Our monthly estimates of GDP suggest that output rose by 0.2% three months ending in August after a decline of 0.3% in the three months ending in July. This is the first time our GDP indicator has been higher over a three month average since May of 2008 and re-inforces our view that the recession ended in May of this year. There may well be a period of stagnation now, with output rising in some months and falling in others; the end of the recession should not be confused with a return to normal economic conditions. Our track record in producing early estimates of GDP suggests that our projection for the most recent three-month period has a standard error of 0.1-0.2% point when compared to the first estimate produced by the Office for National Statistics. This comparison can be made only for complete calendar quarters. Outside calendar quarters the figures are less reliable than this and they are also likely to be less accurate in the current disturbed economic circumstances.
A paper describing the methodology used to produce the data was published in the February 2005 volume of the Economic Journal. From April until October 2006 our estimates were computed using the Index of Services published by ONS. However this monthly series shows considerable volatility which has caused us some problems in estimating GDP. From our November 2006 press release we have therefore reverted to using a model of private services output based on indicator variables. This means that, while all our figures for calendar quarters are fully coherent with ONS data, our estimates of monthly private service output are not. The series can be thought of as indicating the underlying value of the ONS series. The figures for the profile of the economy in 1930-1934 have been revised after Dr Solomou of Cambridge University kindly pointed out some extra data we could take into account. As a consequence the 1930s recession now appears deeper than we had previously thought.
For more information please telephone Martin Weale on 020 7654 1945.