How to deal with missing values of categorical variables

[Sa Li]

Dear scholar
i am using the demographic surveys. Some data about the Children's nationality are missing. I do not really want to just drop it. I was trying to find their parents' nationality to make it. Because i just classify the nationality into minorities and majorities. But it seems negligible. The survey is from 1991-2015. maybe i can find this child's nationality from the following waves.

However, at the same time, i am using the panel data, the time period is also 1991-2015. I am really not sure on how to find the following nationality of this child.

Hope to receive your reply. Thanks!

[Maarten Buis]

that really depends on the exact structure of your data. Can you give us an example using dataex (see https://www.statalist.org/forums/help#stata and help dataex)?

[Sa Li]

Sure, thanks. It is panel data.

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

* Example generated by -dataex-. For more info, type help dataex
clear
input double(Idind wave NATIONALITY)
372302006022 1991 1
522303041006 1997 2
372304044004 1997 1
452404011121 2009 1
412403011121 2009 1
432301162005 2015 1
521203019081 2004 2
432301012142 2011 1
322302016122 2009 1
422203042101 2006 1
112201005003 2011 1
311204004162 2015 1
432201041003 1997 1
412301011141 2011 1
232404012122 2009 1
412402041003 1993 1
451204018142 2011 1
322103006031 1993 1
212303061162 2015 2
422401017031 1993 1
322403019032 1993 1
452104006101 2006 1
452104014141 2011 1
112104004004 2011 1
322102007022 1991 1
422304081004 2004 1
452303006031 1993 1
422303014123 2009 1
552103003006 2011 1
372102162003 2015 1
412204002021 1991 1
322302001162 2015 1
452102003163 2015 1
321105017161 2015 1
322402005122 2009 1
412404008042 1997 1
432201017142 2011 1
522402010041 1997 1
452204001062 2000 1
521108161003 2015 2
452402021122 2009 1
452301002021 1991 1
422101084142 2011 1
452401009061 2000 1
522404001021 1991 1
412102121141 2011 1
322101019022 1991 1
452103010121 2009 1
412104162006 2015 1
372104001161 2015 1
452102103163 2015 1
452402003102 2006 1
321201014083 2004 1
422303006032 1993 1
552202007004 2011 1
452303014162 2015 1
411108011141 2011 1
432203031003 1993 1
312102011003 2011 1
371108018101 2006 1
422304101003 2006 1
322105017101 2006 1
422401121003 2009 1
422101014102 2006 1
452402006142 2011 1
412202041004 1997 1
111401014003 2011 1
451203012161 2015 1
211102016022 1991 1
322201015021 1991 1
232402004102 2006 1
412303012162 2015 1
422202041003 1997 1
211101015021 1991 1
432301121003 2009 1
522103002082 2004 2
311201018005 2011 1
422303016021 1991 1
212302016101 2006 1
452302011164 2015 1
522203007142 2011 2
322302002142 2011 1
422304016031 1993 1
422402001022 1991 1
551203001006 2011 1
412403012102 2006 1
411103082005 1991 1
432201019083 2004 1
522202001142 2011 2
432304014102 2006 1
422104018032 1993 1
231103101162 2015 1
232404004004 1997 1
431201003032 1993 1
412304124004 2009 1
452304141005 2004 1
522303082004 2000 2
232404005003 1997 1
372301011021 1991 1
422403013032 1993 1
end
label values NATIONALITY nationality_label
label def nationality_label 1 "Han", modify
label def nationality_label 2 "Min", modify

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

Listed 100 out of 4721 observations
Use the count() option to list more