I have defined the following function:
def GMM(s1, s2, s3, s4, s5, a):
"""The GMM objective function.
Arguments
---------
si: float
standard deviations of preference distribution
a: float
marginal utility of residutal income
Paramters
---------
Px: array (1,ns)
projector onto nonprice characteristic space
xk, z: arrays (J, 5) and (J, 12)
nonprice char. and instruments
invW: array (12, 12)
GMM weight matrix
Returns
-------
float."""
delta = invert(s1, s2, s3, s4, s5, a, delta0) # Invert market shares to get mean utility
bmean = np.dot(Px, delta) # Project delta onto charancteristic space
xihat = delta - np.dot(xk, bmean) # Compute implied unobservable prod. quality
temp1 = np.dot(xihat.T, z)
if np.any(np.isnan(delta)) == True:
value = 1e+10
else:
value = np.dot(np.dot(temp1, invW), temp1.T)
return np.sqrt(value)
My question pertains to the variable delta bound inside of the function. Outside of the function I will set the initial value of delta0. Now, ultimately I will minimize this function. What I would like to have happen is that each time the function GMM evaluates, delta from the previous evaluation is used as the new delta0. I tried defining delta0 as a global variable, but it did not seem to work... likely this was my error though. Although, I have read here that generally this is a bad approach. Any suggestions?