How to use nonlinear least squares regression for a vector function?

[Jeffrey Weiner]

I am trying to fit the function:
Revenue_i(time) = A0/(1+exp(-A1*(time-A2))) + B*Costs_i

I have 5,000 observations of Revenue and Costs for 8 time periods (time = 0,1,...7).

A0, A1, A2, and B are constants that I am trying to fit.

I am unsure of how to fit this function in Stata using the nl command. Does anybody have suggestions?

If I were to drop the term "B*Costs_i" would I be able to fit the function using the average value of Revenue across all 5000 observations for each time period?

[Phil Bromiley]

You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex. Have you carefully studied the nl pdf documentation? It seems straightforward.