General household survey - Statistics South Africa
General household survey - Statistics South Africa
General household survey - Statistics South Africa
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
<strong>Statistics</strong> <strong>South</strong> <strong>Africa</strong> 49<br />
P0318<br />
Table 15: Most important differences between the questionnaires used for GHS 2010 and preceding<br />
years (concluded)<br />
GHS 2002–2008 GHS 2009–2011 Comparability<br />
Total number of rooms Number of individual rooms and total<br />
number of rooms<br />
Reason why do not pay for<br />
water<br />
All the options are different and now<br />
correspond with the in-house <strong>survey</strong> of<br />
DWAF<br />
Type of toilet facility The main components of the question<br />
remain the same; however, the structure<br />
Making a living from waste<br />
sold for recycling<br />
of the question was simplified<br />
The question was modified to specifically<br />
ask whether the <strong>household</strong> sells waste for<br />
recycling<br />
The options not applicable were added for<br />
Not good. Previous<br />
question was sometimes<br />
confused in the vernacular<br />
with ‘bedrooms’ and<br />
bathrooms and toilets<br />
were excluded<br />
None<br />
Use of<br />
Fair provided that some<br />
pesticides/herbicides <strong>household</strong>s who do not have yards editing can be done<br />
Cellular phone Before 2009 the question was whether None<br />
someone has access to a cellular phone;<br />
in 2009 the question asks whether it is<br />
available within the <strong>household</strong><br />
Assessment of the quality Before 2009 the question was asked of Not comparable<br />
of health services<br />
individuals who were sick and who used a<br />
specific service. However, because of<br />
proxy respondents it was difficult to get an<br />
accurate assessment of levels of<br />
Agricultural production<br />
satisfaction with the service. In 2009 the<br />
question very specifically relates to the<br />
respondents' own experience during their<br />
most recent visit<br />
The question before was general and did<br />
not specifically prod the interviewer to<br />
include small-scale activities such as<br />
backyard food gardening, etc. In 2009 all<br />
activities that relate to food production<br />
have to be included<br />
Not comparable<br />
Sources of income Income from a business was never listed<br />
as a separate source of income and was<br />
often not recorded or recorded under<br />
'Other'. In 2009 this option was added to<br />
the list<br />
Fair<br />
Monthly <strong>household</strong><br />
In 2009 the response categories were Good if categories are re-<br />
expenditure<br />
broken down into finer categories than combined<br />
before<br />
18.11 Editing and imputation<br />
Historically the GHS used a conservative and hands-off approach to editing. Manual editing, and little if any<br />
imputation was done. The focus of the editing process was on clearing skip violations and ensuring that<br />
each variable only contains valid values. Very few limits to valid values were set and data were largely<br />
released as it was received from the field.<br />
Good<br />
None<br />
With GHS 2009, Stats SA introduced an automated editing and imputation system that was continued for<br />
GHS 2010 and GHS 2011. The challenge was to remain as much as possible true to the conservative<br />
approach used prior to GHS 2009 and yet, at the same time, to develop a standard set of rules to be used<br />
during editing which could be applied consistently across time. When testing for skip violations and doing<br />
automated editing, the following general rules are applied in cases where one question follows the filter<br />
question and the skip is violated:<br />
<strong>General</strong> Household Survey, July 2011