The need for independent statisticsBMJ 1997; 314 doi: https://doi.org/10.1136/bmj.314.7078.393r (Published 08 February 1997) Cite this as: BMJ 1997;314:393
Last week–after much government activity–Britain's Office for National Statistics withdrew from sale a document which showed that government spending on the NHS had fallen in real terms (p 395). Inevitably this episode gave rise to questions about the independence of national statistics.
Professor Adrian Smith, president of the Royal Statistical Society and professor of statistics and head of mathematics at Imperial College in London, says that the controversy highlights important points. “This has shown the potential confusion if statisticians are trying to communicate with government employees and ministers without an agreed vocabulary,” he said.
After 24 hours revised figures were released by the Office for National Statistics. The chart that had shown a fall in NHS spending in real terms of £1bn ($1.5bn) was replaced by a new one which showed that spending had risen by £2.4bn. The explanation given was that the first and incorrect …