generating a variable with a custom transformation

[Jinsoo Bae]

Hi, I am analyzing auction data with Stata.

What I would like to do is to generate a variable of equilibrium-bid from a variable called value.

value includes integers from 1 to 100. And I would like to generate equilibrium-bid from value. Unfortunately, I do not have an analytic form of bidding function. Instead, I have a numerical approximation of the bid function (ex 1-> 1.4, 2-> 1.7, 3-> 2.3, ......). So technically, I can generate equilibrium-bid by typing the following.

gen equilibrium-bid = 1.4 if value == 1
replace equilibrium-bid = 1.7 if value == 2
replace equilibrium-bid = 2.3 if value == 3
............
and so on.

But the problem is I have 100 types of values, so it will be inefficient to type 100 lines. Is there any ways to do the same job more conveniently?

Thanks,
Jinsoo

[Clyde Schechter]

Using the data editor, create a new data file that contains 100 observations. The first variable is called value and ranges from 1 to 100. Call the second variable equilibrium_bid and type in the corresponding numbers for equilibrium_bid. (Note the _, not -, because - is not legal in a variable name, but _ is.) Save this data set. Let's call it equilibrium_function.dta. Now use your original data set and

merge m:1 value using equilibrium_function

[Jinsoo Bae]

Thank you! merge will do the job!!