NSCB - Notes on Official Poverty Statistics in the Philippines

Notes on the Official Poverty Statistics in the Philippines
Series TN 200307-SS1-02
July 2003

Annex 3

RELIABILITY OF ESTIMATES

Estimates in this publication are subject to non-sampling and sampling errors.

Non-sampling errors

Non-sampling errors may arise as a result of errors in the reporting, recording or processing of the data and can occur even if there is a complete enumeration of the population. Non-sampling errors can be introduced through: inadequacies in the questionnaire; non-response; inaccurate reporting by respondents; errors in the application of survey procedures; incorrect recording of answers; and errors in data entry and processing.

It is difficult to measure the size of the non-sampling errors and the extent of these errors could vary considerably in significance from survey to survey and from question to question. However, every effort is made in the design of the survey and development of survey procedures to minimize the effect of these errors.

Sampling errors

Sampling error is the error which occurs by chance because the data were only obtained from a sample, not the entire population.

STANDARD ERRORS

One measure of the variability of estimates which occurs as a result of surveying only a sample of the population is the standard error (SE).

There are about two chances in three (67%) that a survey estimate is within one SE of the figure that would have been obtained if all persons had been included, and about nineteen chances in twenty (95%) that it is within two SEs. That is, there are 19 chances in 20 that the figure that would have been obtained if al persons had been included is in the range:

X – 2SE(x) to x + 2SE(x)

(where x is the estimate).

The SE of an estimate can be obtained from the table T1 below. Linear interpolation should be used to calculate the SE of estimates falling between the sizes of estimates listed in the table.

RELATIVE STANDARD ERRORS

The SE can also be expressed as a percentage of the estimate and this is known as the relative standard error (RSE). The RSE is determined by dividing the SE of an estimate SE(x) by the estimate x and expressing it as a percentage. That is:

RSE = [(100 SE(x))/X]

(where x is the estimate). The RSE is a useful measure in that it provides an immediate indication of the percentage errors likely to have occurred due to sampling.

Proportions and percentages formed from the ratio of two estimates are also subject to sampling error. The size of the error depends on the accuracy of both the numerator and the denominator. The formula for the RSE of a proportion or percentage is:

RSE(x/y) = sqrt[[RSE(x)]2 – [RSE(y)]2]

For all tables in this publication, only estimates with RSE of 25 % or less, and percentages based on such estimates, are considered sufficiently reliable for most purposes. However, estimates and percentages with larger RSEs have been included and are preceeded by an * to indicate that they are subject to high SEs and should be used with caution. Estimates with RSEs greater than 50% should not be regarded as reliable, and are indicated by the symbol **.

AGE STANDARDISED VICTIMISATION RATE

To calculate this, first select the variable(s) to standardise by, e.g., employed persons. Then calculate the victimization rates for each age group of the standardizing variable (e.g., victimization rates for each age group of the persons employed). Next, multiply the victimization rate in each age group by the standard population in each age group to give the expected number of victims for each age group in the standard population. Finally, sum the expected numbers of victims and divide by the total standard population to give the standardization rate.

(Source: Crime and Safety, Australia, April 1998, Australian Bureau of Statistics)


E-mail the webmaster	Terms of Use	Home • Top of Page
	1997-2008, National Statistical Coordination Board Makati City, Philippines