Scribd
Upload
9 views3 pages

SAS Nonlinear Regression Example

This document outlines a SAS program for nonlinear regression analyzing wolf predation rates as a function of food supply. The model used is the type II functional response, with parameters estimated through the Gauss-Newton method. The results indicate a significant relationship between the variables, with estimates for parameters a and b being 3.3720 and 0.4705, respectively.

Uploaded by

Sushant
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views3 pages

SAS Nonlinear Regression Example

This document outlines a SAS program for nonlinear regression analyzing wolf predation rates as a function of food supply. The model used is the type II functional response, with parameters estimated through the Gauss-Newton method. The results indicate a significant relationship between the variables, with estimates for parameters a and b being 3.3720 and 0.4705, respectively.

Uploaded by

Sushant
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

/* SAS program to perform nonlinear regression.

*/
/* Response variable y is wolf predation rate (average */
/* number of moose killed per wolf per 100 days. */
/* Predictor variable x is food supply (average number */
/* of moose per thousand square kilometers). */
/* Model is "type II functional response": */
/* */
/* E(y) = a*x/(b + x). */
/* */
/* Here a and b are positive parameters. */
/* Data from wolf ranges across North America assembled */
/* by Messier (1994 Ecology). */
options nocenter ls=72;
data;
input x y;
cards;
0.17 0.37
0.23 0.47
0.23 1.90
0.26 2.04
0.37 1.12
0.42 1.74
0.66 2.78
0.80 1.85
1.11 1.88
1.30 1.96
1.37 1.80
1.41 2.44
1.73 2.81
2.49 3.75
;
proc nlin;
parameters a=3.5 b=.5;
model y=a*x/(b+x);
run;
The NLIN Procedure
Dependent Variable y
Method: Gauss-Newton

Iterative Phase
Sum of
Iter a b Squares
0 3.5000 0.5000 4.8025
1 3.3815 0.4751 4.7807
2 3.3736 0.4712 4.7806
3 3.3723 0.4706 4.7806
4 3.3721 0.4705 4.7806
5 3.3720 0.4705 4.7806
NOTE: Convergence criterion met.

Estimation Summary
Method Gauss-Newton
Iterations 5
R 2.514E-6
PPC(b) 4.933E-6
RPC(b) 0.000031
Object 2.93E-10
Objective 4.780561
Observations Read 14
Observations Used 14
Observations Missing 0
NOTE: An intercept was not specified for this model.

Sum of Mean Approx


Source DF Squares Square F Value Pr > F
Model 2 57.3099 28.6550 71.93 <.0001
Error 12 4.7806 0.3984
Uncorrected Total 14 62.0905
Approx Approximate 95% Confidence
Parameter Estimate Std Error Limits
a 3.3720 0.6717 1.9086 4.8355
b 0.4705 0.2665 -0.1101 1.0512

Approximate Correlation Matrix


a b
a 1.0000000 0.9081861
b 0.9081861 1.0000000

You might also like