Hi,
At the process of matching various datasets, I have encountered that many of my data has missings. For that reason, I would like to know whether you might know a good approach for it. I have already tried with the formulas exposed here ( https://www.stata.com/support/faqs/d...issing-values/ ) but none go forwards one period (eg.
by person_id (year month), sort: replace myvar = myvar[_n-1] if myvar >= . ). My main intention is to take upwards my first non missing data (in this case 1995 month 1) to span all over the time period for every individual in the sample.
My data has the following structure:
If you could provide me any hint on how to fill it up for every person id, I would be really grateful,
Regards,
Miguel
At the process of matching various datasets, I have encountered that many of my data has missings. For that reason, I would like to know whether you might know a good approach for it. I have already tried with the formulas exposed here ( https://www.stata.com/support/faqs/d...issing-values/ ) but none go forwards one period (eg.
by person_id (year month), sort: replace myvar = myvar[_n-1] if myvar >= . ). My main intention is to take upwards my first non missing data (in this case 1995 month 1) to span all over the time period for every individual in the sample.
My data has the following structure:
| person_id | Year | Month | myvar |
| 1 | 1980 | 1 | . |
| 1 | 1980 | 2 | . |
| 1 | 1980 | 3 | . |
| 1 | 1980 | 4 | . |
| 1 | 1980 | 5 | . |
| 1 | 1980 | 6 | . |
| 1 | 1980 | 7 | . |
| 1 | 1980 | 8 | . |
| 1 | 1980 | 9 | . |
| 1 | 1980 | 10 | . |
| 1 | 1980 | 11 | . |
| 1 | 1980 | 12 | . |
| 1 | .... | .... | .... |
| 1 | 1995 | 1 | 50 |
| 1 | 1995 | 2 | 52 |
| 1 | ... | .... | ... |
If you could provide me any hint on how to fill it up for every person id, I would be really grateful,
Regards,
Miguel
Comment