Death Dates-Converting MONTH and YEAR

[Ginny Natale]

Hi, Im doing survival analysis with secondary data. I have two variables [MONTH] and [YEAR] I also have Birth data. I can sort respondents by person number, Household ID


1) How do I transform these into a DEATHDATE

[Andrew Musau]

Hard to say. Do you have information on deaths?

[William Lisowski]

Perhaps your MONTH and YEAR are meant to be the month and year of death. In that case, the answer depends very much on what your birth data are like.

In order to get a helpful response, you need to show some example data.

Be sure to use the dataex command to do this. If you are running version 15.1 or later, or a fully updated version 14.2, dataex is already part of your official Stata installation. If not, run ssc install dataex to get it. Either way, run help dataex and read the simple instructions for using it. dataex will save you time; it is easier and quicker than typing out tables. It includes complete information about aspects of the data that are often critical to answering your question but cannot be seen from tabular displays or screenshots. It also makes it possible for those who want to help you to create a faithful representation of your example to try out their code, which in turn makes it more likely that their answer will actually work in your data.

When asking for help with code, always show example data. When showing example data, always use dataex.

[Sarah Edgington]

Assuming your month and year variables are month and year of death you don't need birth date to calculate date of death. You can create a monthly date as

gen deathdate=ym(year,month)
format deathdate %tm

If your goal is age at death then the birth date would matter.

Regardless of your goal I would highly recommend reviewing the FAQ for this forum. There is a lot of good information there on how to structure your question so that we can most easily help you, including information on showing sample data.

[Ginny Natale]

Sorry, I'm a new postdoc. I have never done survival models before. I am merging death data into a master data set that is long format. My time variable will be wavey (number of years in observation since wave 3 or baseline).

I have month and year of both birth and death. I also have date of initial interview so i know when they entered the study also. I am interested in knowing how long people survive following a probable stroke and probable Alzheimer's, in months. I have 12 waves of data from a large US dataset.

Things that are unique to this dataset -

STRL (probable time in years (linked to wavey) at which where stroke occurs)

FIT (model fit or stroke when stroke fits better it’s deviation from line)

WISTR (has a stroke-like decline observed in episodic memory data)

FITLIN (linear fit on aging pattern for that person)

wavey (number of years in observation since wave 3 or baseline)

ADRL (probable time in years (linked to wavey) at which where AD starts)

FITA (model fit or ADRD when ADRD fits better it’s deviation from linear)

IADR1 (unnecessary)

WIADR (don’t need this)

ADRD (has an AD-like decline observed in episodic memory data)

[Ginny Natale]

generate born= 12*BIRTHYR+BIRTHMO
generate ddied=12*KNOWNDECEASEDYR+KNOWNDECEASEDSOURCE
generate ALIVE1= ddied-born

[Ginny Natale]

dataex 1/5

1 invalid name

[Sarah Edgington]

try

dataex in 1/5

[Ginny Natale]

. dataex born ddied ALIVE1 in 1/5

----------------------- copy starting from the next line -----------------------

* Example generated by -dataex-. To install: ssc install dataex
clear
input float(born ddied ALIVE1)
23258 23941 683
23218 24013 795
23233 24157 924
23265 24181 916
23274     .   .
end

------------------ copy up to and including the previous line ------------------

Listed 5 out of 43216 observations

[Sarah Edgington]

I would probably recommend using Stata data variables to do the calculations but what you've done will work. You could do it this way with monthly dates.

gen born=ym(BIRTHYR,BIRTHMO)
gen ddied=ym(KNOWNDECEASEDYR,KNOWNDECEASEDSOURCE)
gen ALIVE1=ddied-born

Either way ALIVE1 is the number of months alive (or age at death in months).

As an aside, have you specified the variable for month of death correctly? I would expect the variable KNOWNDECEASEDSOURCE to be a variable telling you where the death information came from.