Source: MIL-OSI Submissions
14 April 2020
This report presents the results of an analytical retrospective superlative index time series based on the consumers price index (CPI) for the June 2002 and June 2020 quarters.
This work aims to assess 1) the impact of commodity substitution on the CPI, and 2) how the CPI may have tracked had it been reweighted less frequently than the three-yearly cycle currently used.
Results show that substitution bias has an upward effect on the CPI, and that if the CPI were reweighted less frequently, the index would be higher. Key findings from the report are summarised below.
- The published CPI, which is calculated using a fixed-weight Laspeyres-type formula, increased 41.6 percent between the June 2002 and June 2020 quarters, an average of 2.0 percent per year.
Impact of substitution bias
- The analytical superlative time series, calculated using a Fisher formula, increased 37.7 percent between the June 2002 and June 2020 quarters, an average of 1.8 percent per year.
Impact of less frequent reweighting
- If no CPI reweights had happened after 2002, the CPI would have increased 50.4 percent between the June 2002 and June 2020 quarters, an average of 2.3 percent per year.
- If no CPI reweight had happened in 2017, the CPI would have increased 4.7 percent between the September 2017 and June 2020 quarters (an average of 1.7 percent per year), compared with an increase of 4.2 percent for the published CPI over the same period (an average of 1.5 percent per year).
- If the CPI had been reweighted every six years after 2002, the CPI would have increased 44.2 percent between the June 2002 and June 2020 quarters, an average of 2.1 percent per year.
Visit our website to read the full report: Analytical retrospective superlative index based on New Zealand’s CPI: 2020