TECHNICAL NOTE 2 DIFFERENCES IN CLASSIFICATION


DIFFERENCES IN CLASSIFICATION BETWEEN THE PES AND CENSUS

1 Occasionally, the answers obtained for a person in the PES interview are not consistent with the answers obtained for the equivalent questions in the Census. There are a number of reasons why a response may differ, including:

• a person may have difficulty answering a question for themselves or another household member, either in the Census or the PES;
• a person may interpret the question differently in the Census, where forms are self-completed for the majority of Australia, compared to the PES which is administered by a trained interviewer;
• different people may provide Census and PES responses;
• the correct response could change between the Census and PES. Changes in age can be taken into account using the actual date of birth, but other changes, for example if the person is married or divorced, may not be identified; and
• the Census may contain a 'not-stated', or imputed, response while the PES will have a valid response.

2 This difference in classification is most prevalent for the Indigenous status and Country of birth responses, as these are missing in a number of Census forms, and imputation is not carried out for either of these variables in the Census.

3 The two tables below contain unweighted PES counts of the differences in classification between PES and Census for Indigenous status and Country of birth responses. These tables are counts of all responding people in the PES and include a record for each match made between the PES and Census where a difference in Indigenous status or Country of birth classification has occurred. The match status in the tables only includes those matches used in estimation.

4 The majority of person matches between PES respondents and their corresponding Census records show the same responses for Indigenous status. For example, 93.6% of matched people who reported as Indigenous in the PES also reported as Indigenous in the Census, and 98.4% of those who reported as non-Indigenous in the PES also reported as non-Indigenous in the Census.

DIFFERENCE IN CLASSIFICATION(a), Indigenous status - Responding PES persons - 2011
		PES RESPONSE
		Indigenous		Non-Indigenous		Total
Census response		no.	%	no.	%	no.	%
Matched		5 428	100.0	83 517	100.0	88 945	100.0
	Indigenous	5 083	93.6	316	0.4	5 399	6.1
	Non-Indigenous	268	4.9	82 160	98.4	82 428	92.7
	Not stated	77	1.4	1 041	1.2	1 118	1.3
(a) This table excludes 1,104 not matched Indigenous persons and 7,358 not matched non-Indigenous persons.

5 Similarly, for Country of birth, the majority of person matches between PES and the corresponding Census record show the same response, with 97.3% of matched people who reported as overseas born in the PES also counted as overseas born in the Census, and 97.9% of matched people who reported as Australian born in the PES, also counted as Australian born in the Census.

DIFFERENCE IN CLASSIFICATION(a), Country of birth - Responding PES persons - 2011
		PES RESPONSE
		Australia		Overseas		Total
Census response		no.	%	no.	%	no.	%
Matched		68 484	100.0	20 461	100.0	88 945	100.0
	Australia	67 039	97.9	179	0.9	67 218	75.6
	Overseas	210	0.3	19 906	97.3	20 116	22.6
	Not stated	1 235	1.8	376	1.8	1 611	1.8
(a) This table excludes 5,737 not matched persons who responded in the PES as Australian-born and 2,725 not matched persons who responded in the PES as Overseas-born.

6 The PES used an estimation technique to adjust the weights of responding persons according to their PES-reported categories. This ensured that PES persons not responding in the Census received the same weight adjustments as similar responding persons. The Census categories were then used in producing sample-based estimates of the number of persons counted in the Census. The weighting ensured these estimates matched the actual Census counts for all benchmark categories (for information on benchmarking, see Estimation).