Page 223 - Invited Paper Session (IPS) - Volume 1
P. 223

IPS142 Jorge L. V. V. et al.
                      2
                                                                              3
            regulation  can be obtained from registers. There are other variables  that are
            not compulsory but have a great census tradition or big interest among the
            community  of  users;  in  almost  all  the  cases  it  is  possible  to  obtain  this
            information from registers.
                In a very schematic way, below are the sources used in 2016-PCF for the
            most representative variables of the Census, as well as some of their most
            relevant characteristics:
            Migration variables
                Method and sources: Population register, but because it was not put into
            operation until 1996, it is also necessary to use the 2001 exhaustive Census.
                General issues: In general, the quality of these variables is very high and all
            the information included in the 2011 Census questionnaire (years of arrival
            and previous places of residence) can be obtained from registers.
            Relationship between household members (and other derived variables)
                Method  and  sources:  The  starting  point  is  the  Padrón,  which  contains
            information about the people that live in the same household. In any case,
            information from the Tax Agency, Births and Marriages Bulletins, the Police
            Database  (father’s  and  mother’s  name  are  stored  for  every  person)  and
            previous Censuses are also used.
                General issues: For  each person it is investigated who is his/her father,
            mother,  spouse  and  other  relative.  Next,  derived  variables  related  to  the
            families, nuclei and structure of the household will be generated. In general,
            the search for father and mother (common surnames and certain restrictions
            of age and sex) is much simpler than the search for a couple. Regarding the
            couples, if they have a child living with them at home, they are much easier to
            detect.  In  other  more  complex  cases  (like  cohabiting  or  same-sex  couples
            without children), it will be necessary to establish a model of imputation that
            assigns couples to some situations of people living together.
            Educational attainment
                Method and sources: Padrón has information about this variable, but since
            its  quality  is  not  optimal  it  is  necessary  to  use  other  sources  like:  several
            registers  (diplomas,  graduated  people)  from  the  Ministry  of  Education,
            information stored in the Unemployment Register, 2001 and 2011 Census.
                General issues: Information of this variable will only be provided for people
            aged  15  or  more.  A  person  will  have  as  value  in  this  variable  the  highest
            educational  level  that  has  been  observed  in  the  different  sources.  Those
            residual cases that lack of educational level and also those ones that are kept
            in  doubt  among  several  values,  are  imputed  taking  into  account  the



            2  More details in:
             https://eur-lex.europa.eu/legal-content/EN/TXT/PDF/?uri=CELEX:32017R0543&rid=7
            3  For example some migration variables like year of arrival in the municipality or in the dwelling.
                                                               212 | I S I   W S C   2 0 1 9
   218   219   220   221   222   223   224   225   226   227   228