Estimating birth date from age

This code demonstrates an algorithm for estimating birth date from age. We cannot know the exact birth date, but we can get close: the maximum error is half a year, and the typical error is one quarter of a year.



/* The %age macro was taken from the Internet---maybe from here http://support.sas.com/kb/24/808.html ? */
%macro age(date,birth);
floor ((intck('month',&birth,&date) - (day(&date) %mend age;

/*
Generate 10000 fake people with random birth dates and random perspective days
on which their age was measured. Then, calculate age from that perspective date.
In reality, there is some seasonality to births (e.g., more births in July), but
here we assume each day of the year has an equal distribution of births.
*/
data person;
format birth_date submit_date yymmdd10.;
do i = 1 to 10000;
birth_date = %randbetween(19000,20500);
submit_date = birth_date + %randbetween(0,100*365);
age = %age(submit_date, birth_date);
output;
end;
drop i;
%runquit;

/* Work in reverse from age to estimated birth date. */
data reverse;
set person;
format birth_date_min birth_date_max yymmdd10.;
birth_date_min = intnx('years', submit_date, -1 * (age+1), 's') - 1;
birth_date_max = intnx('years',birth_date_min,1,'s') + 1;

/* check range of estimates for errors */
min_error = (birth_date > birth_date_min);
max_error = (birth_date < birth_date_max);

/* estimate birth date as the middle of the range */
birth_date_avg = mean(birth_date_min, birth_date_max);

/* calculate variance */
abs_days_error = abs(birth_date - birth_date_avg);
%runquit;

/* Both errors should always be zero. */
proc freq data=reverse;
table min_error max_error;
quit;

/* Error of estimates range from 0 to 183.5 with a median of 92 and average of 91.*/
proc means data=reverse n nmiss min median mean max;
var abs_days_error;
quit;

/* Distribution of errors is uniform */
proc sgplot data=reverse;
histogram abs_days_error;
quit;

Tested with SAS 9.4M6

For more posts like this, see Heuristic Andrew.

Meet My SAS

My SAS is a brand-new customer experience page. This new location takes a variety of customer service places and puts them in one interface. The goal of My SAS is to ensure all SAS customers have the best possible experience available in the marketplace.

Meet My SAS was published on SAS Users.

Append and Replace Records in a CAS Table

In my previous blog post, I talked about using PROC CAS to accomplish various data preparation tasks. Since then, my colleague Todd Braswell and I worked through some interesting challenges implementing an Extract, Transform, Load (ETL) process that continuously updates data in CAS. (Todd is really the brains behind getting […]

Append and Replace Records in a CAS Table was published on SAS Users.

Ignore This Blog Post

The Little SAS Book, Sixth Edition is now a year old.  I have already written posts about What’s New in this edition, and the very cool XLSX LIBNAME engine.  So what more is there to say?  A lot, it turns out.  The Sixth Edition was our biggest rewrite since the Second Edition introduced the new […]