Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Identifying the nearest observation in a household survey

From   "Deborah Garvey" <>
To   <>
Subject   st: Identifying the nearest observation in a household survey
Date   Wed, 20 Apr 2005 17:32:19 -0700

Hi, all.

I am using the IPUMS 2000 5% Census Public Use Microdata.  The data are in a flat file.  The unit of observation is an individual with common household information appended. Households are uniquely identified by SERIAL, persons by SERIAL and PERNUM (location in the household). 

The US census only reports a person's relationship to the household head in the variable RELATED.  IPUMS has linked some children to parents using a series of algorithms.  I'm trying to extend the IPUMS parent linking variables for some children (those of partners of the HH head, for example) for whom IPUMS reports no parent in the household.  

I can't use a simple egen(max) or egen(min) command with argument RELATED to link a possible parent in cases where there are two or more potential parents.  This occurs when multiple non-relatives live in a household.  I want the adult who is listed before the child in the household record, since Census/sociology research shows he/she is most likely to be the parent.

An example:

serial     pernum     nfams     famunit famsize   related              age     sex  marital
2411276          1         6           1            1   Head/Householder   88   F  widow
2411276          2         6           2            1   Other non-relatives 49   M single
2411276          2         6           3            2   Other non-relatives 49   M married
2411276          3         6           3            2   Other non-relatives  42  F  married 
2411276          4         6           4            1   Other non-relatives    6  F  single 
2411276          5         6           5            1   Other non-relatives  68  F widow
2411276          6         6           6            1   Other non-relatives  58  M widow 

The child in line #4 is most likely the child of #2 and #3.  Can someone help me get started?  I'm running Stata/SE 8.2, Windows, born 1/10/05.

Thanks kindly,


Deborah Garvey, Ph.D.
Department of Economics
Kenna Hall
Santa Clara University
Santa Clara, CA  95053
408/554-2331 (FAX)

This message scanned for viruses and SPAM by GWGuardian at SCU (MGW1)

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index