUTPUT
Regression StatisticsMultiple R 0.95148137R Square 0.9053168Adjusted R Square 0.8934814Standard Error 0.15905212Observations 10
es
Coefficients Standard Error t Stat P-value Lower 95% Upper 95%Intercept 0.06924242 0.100973708 0.685747071 0.5122514 -0.163603363 0.302088211x 0.00382879 0.000437777 8.745986838 2.286E-05 0.002819273 0.004838302
Estimators a and b
xx
e Sx
ns
21
xxe Ss 1
T-score in Hypothesis
Tests
P-values in Hypothesis
Tests
95% Confidence
Intervals for and
• Compare with the critical t-value(s);
• Compare with the value;
• Check if the interval contains zero.