Like many other countries, the United Kingdom (UK) produces a national consumer priceindex (CPI) to measure inflation. Presently, CPI measures are not produced for regions withinthe UK. It is believed that, using only available data sources, a regional CPI would not beprecise or reliable enough as an official statistic, primarily because the regional partitioning ofthe data makes sample sizes too small. We investigate this claim by producing experimentalregional CPIs using publicly available price data, and deriving expenditure weights from theLiving Costs and Food survey. We detail the methods and challenges of developing a regional CPI and evaluate its reliability. We then assess whether model-based methods such assmoothing and small area estimation significantly improve the measures. We find that a regional CPI can be produced with available data sources, however it appears to beexcessively volatile over time, mainly due to the weights. Smoothing and small areaestimation improve the reliability of the regional CPI series to some extent but they remain toovolatile for regional policy use. This research provides a valuable framework for thedevelopment of a more viable regional CPI measure for the UK in the future.
