1 Introduction | 2 Sampling methodology | 3 Questionnaire development and testing | 4 Fieldwork methods and interviewers | 5 Checks and audits | 6 Response rate and interview length | 7 Classifications and coding | 8 Survey weights | 9 Imputation | 10 Variance estimation and significance tests | References | A1 Response rate by interviewer experience | A2 Sample and population profiles | A3 ACNeilsen area sampling frame | A4 Effect of area unit population changes | A5 Derivation of eligibility probability estimate | A6 Investigation of incident dates | A7 Contact sheets | A8 Showcards | A9 Selected CAPI screenshots
The following tables compare the NZCASS sample profile, unweighted and after each stage of the weighting process, with the corresponding population proportions across various demographic characteristics.
Table A2.1 Sample and population profiles for variables used in post-stratification and raking
|
Unweighted |
Probability |
After non- |
Final weights |
Population |
|
|
% |
% |
% |
% |
% |
|
|
Urbanisation |
|||||
|
Auckland |
22.4% |
23.6% |
26.2% |
26.6% |
26.6% |
|
Other metropolitan cities |
18.1% |
19.2% |
18.4% |
21.6% |
21.6% |
|
Other main urban areas |
24.2% |
24.2% |
24.8% |
22.0% |
22.0% |
|
Secondary urban areas |
76% |
7.5% |
6 9% |
6 6% |
66% |
|
Rural/minor urban areas |
27.8% |
25.5% |
23.7% |
23.2% |
23.2% |
|
Age by gender |
|||||
|
Males 15-24 |
5.1% |
7.3% |
7.3% |
9 5% |
95% |
|
Males 25-39 |
9.9% |
9.8% |
9.8% |
12.5% |
12.5% |
|
Males 40-59 |
14.4% |
14.8% |
14.8% |
16.8% |
16.8% |
|
Males 60-69 |
5.8% |
5.5% |
5.5% |
5.1% |
5.1% |
|
Males 70+ |
5.5% |
4.9% |
4.9% |
4.7% |
4.7% |
|
Females 15-24 |
78% |
9 2% |
9 4% |
9 0% |
9 0% |
|
Females 25-39 |
16.8% |
15.3% |
15.4% |
13.3% |
13.3% |
|
Females 40-59 |
19.8% |
20.9% |
20.8% |
17.4% |
17.4% |
|
Females 60-69 |
6.6% |
6.0% |
5.9% |
5.3% |
5.3% |
|
Females 70+ |
8 4% |
6 2% |
6 1% |
6 3% |
6 3% |
|
Maori by age by gender |
|||||
|
Maori Males 15-39 |
5.6% |
4.2% |
4.3% |
3.8% |
3.8% |
|
Maori Males 40-59 |
3 7% |
2.4% |
2 5% |
18% |
1.8% |
|
Maori Males 60+ |
2.0% |
1.0% |
1.1% |
0.6% |
0.6% |
|
Maori Females 15-39 |
11.6% |
7.4% |
7.7% |
3 9% |
3.9% |
|
Maori Females 40-59 |
6.1% |
4.0% |
4.1% |
2.0% |
2.0% |
|
Maori Females 60+ |
2.3% |
1.3% |
1.3% |
0 6% |
0.6% |
|
Non-Maori |
68.6% |
79.7% |
78.9% |
87.3% |
87.3% |
|
Pacific |
|||||
|
Pacific |
4.1% |
5.4% |
5 6% |
57% |
5.7% |
|
Non-Pacific |
95.9% |
94.6% |
94.4% |
94.3% |
94.3% |
|
Asian |
|||||
|
Asian |
5.1% |
7 8% |
8 2% |
9 4% |
9 4% |
|
Non-Asian |
94.9% |
92 2% |
91.8% |
90 6% |
90.6% |
As expected, the weighted sample profiles for these variables match the population figures precisely.
Table A2.2 Sample and population profiles for other household characteristics
|
Unweighted |
Probability |
After non- |
Final weights |
Population |
|
|
% |
% |
% |
% |
% |
|
|
Number of usual residents in household |
|||||
|
One usual resident |
17.5% |
22.0% |
21.7% |
21.5% |
21.9% |
|
Two usual residents |
34.1% |
34.7% |
34.2% |
34.1% |
32.2% |
|
Three usual residents |
17.4% |
16.1% |
16.3% |
16.4% |
15.8% |
|
Four usual residents |
15.7% |
14.7% |
14.9% |
15.0% |
14.3% |
|
Five usual residents |
8.9% |
7.6% |
7.7% |
7.8% |
7.1% |
|
Six or more usual residents |
6.5% |
4.9% |
5.1% |
5.2% |
4.4% |
|
Tenure |
|||||
|
Owner-occupied |
64.3% |
68.1% |
67.4% |
67.4% |
67.8% |
|
Rented |
32.6% |
28.9% |
29.6% |
29.7% |
29.1% |
|
Provided free |
3.1% |
3.0% |
3.0% |
2.9% |
3.1% |
|
Presence of motor vehicle in household |
|||||
|
Have motor vehicle in household |
90.9% |
91.2% |
91.1% |
91.1% |
89.9% |
|
No motor vehicle |
9.1% |
8.8% |
8.9% |
8.9% |
10.1 % |
|
Broad region |
|||||
|
Upper North Island |
51.0% |
48.3% |
51.6% |
50.5% |
50.2% |
|
Lower North Island |
25.9% |
26.0% |
23.8% |
23.5% |
24.0% |
|
South Island |
23.1% |
25.7% |
24.6% |
26.0% |
25.8% |
|
NZ Deprivation Index |
|||||
|
Quintile 1 (least deprived) |
15.6% |
17.5% |
17.5% |
17.9% |
20.4% |
|
Quintile 2 |
16.3% |
18.0% |
17.8% |
17.9% |
19.9% |
|
Quintile 3 |
19.3% |
21.1% |
20.7% |
20.5% |
20.6% |
|
Quintile 4 |
21.9% |
21.8% |
21.8% |
21.9% |
21.0% |
|
Quintile 5 (most deprived) |
26.9% |
21.5% |
22.1% |
21.7% |
18.1% |
In general, the sample profiles on the household variables in Table A2.2 exhibited a close match with population figures. The biggest differences are that the sample contains too few households in the least deprived areas (quintiles 1 and 2), too many in the most deprived areas (quintiles 4 and 5), and too many larger households. These differences have been reduced by the weighting process, but not eliminated.
Table A2.3 Sample and population profiles for other personal variables
| Unweighted sample |
Probability weights only |
After non- response adjustment |
Final weights (after post- stratification / raking |
Population (2001 Census or 2006 estimates / projections) |
|
|
% |
% |
% |
% |
% |
|
|
Legal and social marital status (combined) |
|||||
|
legally married. or in a civil union |
43.8% |
50 7% |
50 5% |
50 8% |
50.8% |
|
Defacto relationship or living |
14 2% |
13 8% |
13 8% |
13.1% |
11.5% |
|
Single / Never married |
21.8% |
22 0% |
22 4% |
23 7% |
24.6% |
|
Widowed |
9.1% |
5 7% |
5 5% |
5 2% |
5.7% |
|
Divorced / Separated |
11.0% |
7 8% |
7.7% |
7 2% |
7.5% |
|
Employment status |
|||||
|
Employed |
55.7% |
59 0% |
58 9% |
60 1% |
598% |
|
Student[43] |
6 5% |
9 2% |
9 5% |
10 6% |
8 1% |
|
Occupation |
|||||
|
Legislators. Administrators and |
12 9% |
14 3% |
14 4% |
15 0% |
13 2% |
|
Professionals |
13 4% |
14 3% |
14 3% |
14 7% |
14 7% |
|
Technicians and Associate Professionals |
12 0% |
12 6% |
12 8% |
12 7% |
11.7% |
|
Clerks |
7.7% |
7.4% |
7.4% |
7.1% |
13.3% |
|
Service and Sales Workers |
15 8% |
14 0% |
14.1% |
13 4% |
14 8% |
|
Agriculture and Fishery Workers |
9 9% |
9 9% |
9 4% |
9 5% |
8 4% |
|
Trades Workers |
10.8% |
11.3% |
11.4% |
12 4% |
8.9% |
|
Plant and Machine Operators and |
10.4% |
9.9% |
9.8% |
9 5% |
8.8% |
|
Elementary Occupations |
6 9% |
6 2% |
6 2% |
5 7% |
6.2% |
|
Broad region |
|||||
|
Upper North Island |
51 0% |
50 9% |
54 2% |
53 5% |
50 8% |
|
Lower North island |
25.9% |
24 9% |
22 6% |
22 3% |
24.3% |
|
South Island |
231% |
24 2% |
23 2% |
24 2% |
25 0% |
|
Urbanisation |
|||||
|
Auckland |
22.4% |
26 4% |
29 2% |
30 5% |
28 7% |
|
Other metro cities |
18.1% |
19 3% |
18.4% |
19 2% |
21.5% |
|
Other main urban areas |
24 2% |
22 5% |
23 1% |
22 5% |
21 3% |
|
Secondary urban areas |
7.6% |
6.4% |
5 9% |
5 6% |
6.3% |
|
Rural/minor urban areas |
27 8% |
25 4% |
23 4% |
22 2% |
22 1% |
|
NZ Deprivation Index |
|||||
|
Quintile 1 (least deprived) |
15 6% |
18 2% |
18 3% |
19 5% |
21 0% |
|
Qumtile 2 |
16.3% |
17 5% |
17 2% |
18 3% |
19.8% |
|
Quintile 3 |
19 3% |
20 4% |
20 0% |
20 6% |
20 1% |
|
Qumtile 4 |
21.9% |
21.1% |
21 2% |
20 9% |
20 4% |
|
Quintile 5 (most deprived) |
26.9% |
22 8% |
23 3% |
20 6% |
18.6% |
The largest differences on the personal variables shown in Table A2.3 are that there are too few clerks and too many trades workers in the sample. This could indicate some difference in occupation coding procedures, although both the NZ Census and NZCASS used the same standard.
Other differences of note include an excess of people in the most deprived areas and the corresponding shortfall in the least deprived areas, too many people in Auckland and the northern North Island, too many de facto couples, too few singles, and too many students. The last three at least might be explained by definitional differences (who counts as a "student" is not clearly defined in the NZCASS question) or by missing data (nearly 10% of people did not state their legal or social marital status in the Census). Deprivation shows the same skews for people as were evident for households in Table A2.2, while the regional skews for people have occurred despite there being little difference in the household profiles.
Footnote
43 The "Student" figure taken from the Census is the number of those who studied 20 hours or more a week.