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.

3 The LFS sample size in August 2008 was approximately one-third smaller than the sample size in August 2007. This is due to an 11% sample reduction that was implemented from November 2007 to June 2008 based on the 2006 sample design, and an additional 24% sample reduction implemented in July 2008. In combination, the two sample reductions are expected to increase the standard errors for estimates from the supplementary surveys by approximately 22% at the broad aggregate level, relative to the 2001 sample design (standard errors will vary at lower aggregate levels). Detailed information about the sample reduction is provided in Information Paper: Labour Force Survey Sample Design, Nov 2007 (Second edition) (cat. no. 6269.0).


CALCULATION OF STANDARD ERROR

4 An example of the calculation and the use of SEs in relation to estimates of persons is as follows. Table 5 shows the estimated number of female part-time employees in main job was 1,982,800. Since this estimate is between 1,000,000 and 2,000,000, table T1 shows that the SE for Australia will lie between 13,450 and 19,550 and can be approximated by interpolation using the following general formula:



5 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 1,963,400 to 2,002,200 and about 19 chances in 20 that the value will fall within the range 1,944,000 to 2,021,600. This example is illustrated in the diagram below:

6 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%. Table T2 presents the levels at which estimates have RSEs of 25% and 50%.


MEANS AND MEDIANS

7 The RSEs of estimates of mean and median weekly earnings (see paragraph 21 of the Explanatory Notes) 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 for Australian estimates:

• mean weekly earnings: 0.9
• median weekly earnings: 1.0

8 The following is an example of the calculation of SEs where the use of a factor is required. Table 5 shows an estimate of 1,982,800 female part-time employees in main job and table 4 shows mean weekly earnings for the same group as $432. The SE of 1,982,800 was calculated previously as 19,400. To convert this to an RSE we express the SE as a percentage of the estimate, or 19,400/1,982,800 = 1.0%.

9 The RSE of the estimate of mean weekly earnings is calculated by multiplying this number (1.0%) by the appropriate factor shown in paragraph 7 (in this case 0.9): 1.0 x 0.9 =0.9%. The approximate SE of this estimate of mean weekly earnings of female part-time employees in main job is therefore 0.9% of $432, that is about $3.89. Therefore, there are two chances in three that the mean weekly earnings for female part-time employees that would have been obtained if all dwellings had been included in the survey would have been within the range $428.11 to $435.89, and about 19 chances in 20 that it would have been within the range $424.22 to $439.78.

10 Mean and median estimates produced from population estimates smaller than the values in T2 have RSEs larger than 25% and should be used with caution. Table T2 also indicates the size of the population estimates that would produce mean and medians with RSEs greater than 50% which are considered too unreliable for general use.


ALL OTHER ESTIMATES

11 All other estimates produced from population estimates smaller than the values in T2 have RSEs larger than 25% and should be used with caution. T2 also indicates the size of the population estimates with RSEs greater than 50% which are considered too unreliable for general use.


PROPORTIONS AND PERCENTAGES

12 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.



13 Considering the example from the previous page, the 1,982,800 females who were part-time employees in their main job represent 46% of the 4,323,000 female employees. The SE and RSE of 1,982,800 were calculated previously as 19,400 and 1.0% respectively. The SE for 4,323,000 calculated by interpolation is 29,700 which converted to a RSE is 29,700/4,323,000 =0.7%. Applying the above formula, the RSE of the proportion is:



14 Therefore, the SE for the proportion (46%) of female part-time employees is 0.3 percentage points (=(46/100)x 0.7). Therefore, there are about two chances in three that the proportion of female part-time employees was between 45.7% and 46.3%, and 19 chances in 20 that the proportion is within the range 45.4% to 46.6%.


DIFFERENCES

15 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:



16 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
									Aust.
	NSW	Vic.	Qld.	SA	WA	Tas.	NT	ACT	SE	RSE
Size of estimates (persons)	no.	no.	no.	no.	no.	no.	no.	no.	no.	%
100	340	330	250	200	250	130	80	120	120	120.0
200	450	430	370	270	330	180	120	190	220	110.0
300	540	510	450	320	390	220	160	240	300	100.0
500	660	620	570	390	480	270	200	310	440	88.0
700	760	710	670	450	550	310	240	350	550	78.6
1,000	880	810	780	520	630	360	270	380	700	70.0
1,500	1 030	950	930	600	730	410	320	420	890	59.3
2,000	1 150	1 060	1 040	670	820	450	360	440	1 050	52.5
2,500	1 250	1 150	1 150	750	900	500	400	450	1 200	48.0
3,000	1 350	1 250	1 200	800	950	500	400	500	1 300	43.3
3,500	1 450	1 300	1 300	800	1 000	550	450	500	1 400	40.0
4,000	1 500	1 400	1 350	850	1 050	550	450	550	1 500	37.5
5,000	1 650	1 500	1 450	950	1 150	600	500	600	1 700	34.0
7,000	1 850	1 700	1 650	1 050	1 300	700	600	650	1 950	27.9
10,000	2 150	1 950	1 850	1 200	1 500	800	750	800	2 300	23.0
15,000	2 500	2 250	2 050	1 350	1 700	950	1 050	950	2 650	17.7
20,000	2 750	2 500	2 250	1 500	1 900	1 150	1 300	1 100	2 950	14.8
30,000	3 200	2 900	2 600	1 800	2 150	1 450	1 850	1 450	3 350	11.2
40,000	3 550	3 200	2 850	2 050	2 400	1 700	2 300	1 700	3 650	9.1
50,000	3 850	3 500	3 150	2 300	2 650	1 950	2 800	1 900	3 900	7.8
100,000	4 900	4 550	4 300	3 450	3 900	2 750	4 800	2 550	4 900	4.9
150,000	5 750	5 550	5 300	4 400	5 150	3 300	6 600	2 900	5 700	3.8
200,000	6 600	6 450	6 200	5 200	6 150	3 700	8 250	3 050	6 400	3.2
300,000	8 300	8 300	7 850	6 400	7 750	4 200	11 300	3 200	7 600	2.5
500,000	11 650	11 500	10 600	8 000	9 850	4 850	. .	3 200	9 550	1.9
1,000,000	17 300	17 500	15 150	10 200	12 600	5 550	. .	. .	13 450	1.3
2,000,000	23 300	25 850	20 350	12 100	14 550	. .	. .	. .	19 550	1.0
5,000,000	29 700	41 350	27 450	13 650	15 200	. .	. .	. .	32 600	0.7
10,000,000	. .	. .	. .	. .	. .	. .	. .	. .	43 500	0.4
. . not applicable

T2 Levels at which estimates have RSEs 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 weekly earnings	7 000	6 200	4 900	2 400	3 800	1 300	500	1 500	7 600
Median weekly earnings	7 900	6 800	6 300	3 000	4 700	1 700	700	1 700	9 100
All other estimates	7 800	6 700	6 300	3 200	4 400	1 700	1 200	1 700	8 600
50% RSE
Mean weekly earnings	2 300	2 000	1 600	800	1 200	400	100	600	1 900
Median weekly earnings	2 600	2 200	2 100	1 000	1 600	600	200	700	2 400
All other estimates	2 500	2 200	2 100	1 000	1 400	600	300	700	2 300
(a) Refers to the number of people contributing to the estimate.