Converting continuous variable into categorical

[Ivana Rozic]

Hi, I am new to STATA and would really appreciate if someone could advise me on the following:
I would like to generate a new categorical variable that would correspond to histogram bins.
I have 200759 observations, 7064 bins (0.005 widths); min value of the variable is -19.80374 and maximum 15.48759.

I've tried gen with autocode but getting missing values
Thanks.

[David Radwin]

Have you looked at this article?

Harrison, D. A. (2005). Stata tip 20: Generating histogram bin variables. Stata Journal, 5(2):280-281.
https://www.stata-journal.com/sjpdf....iclenum=gr0014

Also please see FAQ #18 on how to spell Stata: https://www.statalist.org/forums/help#spelling

[Ivana Rozic]

Thank you for your help.

I've tried the following code in Stata

twoway__histogram_gen Et, start(-19.805) width(0.005) frequency gen(h x)

and it worked.
However, it seems that bins without the observations are excluded from the x variable. Could you please advise me how I could get them as well.

[David Radwin]

I'm not sure what you expect this function to produce for values of x with no observations. Do you want a value of x with a corresponding value of h equal to zero?

[Ivana Rozic]

Thanks for the reply.
What I would like to get is the following:
If for example,

var1
1
2
3
5
8
10

I would like to get a list of all possible bins from 0 to 10. So I would like to get bins 4, 6, 7 & 9 as well.

[David Radwin]

I'm not sure I understand. If you want to add 4 more observations, setting x to the values you showed and h to zero, you could do

set obs `=_N+4'
replace x = 4 in `=_N-3'
replace x = 6 in `=_N-2'
replace x = 7 in `=_N-1'
replace x = 9 in `=_N'
replace h = 0 in `=_N-3'/`=_N'

Otherwise, I don't think I, or other Statalist members, can give you any further useful advice without a better understanding of your data. Please follow the instructions in item 12.2 of https://www.statalist.org/forums/help#stata on using dataex to show some example data.

[Ivana Rozic]

Thank you.