Chapter 10 : Relationship of bat energy expenditure to mass and echolocation
Fit of LOG Expenditure on indicator variables with REG
The REG Procedure
Model: MODEL1
Dependent Variable: LExpend
Number of Observations Read
20
Number of Observations Used
20
Analysis of Variance
Source
DF
Sum of Squares
Mean Square
F Value
Pr > F
Model
3
29.42148
9.80716
283.59
<.0001
Error
16
0.55332
0.03458
Corrected Total
19
29.97480
Root MSE
0.18596
R-Square
0.9815
Dependent Mean
2.48220
Adj R-Sq
0.9781
Coeff Var
7.49187
Parameter Estimates
Variable
DF
Parameter Estimate
Standard Error
t Value
Pr > |t|
95% Confidence Limits
Intercept
1
-1.49770
0.14987
-9.99
<.0001
-1.81540
-1.17999
LMass
1
0.81496
0.04454
18.30
<.0001
0.72053
0.90938
TypeNON
1
-0.07866
0.20268
-0.39
0.7030
-0.50832
0.35100
TypeBIRD
1
0.02360
0.15760
0.15
0.8828
-0.31050
0.35770
Chapter 10 : Relationship of bat energy expenditure to mass and echolocation
Fit of LOG Expenditure on indicator variables with REG
The REG Procedure
Model: MODEL1
Test Test_of_intercepts Results for Dependent Variable LExpend
Source
DF
Mean Square
F Value
Pr > F
Numerator
2
0.01479
0.43
0.6593
Denominator
16
0.03458
Chapter 10 : Relationship of bat energy expenditure to mass and echolocation
Fit of log Expenditure on indicator variables with GLM
The GLM Procedure
Class Level Information
Class
Levels
Values
Type
3
1 2 3
Number of Observations Read
20
Number of Observations Used
20
Chapter 10 : Relationship of bat energy expenditure to mass and echolocation
Fit of log Expenditure on indicator variables with GLM
The GLM Procedure
Dependent Variable: LExpend
Source
DF
Sum of Squares
Mean Square
F Value
Pr > F
Model
5
29.46993221
5.89398644
163.44
<.0001
Error
14
0.50486800
0.03606200
Corrected Total
19
29.97480021
R-Square
Coeff Var
Root MSE
LExpend Mean
0.983157
7.650468
0.189900
2.482201
Source
DF
Type I SS
Mean Square
F Value
Pr > F
LMass
1
29.39190909
29.39190909
815.04
<.0001
Type
2
0.02957359
0.01478680
0.41
0.6713
LMass*Type
2
0.04844954
0.02422477
0.67
0.5265
Source
DF
Type III SS
Mean Square
F Value
Pr > F
LMass
1
3.37875389
3.37875389
93.69
<.0001
Type
2
0.04122472
0.02061236
0.57
0.5773
LMass*Type
2
0.04844954
0.02422477
0.67
0.5265
Parameter
Estimate
Standard Error
t Value
Pr > |t|
Intercept
-1.470515265
B
0.24767033
-5.94
<.0001
LMass
0.804657049
B
0.08668453
9.28
<.0001
Type 1
1.268067693
B
1.28542004
0.99
0.3406
Type 2
-0.110322504
B
0.38474216
-0.29
0.7785
Type 3
0.000000000
B
.
.
.
LMass*Type 1
-0.214874992
B
0.22362264
-0.96
0.3529
LMass*Type 2
0.030713281
B
0.10283304
0.30
0.7696
LMass*Type 3
0.000000000
B
.
.
.
The X'X matrix has been found to be singular, and a generalized inverse was used to solve the normal equations. Terms whose estimates are followed by the letter 'B' are not uniquely estimable.
Chapter 10 : Relationship of bat energy expenditure to mass and echolocation
Chapter 10 : Relationship of bat energy expenditure to mass and echolocation
Analysis of Covariance with GLM
The GLM Procedure
Class Level Information
Class
Levels
Values
Type
3
1 2 3
Number of Observations Read
20
Number of Observations Used
20
Chapter 10 : Relationship of bat energy expenditure to mass and echolocation
Analysis of Covariance with GLM
The GLM Procedure
Dependent Variable: LExpend
Source
DF
Sum of Squares
Mean Square
F Value
Pr > F
Model
5
29.46993221
5.89398644
163.44
<.0001
Error
14
0.50486800
0.03606200
Corrected Total
19
29.97480021
R-Square
Coeff Var
Root MSE
LExpend Mean
0.983157
7.650468
0.189900
2.482201
Source
DF
Type I SS
Mean Square
F Value
Pr > F
LMass
1
29.39190909
29.39190909
815.04
<.0001
Type
2
0.02957359
0.01478680
0.41
0.6713
LMass*Type
2
0.04844954
0.02422477
0.67
0.5265
Source
DF
Type III SS
Mean Square
F Value
Pr > F
LMass
1
3.37875389
3.37875389
93.69
<.0001
Type
2
0.04122472
0.02061236
0.57
0.5773
LMass*Type
2
0.04844954
0.02422477
0.67
0.5265
Parameter
Estimate
Standard Error
t Value
Pr > |t|
Intercept
-1.470515265
B
0.24767033
-5.94
<.0001
LMass
0.804657049
B
0.08668453
9.28
<.0001
Type 1
1.268067693
B
1.28542004
0.99
0.3406
Type 2
-0.110322504
B
0.38474216
-0.29
0.7785
Type 3
0.000000000
B
.
.
.
LMass*Type 1
-0.214874992
B
0.22362264
-0.96
0.3529
LMass*Type 2
0.030713281
B
0.10283304
0.30
0.7696
LMass*Type 3
0.000000000
B
.
.
.
The X'X matrix has been found to be singular, and a generalized inverse was used to solve the normal equations. Terms whose estimates are followed by the letter 'B' are not uniquely estimable.
Chapter 10 : Relationship of bat energy expenditure to mass and echolocation