Combining Three Estimates of Gross Domestic Product

Abstract

Much of the discussion about the state of the economy and many planning decisions have centred on the level and rate of growth of Real Gross Domestic Product (GDP).1 However, looking at the figures published by the government in the annual national income Blue Book we find that there are three figures which purport to measure the concept we call GDP. Furthermore, they are each revised in successive Blue Books as more information becomes available through various censuses and inquiries; these revisions are often fairly substantial, particularly in the first four to five years. Thus, although a great deal is made in the press about small changes in the figures, and one is led to believe from the economic literature that the budget surplus or deficit is determined on the basis of the figures of GDP, in fact we do not know the true figure to anything like the degree of accuracy that is implied by a debate about whether the inflationary gap is ?50m. or ?150m. Indeed, it is not clear in some years whether GDP has increased or fallen. For example, in 1958 the first set of figures published showed a fall of 075 and 065 per cent. respectively for the estimates from expenditure data and income data, but no change according to the estimate from output data. The second set of figures published a year later showed an increase of 009 per cent. according to output data and a fall of 1 11 per cent. according to income data. It was not until the fifth set of revised figures that the three estimates even agreed that there had been a fall in the level of GDP and even these were not the final figures. It should be noted that actual level of GDP is subject to more estimation error than the changes in the figures, a point which will be brought out later, although, of course, the figures for changes are more important to the economist. This profusion of estimates is not a criticism of the government statistical service as it must surely be a good thing that we know how reliable the figures are. If only one estimate were made, and if that were not revised, we would run the risk of having too much reliance placed upon inaccurate information. The three different estimates should warn us of the dangers of picking one estimate in one Blue Book in an arbitrary fashion and using this to test economic hypotheses. Their independence will be considered later in the article.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 122 citations exist upstream.