21.06.2014 Views

Questionnaire Dwelling Unit-Level and Person Pair-Level Sampling ...

Questionnaire Dwelling Unit-Level and Person Pair-Level Sampling ...

Questionnaire Dwelling Unit-Level and Person Pair-Level Sampling ...

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

1. The counts disagreed if a household member left or entered the household between<br />

interviews. As before, the roster that was closest to the screener was used to<br />

determine the count. In particular, depending upon the domain, the count of<br />

household members within the age range of the siblings being counted was compared<br />

between each pair member <strong>and</strong> the screener. The multiplicity count from the pair<br />

member with the count closest to the screener was used, provided that the member<br />

had no bad relationship codes within the relevant age range.<br />

2. If the counts of household members within the age range of the siblings being<br />

counted differed between pair members <strong>and</strong> those counts were both exceeded by the<br />

screener count, then the multiplicity associated with the pair member with the age<br />

range count closest to the screener was chosen, provided that the member had no bad<br />

relationship codes within the relevant age range.<br />

3. In some cases, the counts of household members within the age range of the siblings<br />

being counted were the same for the two pair members, but the multiplicity counts<br />

disagreed.<br />

a. If one pair member had bad relationship codes <strong>and</strong> the other did not, the<br />

disagreement could have been due to the bad relationship codes. If the sum of the<br />

multiplicity count <strong>and</strong> the number of bad relationship codes were equal across<br />

pair members, then the final count was set equal to the multiplicity of the pair<br />

member who did not have bad relationship codes.<br />

b. If one pair member identified the other as "sibling" but the other pair member did<br />

not reciprocate, then imputation was required to establish whether the relationship<br />

was sibling-sibling. The count associated with the pair member who indicated that<br />

the other pair member was a sibling should have been chosen as the final count. In<br />

effect, this was done by taking the maximum of the two pair members' counts.<br />

4. If the counts of household members within the age range of the siblings being<br />

counted disagreed <strong>and</strong> both exceeded the screener count of household members<br />

within the relevant age range, then the multiplicity count was set to the screener<br />

count. If the screener roster had missing exact ages, then the minimum multiplicity<br />

count from the two pair members' rosters was used as the final count.<br />

5. If differing multiplicity counts could not be reconciled with the above rules, upper<br />

<strong>and</strong> lower bounds for the true multiplicity were determined using the two multiplicity<br />

counts, as well as the counts of children within relevant age ranges in both pair<br />

member's rosters <strong>and</strong> the screener roster. In rare cases, the values for these bounds<br />

were equal. These cases were investigated, <strong>and</strong> if the reasons were legitimate, then<br />

the final multiplicity count was set to this value. Otherwise, the final multiplicity was<br />

left to imputation.<br />

R-6

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!