Page 1 of 1

Simulating WTP for normal dist. param when price is negative log normal/

Posted: 22 Mar 2024, 10:24
by manes
Hi,

I estimated a MMNL which converged successfully. I am trying to simulate WTP for the ASC (ASC_low) which is normally distributed. My cost parameter is negatively log-normal distributed.
this is the code:

Code: Select all

N <- 10000
b_low = rnorm(N, mean=model$estimate["asc_low_mu"], sd=model$estimate["asc_low_sig"])
b_cost = exp(rlnorm(N, mean=model$estimate["b_log_cost_mu "], sd=model$estimate["b_log_cost_sig"] ))
wtp_low = b_low/b_cost
mean(wtp_low); sd(wtp_low)
I received:
[1] NaN
[1] NA
I'm not sure what could be the reason for this.
These are the estimated values:
b_log_cost_mu = 1.186
b_log_cost_sig = -1.579

asc_low_mu = 1.5071
asc_low_sig = 2.7057
Thanks,
Anat

Re: Simulating WTP for normal dist. param when price is negative log normal/

Posted: 05 May 2024, 11:10
by stephanehess
Annat

can you show us the model estimates too? It might be that you need to take the absolute values of the sigma parameters as the estimates might have been negative

Also, you're missing the minus sign in front of the exponential

Stephane