6222.0 - Job Search Experience, Australia, Jul 2007  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 07/12/2007   
   Page tools: Print Print Page Print all pages in this productPrint All

TECHNICAL NOTE DATA QUALITY


INTRODUCTION

1 Since the estimates in this publication are based on information obtained from occupants of a sample of dwellings, they are subject to sampling variability. That is, they may differ from those estimates that would have been produced if all dwellings had been included in the survey. One measure of the likely difference is given by the standard error (SE), which indicates the extent to which an estimate might have varied by chance because only a sample of dwellings was included. There are about two chances in three (67%) that a sample estimate will differ by less than one SE from the number that would have been obtained if all dwellings had been included, and about 19 chances in 20 (95%) that the difference will be less than two SEs. Another measure of the likely difference is the relative standard error (RSE), which is obtained by expressing the SE as a percentage of the estimate.


2 Due to space limitations, it is impractical to print the SE of each estimate in the publication. Instead, a table of SEs is provided to enable readers to determine the SE for an estimate from the size of that estimate (see table T1). The SE table is derived from a mathematical model, referred to as the 'SE model', which is created using data from a number of past Labour Force Surveys. It should be noted that the SE model only gives an approximate value for the SE for any particular estimate, since there is some minor variation between SEs for different estimates of the same size.



CALCULATION OF STANDARD ERROR

3 An example of the calculation and the use of SEs in relation to estimates of persons is as follows. Table 4 shows the estimated number of unemployed women in Australia who were looking for full-time work was 131,400. Since this estimate is between 100,000 and 150,000, table T1 shows that the SE for Australia will lie between 4,000 and 4,700 and can be approximated by interpolation using the following general formula:


Equation: Calculation of standard errors


4 Therefore, there are about two chances in three that the value that would have been produced if all dwellings had been included in the survey will fall within the range 127,000 to 135,800 and about 19 chances in 20 that the value will fall within the range 122,600 to 140,200. This example is illustrated in the diagram below.

Diagram: Confidence intervals of estimates


5 In general, the size of the SE increases as the size of the estimate increases. Conversely, the RSE decreases as the size of the estimate increases. Very small estimates are thus subject to such high RSEs that their value for most practical purposes is unreliable. In the tables in this publication, only estimates with RSEs of 25% or less are considered reliable for most purposes. Estimates with RSEs greater than 25% but less than or equal to 50% are preceded by an asterisk (e.g. *3.4) to indicate they are subject to high SEs and should be used with caution. Estimates with RSEs of greater than 50%, preceded by a double asterisk (e.g. **0.3), are considered too unreliable for general use and should only be used to aggregate with other estimates to provide derived estimates with RSEs of less than 25%.



MEANS AND MEDIANS

6 The RSEs of estimates of mean duration of unemployment and median duration of unemployment are obtained by first finding the RSE of the estimate of the total number of persons contributing to the mean or median (see table T1) and then multiplying the resulting number by the following factors:

  • mean duration of unemployment: 1.6
  • median duration of unemployment: 2.5

7 The following is an example of the calculation of SEs where the use of a factor is required. Table 4 shows that the estimated median duration of unemployment for unemployed women in Australia was 12 weeks and shows that the number of unemployed women was estimated as 210,100. The SE of 210,100 can be calculated from table T1 (by interpolation) as 5,400. To convert this to an RSE we express the SE as a percentage of the estimate or 5,400/210,100 =2.6%.


8 The RSE of the estimate of median duration of unemployment for unemployed women is calculated by multiplying this number (2.6%) by the appropriate factor shown in the previous paragraph (in this case 2.5): 2.6 x 2.5 = 6.5%. The SE of this estimate of median duration of unemployment for unemployed women is therefore 6.5% of 12, i.e. almost one week. Therefore, there are two chances in three that the median duration of unemployment for women that would have been obtained if all dwellings had been included in the survey would have been within the range 11 weeks to 13 weeks, and about 19 chances in 20 that it would have been within the range 10 weeks to 14 weeks.



PROPORTIONS AND PERCENTAGES

9 Proportions and percentages formed from the ratio of two estimates are also subject to sampling errors. The size of the error depends on the accuracy of both the numerator and the denominator. A formula to approximate the RSE of a proportion is given below. This formula is only valid when x is a subset of y:


Equation: Calculation of relative standard errors of proportions and percentages


10 Considering the example from the previous page, of the 131,400 unemployed women who were looking for full-time work, 24,900 or 18.9% had been unemployed for one year or more. The SE of 24,900 may be calculated by interpolation as 2,500. To convert this to an RSE we express the SE as a percentage of the estimate, or 2,500/24,900 = 10.0%. The SE for 131,400 was calculated previously as 4,400, which converted to an RSE is 4,400/131,400 = 3.3%. Applying the above formula, the RSE of the proportion is:


Equation: Example calculation of relative standard errors of proportions


11 Therefore, the SE for the proportion of unemployed women looking for full-time work who had been unemployed for one year or more is 1.8 percentage points (=(18.9/100)x9.4). Therefore, there are about two chances in three that the proportion of unemployed women looking for full-time work who have been unemployed for one year or more is between 17.1% and 20.7% and 19 chances in 20 that the proportion is within the range 15.3% to 22.5%.



DIFFERENCES

12 Published estimates may also be used to calculate the difference between two survey estimates (of numbers or percentages). Such an estimate is subject to sampling error. The sampling error of the difference between two estimates depends on their SEs and the relationship (correlation) between them. An approximate SE of the difference between two estimates (x-y) may be calculated by the following formula:


Equation: Calculation of differences between estimates


13 While this formula will only be exact for differences between separate and uncorrelated characteristics or subpopulations, it is expected to provide a good approximation for all differences likely to be of interest in this publication.



STANDARD ERRORS

T1 STANDARD ERRORS OF ESTIMATES

NSW
Vic.
Qld
SA
WA
Tas.
NT
ACT
Aust.
Size of estimate (persons)
no.
no.
no.
no.
no.
no.
no.
no.
no.
%

100
290
250
250
150
160
100
90
140
100
100.0
200
380
330
330
210
220
140
150
180
180
90.0
300
440
390
390
250
260
180
190
200
240
80.0
500
540
470
470
300
330
220
250
230
350
70.0
700
620
540
540
350
380
260
300
260
430
61.4
1,000
710
620
610
400
440
300
350
280
540
54.0
1,500
830
730
710
470
520
340
410
320
690
46.0
2,000
920
810
790
530
590
370
460
340
820
41.0
2,500
1 000
900
850
550
650
400
500
350
900
36.0
3,000
1 100
950
900
600
700
400
500
400
1 000
33.3
3,500
1 150
1 000
950
650
750
450
550
400
1 100
31.4
4,000
1 200
1 050
1 000
700
750
450
600
400
1 200
30.0
5,000
1 300
1 150
1 100
750
850
500
650
450
1 300
26.0
7,000
1 500
1 300
1 250
850
950
550
750
500
1 550
22.1
10,000
1 700
1 500
1 400
950
1 100
650
950
600
1 800
18.0
15,000
2 000
1 750
1 600
1 100
1 250
800
1 300
750
2 100
14.0
20,000
2 200
1 950
1 800
1 200
1 400
950
1 600
850
2 300
11.5
30,000
2 600
2 300
2 050
1 450
1 600
1 250
2 150
1 100
2 650
8.8
40,000
2 850
2 550
2 250
1 700
1 750
1 500
2 750
1 350
2 900
7.3
50,000
3 100
2 800
2 450
1 900
1 950
1 750
3 250
1 500
3 100
6.2
100,000
4 050
3 600
3 400
2 900
3 050
2 600
5 850
2 050
4 000
4.0
150,000
4 800
4 350
4 250
3 700
4 100
3 200
8 300
2 350
4 700
3.1
200,000
5 550
5 200
5 100
4 400
4 950
3 650
10 700
2 450
5 300
2.7
300,000
7 100
6 800
6 800
5 450
6 250
4 300
15 450
2 550
6 350
2.1
500,000
9 950
9 300
9 550
6 900
7 950
5 150
. .
2 550
8 100
1.6
1,000,000
14 950
13 700
13 500
9 000
10 050
6 250
. .
. .
11 600
1.2
2,000,000
21 350
19 350
16 550
11 000
11 400
. .
. .
. .
17 150
0.9
5,000,000
31 500
28 550
17 350
13 000
11 500
. .
. .
. .
29 250
0.6
10,000,000
39 750
36 450
15 250
. .
. .
. .
. .
. .
39 200
0.4
15,000,000
. .
. .
. .
. .
. .
. .
. .
. .
44 050
0.3

. . not applicable

T2 Levels at which estimates have RELATIVE STANDARD ERRORS of 25% and 50%(a)

NSW
Vic.
Qld
SA
WA
Tas.
NT
ACT
Aust.
no.
no.
no.
no.
no.
no.
no.
no.
no.

25% RSE

Mean duration of unemployment
9 600
8 000
7 000
3 800
4 400
2 000
1 700
1 900
12 100
Median duration of unemployment
25 200
21 900
18 900
11 400
13 400
6 900
5 800
4 200
24 400
All other estimates
5 400
4 400
4 100
2 200
2 600
1 300
1 800
1 200
5 500

50% RSE

Mean duration of unemployment
3 100
2 600
2 400
1 300
1 400
700
500
700
3 400
Median duration of unemployment
8 300
7 100
6 600
4 000
4 500
2 500
1 900
1 600
8 000
All other estimates
1 800
1 400
1 400
700
800
400
500
400
1 200

(a) Refers to the number of people contributing to the estimate.