§ Mr. Edward DaveyTo ask the Chancellor of the Exchequer (1) if he will review the methodology for adjusting for quality improvements in the calculation of the Retail Prices Index; and if he will make a statement; [137865]
(2) what research his Department has undertaken on the matter of hedonic price indices; and if he will make a statement. [137864]
§ Miss Melanie JohnsonThe information requested falls within the responsibility of the National Statistician. I have asked him to reply.
Letter from John Pullinger to Mr. Edward Davey, dated 30 November 2000:
The National Statistician has been asked to reply to your recent questions on the methodology for adjusting for quality improvements in the Retail Price Index (RPI) (137865) and hedonic price indices (137864). I am replying in his absence.
The Office for National Statistics (ONS) does not currently use hedonic regression techniques to correct for changes in quality of new goods in the RPI sample. However, changes in quality are allowed for in two ways. Firstly, explicitly using option costs for computers. In this case the actual costs of individual changes of specification in the computer are recorded, and 50 per cent of this cost is applied to the price of an item as the value of the quality change. Secondly, for all other items, we make an implicit adjustment. In this case when a new item is selected during price collection, to replace an item no longer available, any price change, above that seen in other goods of this type, is assumed to be related to quality changes.
However the ONS is actively participating in discussions about which methods are most appropriate for quality adjusting price indices. As part of the ongoing methodological research programme for the RPI, the ONS is looking closely at the question of adjustments for quality changes in new goods introduced into the index, whether these be improvements or reductions in quality. This work involves a technical assessment of the current methodology used in the RPI, comparing this with practices in other countries and evaluating which methodology is most appropriate for the UK.
As part of this work we are examining techniques either used by other National Statistics Offices, or recommended by academics, to see if they are of potential use in the UK. In particular, we are looking at whether the hedonic regression techniques adopted in the USA, and other countries, would be suitable for the UK, both theoretically and practically. The research will not, necessarily, recommend a single quality adjustment technique, but rather may recommend different solutions for different product groups.
938WThis work is taking place in close collaboration with Eurostat, other National Statistical Offices, and the academic community to ensure that results are based on a strong foundation, and can be used to allow International comparisons to be made.
The results will also be taken into account in the work on methodological improvements for the Producer Price Index (PPI).
This work is progressing, and the results will be published when reliable conclusions have been reached.