Rodgers, J. R., Statistically Significant Changes in the Poverty-Rate, 1997-98 to 2002-03, Department of Economics, University of Wollongong, 2007.
Sampling variation should be taken into account when sample data are used to estimate changes in the poverty rate over time. This paper reports poverty rates and their standard errors, calculated using data from the 1997-98 and 2002-03 Surveys of Income and Housing, and tests whether the poverty rate in Australia has changed significantly over this time period. The results depend on where the equivalised poverty line is set and whether its real value is held constant. With a constant real poverty line, a decrease in the poverty rate is observed and, except at low poverty thresholds, the reduction is statistically significant. However, with a relative poverty line set equal to half the median, or half the mean, current income, a significant increase in the poverty rate is observed, which is due to an increase in the average real income of the Australian population between the two survey dates.