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.

Table 6.3 Measures of the Quality of Roster Matches That Are Not Definitive, Given<br />

That One Side Had a Definitive Match (as Shown by the Conditions Provided<br />

in Table 6.2)<br />

Weakest Measure Allowed<br />

Measure<br />

for Other <strong>Pair</strong> Member<br />

Number Description In Code Observed<br />

11 Age within 10, gender matched exactly, with MBRSEL 8 4<br />

missing for all roster members, provided another roster<br />

member with a closer age could not have been chosen<br />

12 Everything missing, but the other pair member had good 9 3<br />

data<br />

13 Age missing, gender matched exactly, household sizes 9 8<br />

equal<br />

14 Age, gender, <strong>and</strong> relationship code matched exactly for<br />

two roster members, with two MBRSELs identifying the<br />

two roster members (one was r<strong>and</strong>omly selected) 1 8 Not observed<br />

15 Age, gender, <strong>and</strong> relationship code matched exactly for 8 0<br />

two roster members, but MBRSEL was missing for all<br />

roster members (one was r<strong>and</strong>omly selected)<br />

16 Age <strong>and</strong> gender matched exactly for two or more roster 8 0<br />

members, <strong>and</strong> MBRSEL was missing for all roster<br />

members (one with matching relationship code was<br />

r<strong>and</strong>omly selected)<br />

17 Age within one <strong>and</strong> gender matched exactly for two<br />

8 Not observed<br />

(one was r<strong>and</strong>omly selected) 1<br />

roster members, both with the same relationship code,<br />

with two MBRSELs identifying the two roster members<br />

18 Age within one <strong>and</strong> gender matched exactly for two<br />

8 Not observed<br />

roster members, both with the same relationship code,<br />

but MBRSEL was missing for all roster members (one<br />

was r<strong>and</strong>omly selected)<br />

19 Age within one, gender off, with exactly one MBRSEL<br />

correctly identifying the other pair member, <strong>and</strong> only<br />

two members in household<br />

10 0<br />

20 No matches possible, but relationship codes indicate the<br />

pair is not a part of a domain of interest<br />

21 Age matches exactly, gender off, with MBRSEL<br />

missing for all roster members<br />

As with other<br />

pair member<br />

As with other<br />

pair member<br />

9 Not observed<br />

22 No matches possible 9 5<br />

1<br />

Since the 2001 survey, it was technically impossible to identify more than one roster member as the "other pair member<br />

selected," resulting in either 0 or 1 MBRSEL for each responding pair. As a result, measures #14 <strong>and</strong> #17 did not occur in the<br />

2006 survey.<br />

31

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

Saved successfully!

Ooh no, something went wrong!