Non Linear regression

% name: myfun.m file

function yhat = myfun(beta,X)
b1 = beta(1); %(Feight multiplier)
b2 = beta(2); %(Freight rate multiplier)
e = X(1); %(Economic growth)
p = X(2); %(Previous year freight)
r = X(3); %(Real freight rate change)

yhat = p*(1.0+(e*b1))*(1.0+(r*b2));

inputs are

x=(11,3) Matrix
y= (11,1) Matrix
beta0 = rand(11,2) Matrix

when i run the script i get the following;

   beta = nlinfit(X,y,'myfun',beta0)
  ??? Error using ==> nlinfit at 127
  MODELFUN should return a vector of fitted values the same length as Y.

I dont understand what the error is can someone please help.

Thanks in advance

Answer 1

[Greg Heath]

% name: myfun.m file

function yhat = myfun(beta,X)

b1 = beta(1); %(Freight multiplier)

b2 = beta(2); %(Freight rate multiplier)

e = X(:,1); %(Economic growth)

p = X(:,2); %(Previous year freight)

r = X(:,3); %(Real freight rate change)

yhat = p.*(1.0+(e*b1)).*(1.0+(r*b2));

inputs are

x=(11,3) Matrix

y= (11,1) Matrix

beta0 = rand(11,1) Matrix

Hope this helps

Greg

Answer 2

[bym]

try changing these lines:

e = X(1); %(Economic growth)
p = X(2); %(Previous year freight)
r = X(3); %(Real freight rate change)

to

e = X(:,1); %(Economic growth)
p = X(:,2); %(Previous year freight)
r = X(:,3); %(Real freight rate change)

(untested)