The shock 0.4% further drop in GDP in the third quarter reflects falls of 0.7% and 0.2% in industrial and services output respectively. Industrial weakness had already been signalled by August production numbers but the services decline is a big surprise and at odds with recent stronger purchasing managers' survey results (although the coverage of this survey is narrower than that of the GDP figures).

August monthly figures for services output were also released today. The July / August average of this series, which feeds directly into the GDP numbers, was 0.05% below the second-quarter level. To generate a 0.2% quarterly decline, the Office for National Statistics must be assuming a significant output fall in September. This seems odd given the limited information available at this stage.

The chart plots quarterly GDP together with a monthly proxy based on industrial and services output. After recovering by 0.4% in June and July, monthly GDP is estimated to have slumped by 0.6% in August with a further 0.3% decline in September implied by the quarterly estimate.

Today's figures conflict with the MPC's assessment at its last meeting that "output in the third quarter was likely to be close to the central projection in the August Inflation Report" – this projection implied a 0.1% rise last quarter (taking account of a 0.2% upward revision to second quarter numbers). The Committee, however, is likely to be puzzled by the apparent inconsistency with survey evidence and the assumption of a further output fall in September.

November's meeting is shaping up to be a cliff-hanger, with GDP weakness offsetting other factors arguing for an increase in the MPC's inflation forecast, including recent higher-than-expected outturns, better global economic news, stronger asset and commodity prices and a fall in the exchange rate. The two-year-ahead projection based on unchanged policies was above the target at 2.17% in August so the MPC needs to conclude that inflation prospects have improved to justify extending asset-buying. This still looks a stretch, even after today's number.

More equity analysts upgraded their forecasts for company earnings in October, suggesting a further rise in economic momentum. The world earnings revisions ratio – i.e. upgrades minus downgrades divided by the total number of estimates – reached its highest level since May 2004. The ratio is closely correlated with business surveys, which may show further improvement this month – see chart.

The Bank of England's gilt-buying has cut the effective maturity of the UK's public debt, implying greater vulnerability of interest costs to changes in market rates. The maturity of liabilities remains longer than in other major countries but the gap has narrowed significantly over the last year.
 
According to the Debt Management Office (DMO) Quarterly Review, the average maturity of conventional gilts outstanding fell to 13.4 years in September 2009 from 14.3 years 12 months earlier. The latest figure, however, is misleading because it includes the £164 billion of gilts now held by the Bank of England's asset purchase facility (APF) – 27% of the total stock.
 
The market has, in effect, exchanged these gilts, with an average maturity of about 10 years, for reserves at the Bank of England, which are repayable on demand. The relevant metric for assessing refinancing risk is the average maturity of the market's combined holdings of gilts and reserves, not that of the entire stock of gilts, including the APF. This is significantly lower, at about 10.7 years (based on a 10-year average life of APF gilts).
 
The Bank of England pays Bank rate on reserves. This results in an interest saving when Bank rate is below the average yield on gilts, as at present. The differential, however, has been positive for about half of the time since the MPC's inception in 1997 and could rise sharply in the event of a loss of market confidence in UK economic policies. This would be instantly reflected in the combined government / Bank interest bill.
 
The DMO figure also does not take into account expansion in the stock of Treasury bills, from £18 billion at the end of 2007 to £52 billion currently. If these are included in the calculation, in addition to adjusting for the APF gilts / reserves swap, the average maturity of liabilities falls further to an estimated 9.8 years. (All these figures exclude index-linked gilts.)
 
This is still significantly longer than for other major countries – the US is at the low end of the range, with an average maturity of publicly-held marketable debt, including bills, of less than four years. The gap, however, is much smaller than a year ago and will continue to erode if the Bank of England extends its gilt-buying programme.

Recent posts have argued that there is "excess" liquidity in the UK economy, helping to explain sterling weakness and rapid asset price gains. This excess is not captured by broad money statistics partly because it reflects a fall in the demand to hold money and partly because liquidity has been exported.

Today's MPC minutes are interesting because, for the first time, broad money trends are compared with nominal GDP (see paragraphs 11 and 23). To the extent that money demand moves in line with output (i.e. falling recently), the rate of change of the broad money to GDP ratio is a better guide to "excess" liquidity creation than money expansion itself.

This change of emphasis suggests that the MPC is unlikely to expand gilt purchases next month on the basis that broad money growth remains low. Instead, the decision will hinge on the medium-term inflation forecast generated for the November Inflation Report.

The two-year-ahead projection based on unchanged policies was above 2% and rising in the August Report. Since then, output news has been consistent with the August forecast (according to today's minutes), actual inflation has been higher than expected, sterling has weakened and equity, property and commodity prices have strengthened. The presumption must be that the inflation forecast is unlikely to be revised lower, implying no case for a further extension of gilt-buying.

Recent public borrowing figures cast doubt on the consensus view that the deficit will exceed the Budget forecast of £175 billion in 2009-10. According to the Treasury's September survey of forecasters, the median projection is £184 billion.

The £175 billion official target implies an average of £14.6 billion a month. In the first half of the year, however, a measure of borrowing adjusted for seasonal variation averaged £12.4 billion – see first chart.

To reach the official projection, borrowing would need to rise to £16.8 billion a month in the second half of the year but a three-month moving average has recently stabilised well below this level. The reversal of last December's VAT cut from January should limit further deterioration later in 2009-10.

Money supply figures also released today show a further pick-up in "retail M4", comprising notes and coin in circulation, retail bank deposits and building society deposits – second chart. Inflation-adjusted retail M4 is a leading indicator of retail sales – third chart. The improvement suggests stronger spending into year-end but real money growth is likely to fall back in late 2009 and early 2010 as headline inflation rebounds – see previous post.

As discussed in a post last week, equities and other "risky" assets have recently shown a strong correlation with movements in the US monetary base, with the base tending to lead. This relationship was highlighted by former hedge fund manager Andy Kessler in an article, "The Bernanke Market", published in the Wall Street Journal in July. (The monetary base comprises currency in circulation and banks' reserve balances with the Federal Reserve.)

The new rally highs reached by many equity markets last week followed an acceleration in the monetary base in late September and early October. The base posted another solid increase in the week ending last Wednesday – see first chart. (The Fed publishes the weekly data after the market close on Thursdays.)

The monetary base is likely to continue to expand at least until year-end. This is because the Fed is committed to buying about $500 billion more agency mortgage-backed securities (MBS) and other agency debt by the end of the first quarter of 2010. (At its last meeting, the Federal Open Market Committee agreed to purchase a total of $1.25 trillion of MBS and up to $200 billion of other agency debt. As of last week, the Fed held $763 billion of MBS and £136 billion of agencies.)

The impact of this buying on banks' reserve balances is likely to be partly offset by a decline in other forms of Fed lending, including "term auction credit", discount window loans, its holdings of commercial paper and liquidity swaps with other central banks. These four items, however, currently sum to $267 billion – even in the unlikely event of the total falling to zero, the effect on reserves would be swamped by securities purchases.

Banks' reserves will also be boosted by the US Treasury's plans to run down the balance in its supplementary financing account at the Fed, using the funds to reduce the stock of Treasury bills. This balance currently stands at $100 billion and a recent Treasury release projected a fall to $15 billion.

The prospect of the monetary base continuing to grow rapidly until year-end evokes memories of 1999, when the Fed injected liquidity on a then-unprecedented scale to meet a perceived rise in the precautionary demand for cash caused by fear of Y2K computer disruption. This fed the final stages of the bubble in technology-related stocks, which fell sharply soon after the Fed drained liquidity in early 2000 – second chart

"Excess" liquidity tends to be channelled towards assets perceived as "hot", usually reflecting a combination of a plausible investment story and recent outperformance. Technology stocks were the speculation of choice in late 1999. Bullish commentary now focuses on emerging equity markets and wider commodity themes – these areas may continue to outperform, at least until the Fed turns off the liquidity tap.