|Page tools: Print Page|
Imputation Flag for Number of Males and Females in Dwelling
Quality Statement - Imputation Flag for Number of Males and Females (IFNMFD)
There are many aspects which can affect the quality of Census data; the following information should be considered when viewing data on Imputation Flag for Number of Males and Females (IFNMFD).
Most occupied private dwellings (95.8%) return a completed form so the number of persons, by sex is known. For the remainder, consisting of non-responding dwellings, a count of males and females needs to be established. The Collector was able to obtain a count of males and females for a further 1.40% (of occupied private dwellings), leaving 2.8% where the number of males and females was imputed. Checks are made to ensure that Imputation Flag for Number of Males and Females (IFNMFD) has identified the correct records (that is, all records where male and female counts were not collected but are still required).
Collectors sometimes find it difficult to determine whether dwellings are occupied or unoccupied on Census Night, and where there is insufficient information to make this distinction the dwelling normally will be deemed to be occupied. The ABS plans to do further analysis on the proportion of non-responding dwellings which may have been unoccupied on Census night, as the resultant imputation for these dwellings would produce an overcount of persons.
For the purposes of imputation the count of males and females should be a "Census Night count" (a count of persons staying at the dwelling on Census Night). Realistically, however, the count provided to the Collector may on occasions be a "Usual resident count" (a count of all persons usually residing in the dwelling). A "usual resident count" may result in a small overcount in cases where usual residents are temporarily absent and enumerated elsewhere, (and to a lesser extent an undercount if there were visitors staying at the dwelling on Census Night). Once again, the ABS plans to do further analysis on this issue to determine its possible impact.
The ABS aims to produce high quality data from the Census. To achieve this, extensive effort is put into Census form design, collection procedures, and processing procedures.
There are four principal sources of error in Census data: respondent error, processing error, partial response and undercount. Quality management of the Census program aims to reduce error as much as possible, and to provide a measure of the remaining error to data users, to allow them to use the data in an informed way.
When completing their Census form, some people do not answer all the questions which apply to them. In these instances, a 'not stated' code is allocated during processing, with the exception of non-response to age, sex, marital status and place of usual residence. These variables are needed for population estimates, so they are imputed using other information on the Census form, as well as information from the previous Census.
The processing of information from Census forms is now mostly automated, using scanning, Intelligent Character Recognition and other automatic processes. Quality assurance procedures are used during Census processing to ensure processing errors are kept at an acceptable level. Sample checking is undertaken during coding operations, and corrections are made where necessary.
The Census form may be completed by one household member on behalf of others. Incorrect answers can be introduced to the Census form if the respondent does not understand the question or does not know the correct information about other household members. Many of these errors remain in the final data.
More detailed information on data quality is available in the 2006 Census Dictionary (cat. no. 2901.0), in the section titled Managing Census Quality.