Forum: help

Monitor Forum | Start New Thread

Nested Flat Threaded Ultimate

Show 25 Show 50 Show 75 Show 100

RE: Confidence Intervals for estimated Marginal Cost [ Reply ] By: Arne Henningsen on 2018-03-30 08:09

[forum:45801]

You can use the Delta method [1] to calculate approximate standard errors of the marginal costs and then you can use these standard errors to calculate approximate confidence intervals of the marginal costs. There is not yet a ready-made function available for this. You could consider to add such a function to the frontier or micEcon package -- it is easier than you think and I could assist you with this. [1] https://en.wikipedia.org/wiki/Delta_method

Confidence Intervals for estimated Marginal Cost [ Reply ] By: Antonio Robles on 2018-02-15 09:32

[forum:45662]

Dear professor Henningsen, first of all thank you so much for this great, easy to use, package. While presenting my work, someone raised the question about why I did not have confidence intervals for my estimated marginal costs. I have not seen previously any confidence intervals for them so I did not estimate them. I estimated a translog (single product) cost function with 3 inputs and time trend. I used the Z variable approach with time effects. I have searched how to estimate the CI but I did not find any good responses. ¿How could I estimate them? ¿Is there any built-in function to do it? Thank you.