6227.0.55.002 - Experimental estimates of education and training performance measures based on data pooling, Survey of Education and Work, 2007 to 2010, Sep 2011  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 09/09/2011  First Issue
   Page tools: Print Print Page Print all pages in this productPrint All

NEA 10: ENGAGEMENT, 18-24 years

The discussion for this indicator is similar to that for the other engagement indicator, NEA 9 (engagement, 15-19 years). In this case the sample is somewhat larger since it covers 7 years rather than 5, and includes all people in the age group whereas NEA 9 includes only that component of the 15-19 year-old population that has left school.

The potential benefits of boosting the sample size through data pooling to provide more accurate point in time estimates and the capacity to measure change at the national level would be greatly enhanced if pooling were to occur over one year rather than two.


NATIONAL AND STATE/TERRITORY DATA

Based on standard single-year estimates, the proportion of 18 to 24 year olds fully engaged in employment or education or training at or above Certificate III was 75.5% in 2007 and 72.6% in 2010 (Datacube Table 1a).

At the national level for the total fully-engaged population aged 18-24 years, the RSE in 2010 ranged from 1.0% for single-year data to 0.9% for two-year pooled data and 0.7% for four-year pooled data (Table F below). As with NEA 9, the change over 2008 to 2009 but not 2009 to 2010 tested as statistically significant, and the change over the two years 2008 to 2010 tested as significant using both single year and pooled data (Datacube Table 1c).

When the fully engaged population was partitioned into its constituent parts (slightly differently from NEA 9): young people in full-time education/training only, full-time employment only and a mix of education/training and employment (full-time education combined with full time employment or part time education combined with part time employment), a fall in full-time employment was detected between 2008 and 2009, and between 2008 and 2010 using both single-year and pooled data. Moreover, pooled but not single-year data detected a significant rise in full-time education/training over 2008 to 2010. This reflected both a larger difference in the indicator values and lower RSEs in the pooled as compared with the single-year data (see tables 1a, 1b, 1c).

At the state/territory level, the relatively high single-year RSEs for 2010 of 5.2% for Tasmania and 4.1% for the NT, were reduced to 4.1% and 3.6% respectively under two-year pooling and to about 3% each under four-year pooling (Table F below). Despite gains in accuracy, there was little detection of statistically significant change using pooled data. Between 2008 and 2009, Victoria was the only jurisdiction to record a significant fall in full engagement among 18-24 year olds. This was reflected in a corresponding fall in full engagement between 2008 and 2009 based on pooled but not single-year data. Some change was detected in NSW, where full-time employment fell between 2008 and 2009 and between 2008 and 2010. Conversely, participation in full-time education/training in NSW rose between 2008 and 2010, according to the pooled but not single-year data (Datacube Table 2c).

TABLE F. DIFFERENCE IN ESTIMATES FOR 2010, change through data pooling (NEA 10)

Single-year

(2010)
2-year pooled

(2009-10)
4-year pooled

(2007-10)

'000
%
RSE of %
'000
%
RSE of %
'000
%
RSE of %
NSW
493.5
70.8
2.6
501.5
72.0
1.8
504.3
72.5
1.3
Vic.
424.2
75.6
1.6
412.3
73.8
1.5
420.0
74.8
1.0
Qld
316.9
72.1
2.7
322.6
73.2
1.9
325.1
73.9
1.4
SA
109.3
68.8
3.0
111.8
70.3
2.2
111.0
70.0
1.5
WA
170.8
74.6
2.6
172.5
75.2
1.9
174.1
75.9
1.2
Tas.
28.2
62.8
5.2
30.0
65.9
4.1
29.7
65.4
3.1
NT
16.2
71.3
4.1
16.1
70.5
3.6
15.9
70.8
3.0
ACT
33.0
84.8
2.3
32.3
82.8
2.9
33.1
84.3
2.2
Australia
1592.0
72.6
1.0
1599.1
73.0
0.9
1613.1
73.6
0.7



SOCIO-ECONOMIC STATUS

At the national level between 2008 and 2009 and between 2008 and 2010, statistically significant falls in full engagement among 18-24 year olds were detected in two SEIFA quintiles: Quintile 3 and Quintile 5 (the least disadvantaged) [1]. These falls were consistently recorded in single-year and pooled data. In addition, single-year data detected a fall in full engagement between 2008 and 2010 among young people in the most disadvantaged areas, Quintile 1 (Datacube Table 1c).

There were a small number of detectable changes by socioeconomic status in the larger states between 2008 and 2010. Data pooling over two years did not provide a clear benefit over single-year data. For instance, in Victoria, there was a detectable fall in full engagement among 18-24 year olds living in the least disadvantaged areas, Quintile 5, between 2008 and 2009 and a detectable rise between 2009 and 2010. This resulted in a mixed result over the two-year period 2008 to 2010, whereby no change was recorded based on single-year data but a significant fall based on pooled data (Datacube Table 3c). In NSW (single-year data) and Queensland (pooled data) there were significant falls between 2008 and 2010 in full engagement in Quintile 5 (Datacube Tables 2c, 4c). As noted in the section on NEA 9 (engagement, 15-19 years), the level of full engagement in employment and education/training generally follows a rising gradient from lowest to highest quintile. The detection of change in Quintile 5, therefore, is due not only to the magnitude of change but also to the smaller RSEs associated with the relatively large population base. The considerable falls in full engagement recorded in Tasmania in two quintiles between 2009 and 2010 are based on a small sample and may be due to sampling variability (Datacube Table 7c). See the section on significance testing for further explanation of sampling variability and measures of change.


FOOTNOTE

[1] SEIFA Index of Relative socioeconomic Disadvantage. For further information on this and other SEIFA Indexes, see Information Paper: An Introduction to Socio-Economic Indexes for Areas (SEIFA), 2006 (cat. no. 2039.0) (back to text)