April 2009 Monetary Policy Update

April's Monthly Statistical Bulletin released a couple of days back shows money supply growth still decelerating, except for M1 (log annual changes):



That actually worries me less than the fact that so is velocity (log annual changes):



Why be concerned over velocity? Because a fall in the velocity of money (the number of times money goes around within an economy) can amplify movements in the money supply. Falling velocity coupled with slower money growth makes monetary policy tighter than the money supply growth alone would indicate. Having said that, money supply growth is still supportive of economic growth right now:



Since adjusted M3 growth still exceeds the drop in GDP growth, we’re still looking at a loose monetary policy stance. Just be cautious when taking this chart at face value, because my methodology isn’t exactly rigorous here.

On the other hand interest rates, after the market absorbed the likely pace of government debt issuance after the tabling of the mini-budget, have settled down:



MGS spreads on the long end have continued to widen slightly but not by much, and current market data is showing a little pullback as well so I’m not overly worried about rising funding costs for the government just yet.

The banks are having a fine time though, with loan growth purring along and cost of funds very much in their favour. That part of the equation is a bit of a concern to me – the whole idea of loose monetary policy is to get credit flowing into the economy (which it is) and to lower borrowing costs (which is not). What should be cheaper funding for consumers and businesses is turning into a profit party for the banks, even bearing in mind potential losses from non-performing loans. NPLs in April have just registered the first uptick in over a year but it amounts to an increase of just RM150 million on a 6-month basis for the entire banking system, which is peanuts compared to the RM736.5 billion in outstanding loans.

In short, while BNM has cut bank funding costs to the lowest point I can remember, the margin between lending and funding is actually at the same level as it was when the economy was booming:



Never mind the increase in car financing costs – effectively the cost of every other loan is rising as well relative to what it could and should be. That makes a mockery of central bank policy, and I don’t see how this can be beneficial at all, unless it’s to boost the financial sector contribution to GDP at the expense of everyone else. Unfortunately, with the reforms under the Financial Sector Master Plan, there’s little that BNM can do about this, and we’ll just have to live with it.

1Q2009 GDP Growth Worse Than Expected

I've been trying to digest the numbers, but whichever way you look at it, the GDP numbers are bad (log annual change):



One saving grace is that the revised 4Q2008 figures are stll positive, but just by a hair's breadth. What really surprised me though was the extent of the revisions, with DOS revising GDP data all the way back to 2006. In any case, both demand side and supply side numbers are horrible:




Are we then in a technical recession? Not "officially", but that's due to our singular way of calculating growth figures. I outlined the difference in an early post in my blog. To recap, Malaysia uses quarter on last year's quarter to arrive at the growth figure, while most advanced economies use seasonally adjusted quarter on previous quarter, annualised. The former method yields a less volatile growth measure, while the latter better captures momentum.

If we use the seasonally adjusted method, it does show a technical recession (log quarterly changes, seasonally adjusted and annualised):



The depth of the pullback though is startling - that's a 17.4% drop in 1Q2009 after an already steep 9.1% fall in 4Q2008. On that basis, we are definitely in a technical recession, though I've little doubt that 2Q GDP numbers will confirm it "officially".

I've also been looking at some of the structural aspects of the economy, now that there's a lot of talk about a "new economic model". While I'll save my thoughts on that for another day, one thing that I think is going on is that like it or not, we ended up with a new economic model anyway without anyone looking. Or to be more precise, the export-growth model had already hit a dead end in my view a couple of years back.

I really don't have any firm convictions on what should replace it though. A structuralist approach to development would imply a shift towards higher services output on the supply side, and consumption on the demand side, but that's already occured and hasn't fully displaced export-led manufacturing. Or it could just be that I'm expecting too much too soon, and the results would be more evident a few more years down the road. Or we could end up a unique amalgam, with a highly diversified economy that's neither weighted to the external sector nor the domestic sector.

Interesting times.

Deflation or Disinflation?

Last week's April CPI report shows inflation continuing to shift downwards, mainly from a drop in food prices (log changes in CPI, 2005=100):



We're now back at Malaysia's long term average of 3% annual inflation, which on the face of it looks fine. Disinflation was always on the cards with the slow down in the economy, as well as the sharp drop in oil and commodity prices from their July 2008 peaks. With the rate of descent in economic indicators also slowing, deflation is less of a concern than it was in the early months of this year - or is it? The commodity bubble of 2007-2008 royally screws up any attempt at getting a feel for where inflation actually is:



Certainly the index level for April is showing the price level dropping as well, which is indicative of deflation (2005=100):



We're not just talking about the base effect here, folks. Month-on-month changes are also in the negative, except for the spike during Chinese New Year (log monthly changes in CPI, 2005=100):



I've tried constructing alternate measures, using 12-month, 6-month and 3-month moving averages:



Only the annual series is still pointing upwards as of April, which doesn't exactly fill me with confidence.

Worse still, the Jan-Mar 2009 manufacturing industry numbers show annual wage growth (-8.9%) dropping faster than employment (-7.0%), which suggests average wages dropped by 1.9%.

This is the critical channel by which deflation feeds on itself by reducing demand, which leads to further reduction in prices, which forces companies to lower output, and leads again to lower employment and wages. So although prices might be coming down, which is good for consumers, real income for those very same consumers is falling faster.

On that basis, I'm not convinced that the deflation threat is over yet. What comfort I have is that manufacturing is the worse hit sector in this downturn, and wage trends there might not be reflective of the economy as a whole. Also, anecdotal evidence from a reliable source (my mom!) suggests food prices have come up again in May, so we could see some upward movement in the index for this month. But I'm not holding my breath.

Recommended Reading

I’m a big fan of audiobooks – there’s little better to pass the time in traffic jams than to listen to a good book or novel, especially with a talented narrator. I get all of mine from Audible.com, which also has the virtue of providing free of charge the audio version of the Wall Street Journal with some of its membership plans. Membership isn’t cheap, but if you read/listen as much as I do, then it pays for itself in the long run.

The latest book I’ve read (or is that listened to?), is Muhammed Yunus’ “Banker to the Poor: Micro-Lending and the Battle Against World Poverty”, which describes the founding of the Grameen project in Bangladesh and the success it has had in opening up access to credit and economic opportunities for the absolute poor.

Prior to Grameen, there was little the poor could do to improve their circumstances, especially under the conservative Muslim society – or to be more accurate, conservative patrician society – that existed in Bangladesh. Banks, as conventional banks do everywhere, were and are only interested in lending to those with collateral, rather than to those who have business ideas or have willingness to work. That’s a fairly common complaint I hear, and not just from the poor. What money the poor received was generally through charity or ill-run government projects, and didn’t harness the energy or the labour of the poor in any meaningful way – neither for the country nor for the poor themselves. Some of the stories of the poor, quite frankly, brought a lump to my throat.

But Grameen offered a way out of the poverty trap, albeit one that depended on one’s own willingness to take a chance. By offering tiny loans with no collateral (because the poor didn’t have any), no documentation (since many of the borrowers were illiterate), and relatively low interest rates (compared to money lenders), Grameen helped the absolute poor work for themselves, earn enough to if not prosper then at least survive, and gain a measure of self respect. Just as important, and probably the vital key to its success, Grameen also pushed forward an agenda for social change by concentrating on women borrowers, and encouraging education, family planning and basic personal healthcare. All common sense stuff, but nothing the market economy would attempt on its own left to its own devices.

The book is part autobiography, part microlending manual, and part polemic (with some justice) against multilateral development agencies. If there’s a note of self-congratulation in some of the passages, its well deserved. Probably the best evidence of the effectiveness of Grameen has been the explosion of interest and thousands of copycat organizations across the globe, including in advanced economies. In Malaysia, Amanah Ikhtiar Malaysia conducts microlending operations – I don’t count the micro-finance program run by BNM as equivalent as it doesn’t target the absolute poor.

If there’s a criticism I have, is that microlending is only one aspect of the fight against poverty. I think Grameen’s approach acknowledges this since it explicitly incorporates social reengineering within its operational framework. The problem of course is that all the other methods – education, infrastructure, healthcare, technology transfers – don’t work without access to credit. On that score Prof Yunus has probably stumbled on the one thing that can lift desperately poor places like Sub-Saharan Africa, despite a flood of aid money.

If anyone’s interested in obtaining a copy, the book is available through Amazon.com and locally through MPH.

March Industrial Production: Still No Sunlight

If you consider the second derivative a valid indicator, than today's IPI reading may give some hope that things are getting better (if the High Court decision on Perak wasn't enough for you).

While a little worse than the consensus, March IPI growth of negative 14.4% y-o-y is at least showing a slowdown in the slowdown compared to Febuary's reading of minus 14.6%. The actual log differences are actually a little worse at 15.5% versus February's 15.8%, but this is the first uptick in the IPI and all its constituents since last July (index numbers; 2000=100):



Monthly growth numbers are even more positive, with the main index up 6.1% in log terms (log monthly difference; non-annualised). Pretty strong stuff...



...until you put in seasonal adjustment. March industrial production is almost always higher than Febuary's for the simple reason that March has more working days. Making that adjustment yields a more disappointing story (index numbers; 2000=100, x11 seasonal adjustment):



...and monthly growth numbers (except for Mining) all turn negative instead (log monthly difference; non-annualised):



While anecdotal evidence is pointing to an improvement in orders and capacity utilization, I don't think I'm ready to call a bottom just yet. I'm thinking we're in an inventory adjustment phase at this point, where firms are having to rebuild stocks that were run down from the savage cut in output between August and February. The implication is that we might see a further dip as soon as next month, as supply adjusts to the new demand realities.

March Trade Data: A False Dawn?

Malaysia's March trade data is providing a glimmer of hope that the worst is behind us...or does it? On a month-to-month basis, both exports and imports turned up in impressive fashion:



However, on a year to year basis, the rate of decline is at best stabilising:



We're not out of the woods just yet, not by any means. On the other hand external demand is just one part of a larger picture, and with bank lending increasing at a good clip and borrowing costs trending down, there's some hope that at the very least we'll see a bottom form for the economy in the second quarter.

Moving on to my ongoing saga in determining a good forecasting model for exports, recall in my last external trade post I constructed 5 different models and used them to predict March exports. Model selection procedures suggested the best choices were to either seasonally adjust the trade data prior to running the regression, or directly modelling the seasonal effect within the regression.

How did these models do? The predictions:

1. Baseline: RM33832; Range: RM40.0-27.6b

2. ARMA: RM44618; Range: RM51.5-37.7b

3. Structural ARMA: RM33712; Range: RM39.9-27.5b

4. Seasonally adjusted: RM39792*; Range: RM44.7*-34.9*b

5. Seasonal Effect: RM43861; Range: RM49.4-38.3b

And actual March exports were RM43645 (RM42778 seasonally adjusted).

Models 1 and 3 are completely off the reservation - in retrospect, not accounting for seasonal effects means these models will always have large errors in months when the seasonal effect is strong. Models 2 is very close and 4 is close enough, so I'll keep evaluating those.

Model 5 however is a spectacular RM200 million within the preliminary figure (trade data is always revised the next month), so that's the obvious winner this month.

Here's the April forecast:

2. ARMA: RM44555; Range: RM51.3-37.8b

4. Seasonally adjusted: RM37561*; Range: RM42.2*-32.9*b

5. Seasonal Effect: RM38293; Range: RM43.4-33.2b (shown below)



Note that Models 4 and 5 are predicting a further downturn in external trade, while Model 2 suggests exports will remain flat from March. If this does happen, I'd think that we might have turned the corner, at least as far as external demand was concerned. An April disappointment on the other hand suggests that the bounce in exports and potentially IPI would be due to inventory rebuilding within the global supply chain, rather than a more sustainable increase in global final demand.

May Effect In Stock Markets: True Or False?

The Malaysia-Finance blog the other day brought up an interesting seasonal effect that I never heard of before: to wit, when investing in stock markets sell in May and go away (until October). Essentially this divides up the year into a bull period (Nov to April) and a bear period (May to Oct). Ordinarily I dont't bother much with equity market analysis – it`s not really my field – but this sort of seasonal effect is amenable to statistical testing.

Rather than doing something complicated like a seasonal ARCH model or laborious like directly calculating compound returns for each subperiod, I hit on a fairly simple way to prove the May effect (anyone feel free to tell me this is wrong). In essence I cut the daily return* data I had through using two dummy variables (E1 for Nov to April, E2 for May to Oct) which took the value of 1 for each subperiod and 0 for the opposite period. This gave me two daily return series, each with its own sample mean and distribution. All that was then required to prove the May effect was to verify that the Nov to April series had a higher mean, and that this mean was statistically significantly different from the mean of the May to Oct series.

*returns are calculated as the log difference between two trading days.

It took longer to write about than to do.

Here are the results tabulated for the markets that I have coverage for. Mean difference is the net difference between the sample means of series E1 and E2; F-stat is the value of the ANOVA F-Statistic (t-tests yielded virtually identical results); and Prob. is the threshold on the test probability distribution where the null hypothesis is not rejected (1 minus prob. gives the confidence level). The results are ordered from strongest to weakest:

^STI
Mean difference: 0.0005
F-Stat: 8.94
Prob.: 0.003

^DJI
Mean difference: 0.0003
F-Stat: 8.24
Prob.: 0.004

^TWII
Mean difference: 0.0008
F-Stat: 6.97
Prob.: 0.008

^JKSE
Mean difference: 0.0009
F-Stat: 6.75
Prob.: 0.009

^GDAXI
Mean difference: 0.0005
F-Stat:F-Stat: 5.22
Prob.: 0.022

^FTSE
Mean difference: 0.0003
F-Stat: 5.15
Prob.: 0.023

^IXIC
Mean difference: 0.0003
F-Stat: 4.85
Prob.: 0.028

^N225
Mean difference: 0.0004
F-Stat: 4.45
Prob.: 0.035

^KLCI
Mean difference: 0.0005
F-Stat: 4.42
Prob.: 0.036

^GSPC
Mean difference: 0.0002
F-Stat: 4.23
Prob.: 0.040

^KS11
Mean difference: 0.0007
F-Stat: 3.51
Prob.: 0.061

^SSEC
Mean difference: 0.0007
F-Stat: 2.08
Prob.: 0.150

^AORDS
Mean difference: 0.0002
F-Stat: 1.99
Prob.: 0.159

^HSI
Mean difference: 0.0002
F-Stat: 0.81
Prob.: 0.370

^BSESN
Mean difference: 0.0001
F-Stat: 0.06
Prob.: 0.800

Quite a few surprises here, although I'd encourage anyone to read through the caveats before taking any of these conclusions at more than face value. First though is that the May effect appears to be pervasive – two thirds of the 15 markets covered here have better than a 95% chance that the May effect is true. The second surprise is that developing markets are as likely as developed markets to exhibit the May effect. The third surprise was the difference in probabilities for the Dow Jones Industrials and the broader S&P500, though I suspect the difference here is that less of the S&P500 counters are within the investment universe of investors.

Now for the caveats - the sample sizes for each index is different, with the SSEC the shortest at just four years. Most of the rest date back to the 1990's, although the developed country indexes go back further (US markets are from 1970). The impact of this is that for the short sample indexes, the degree of the May effect is less certain. That also makes the ordering that I've done here much less reliable than I would like. One other related problem here is that I've only covered a small sample of the available markets, and a larger sample might reach different conclusions.

In summary though, what's clear is that if you're thinking of trading on the basis of the May effect, you're likely to end up in the money – but you have to be careful and confirm that there's a historical basis for it in the market you're in. There's no substantive dividing line between developing and developed markets here. You should also be aware that the difference in yield between markets of the May effect can be strikingly different – it might not be worth the trouble, especially if you have a mandate that requires a certain level of constant exposure to equities.

Monetary Policy Update III: Is The Ringgit Oversold?

There has been a lot of movement on the currency front over the last year or so. Here's the trends against the G3 currencies (index movement relative to Dec 2007, 2000=100, all charts use MYR as the base currency, hence a rise is an appreciation, a fall a depreciation):



Between Dec 2007 and Dec 2008, MYR lost 10.2% against the USD, 1.3% against EUR, and 26.7% against the JPY. The tight trading range against the EUR is pretty remarkable. Against the Yuan and the other "dragon" economies:



Notice the massive appreciation of 37.2% against the KRW to the end of 2008. Against the rest of ASEAN plus Vietnam:



The contrast in different trajectories is striking between this group against the "dragon" group. Finally, the other major trade partners we have a general trend of appreciation:



However, on the whole, MYR has been depreciating through the year even including inflation adjustments. On a trade weighted basis:



...and cumulative gains/losses:



The question is: is this depreciation an equilibrium movement, or a disequilibrium movement? It is well known and documented that movements in currencies over the short term cannot be predicted with any accuracy, and that currency exchange rates tend to stray from the rate predicted by economic fundamentals for long periods of time. The fact that currency markets are perhaps the largest, deepest, and most liquid in history makes the latter phenomenon extremely vexing to economists, particularly free-market fundamentalists.

But back to the question at hand, a believer in Purchasing Power Parity (PPP) would strongly be of the opinion that MYR strengthening has a long ways to go. The IMF estimates the implied PPP conversion rate for MYRUSD is 1.967 in 2008, the World Bank estimate is 2.105 for 2007, while the Penn World Tables suggest 1.28! On the other hand, evidence for strong-form PPP being a determinant of exchange rates is extremely weak, even over very long periods of time. Similarly, interest rate parity does not appear to matter unless you add in a time-varying risk premium and expected inflation, both of which are unobservable variables and thus not amenable to rigorous empirical testing. I’ve covered this and other arguments against PPP in my exchange rate policy posts (here, here and here).

Based on the variables I identified in those posts, what appears to matter (strongly) for the MYR are terms of trade and government consumption. On that basis the long term annual model I have suggests the MYR was overvalued by about 5.5% at the end of 2007. The model hasn’t been updated since I first estimated it in late 2008, mostly because the data requirements are extremely onerous (24 currencies, 14 times series for each). A lot has changed since then, particularly with the relative changes in government spending as well as a sharp fall in commodity prices, which changes the terms of trade. Insofar as individual fiscal stimulus spending plans cancel out, the prime factor behind the MYR depreciation has been a change in the terms of trade.

In summary, what I think we’ve seen in 2008-2009 is a move to equilibrium, as well as a change in fundamentals i.e. the equilibrium rate has been falling as well. What that means is that I suspect the MYR is still overvalued, and may have a bit further to fall. This is weakly supported by the real exchange rate being below the nominal exchange rate.

Where MYR weakness will manifest itself is likely to be against the Yuan and the “dragon” currencies (with the exception of the KRW) and not necessarily against the USD, which has its own reasons for weakness. That’s an opinion and not a prediction by the way – foreign exchange rate determination is complex enough at the best of times. Note that my argument here implies that the MYR is actually not that far off its true equilibrium value, and is very much in contrast with the rest of the domestic investment/academic community who still seem stuck on PPP as the appropriate valuation method for exchange rates.

Interesting sidenote: In general, nominal and real rates for MYR track closely for free float currencies (USD, EUR, GBP), and has tended to diverge with currencies that are either pegged or feature intervention (very, very obvious for JPY, Indian Rupee, and Vietnam Dong). Does this make the MYR a free float currency? It sure looks like it to me.

Technical Notes:
All currency data from Pacific Exchange Rate Service. CPI deflators are from various sources including the IMF, ILO, and national sources.

Monetary Policy Update II

Since the interest rate front is showing little progress in loosening monetary policy, what can we glean from changes in monetary aggregates? Not a whole lot unfortunately. Here’s the situation up to March (log annual changes):



…and net of inflation:



Note that net M1 growth is essentially zero, while M3 growth is at just 3.6%. If you saw my post on Malaysia’s leading indicators, the forecast for GDP growth looks like it’ll hit negative 1% for 1Q 2009, which implies that money supply growth is still supportive of economic activity. This assessment ignores the possibility of the velocity of money (the rate at which money flows through the economy) falling however.

Back in March, I talked about the instability of money velocity and how it impacts monetary policy evaluation. Recall that the relationship between money and economic growth can be shown through the Fisher Identity:

Ln(ΔM) + Ln(ΔV) - Ln(ΔP) = Ln(ΔY)

Substituting the known numbers (including forecast rGDP) yields an expected velocity of -4.3%. My estimate of actual change in velocity in 1Q is about 2.0%, which means growth in M3 is higher than strictly required – thus we’re still looking at a loose monetary policy stance. This is with the proviso that both inflation and velocity are showing base effects – the levels for both have been dropping since the peak of the commodities boom in the middle of last year:



As a side note, I stumbled on this chart while preparing this post (monthly log changes in money velocity):



Money velocity has been considerably more volatile since abolishing the USD peg – in fact so have spreads and volatility of market interest rates. I’m speculating this has to do with portfolio flows, but certainly something for future investigation.

As I mentioned in the previous post, the monetary policy stance is unambiguously loose, but not to the degree I would like to see it. One way to support or disprove my opinion (and it is just an opinion), is to evaluate monetary policy based on some form of Taylor Rule which provides a consistent approach to interest rate policy setting. Does BNM follow a Taylor Rule? Given the shift to the OPR as the policy instrument, this is more than a possibility – again an area for future investigation.

Despite my misgivings regarding the cost of credit, bank lending growth is actually fairly solid (annual log changes in total loans):



…and based on plenty of resources:



Unfortunately, direction of lending is a bit of a mixed bag (log annual changes):








Loan growth to the financial sector at nearly 20% per annum doesn’t strike me as a terribly healthy development. I like this one though:



That’s right – 81.2% annual growth in March 2009. The runup appears to have started in October – no guesses as to why.

Monetary Policy Update I

Since BNM has opted not to change the OPR from the current 2.0% level, have there been any substantive changes in the monetary policy stance? Are they putting monetary easing on hold with expectations of a recovery in the second half, or is something else going on?

The three instruments of monetary policy are interest rates, money supply and the exchange rate - I will deal with the latter two in separate posts. There's a few interesting things happening on the interest rate front.

The OPR as a policy instrument is aimed at putting a band around the interbank overnight rate. On that score, March data shows market rates right on the money:



In fact, the spread between the overnight rate and 6 month money is a ridiculous 8 basis points.

Yields on BNM bills and Treasury bills have fallen in tandem, though it’s hard to say where the real market lies with these assets because volume is either low or non-existent. There's just enough action on T-bills though to show the yield curve is still inverted (for the third straight month), while flattening slightly:



The movements in MGS yields in March are fascinating. Recall that the mini-budget was tabled in the first week of March, and we already saw a general movement toward the short end with spreads on longer term yields up sharply across the yield curve. With the expected federal borrowing requirement now known, the market acted accordingly:



The yield on the extreme short end fell, but medium term yields reflected the potential supply situation. I'm a bit at a loss to explain the compression in spreads at 10yr maturities and above, unless it’s because recent auctions have concentrated on medium term maturities - the three MGS auctions in March were for 3 year and 5 year terms. The latest data shows yields on these maturities still inching up. On the other hand, it looks like the market is well able to digest planned government borrowing, RM60 billion stimulus package and all, with yields about on par with the last couple of years.

More importantly for the domestic impact of monetary policy is the continued fall in average lending rates (here for commercial banks):



...and net of inflation:



However, this is still a little higher than I'd like. Despite the fall in lending rates, it's still lagging the cuts in the OPR - the spread between lending rates and overnight interbank money has actually been rising since November, and is at the highest point since early 2006:



This is probably reflective of perceived higher default risks, although we probably won't see any upward movement in delinquent accounts until the second half of the year.

With inflation as it is, the OPR and interbank rates are resoundingly negative which should be a strong enticement to banks to lend. While loan growth has held up (which I'll cover in the next post), there is still a lot of caution and fear - note the massive RM173.5 billion on deposit with BNM, despite the cut in the SRR to 1%. The only positive I see here is that both interest rates and net lending margins are lower than they were in the last downturn in 2001, but since the scale of this downturn is more severe, that's cold comfort.

Technical Notes:
All interest rate data from March 2009 Monthly Statistical Bulletin. Inflation is based on log annual changes to my spliced Consumer Price Index (2000=100).

Indicators For The Economy: Leads, Lags, and Coincidence

One common complaint from just about everyone is that economic data comes out at a fairly big lag. Malaysian quarterly GDP reports typically come out two months after the fact, which makes informed decision making difficult at best. I've laid out some of the reasons for the lag in this post here.

There are however some indicators that can give you a fairly accurate representation of what the economy is doing at much faster frequencies. The Department of Statistics issues monthly composite indexes that do exactly that. The Lagging Index is supposed to affirm the trajectory of the economy after the fact, the Coincident Index shows what the economy is doing right now, while the Leading Index gives an idea of how the economy will do in the future about 1 or 2 quarters ahead.

Here's what the indexes are showing up to February 2009:




All the Indexes are turning up, which gives some comfort that things are turning around. But how good really are these indexes relative to actual economic performance? The answer is: except for the Lagging Index surprisingly good.

I evaluated all three against real GDP (sample range 2005:1 to 2008:4), using both seasonal adjustment (x11) and with seasonal dummies. The quarterly index numbers are arrived at by averaging the monthly index numbers.

Only the Lagging Index didn't fit at all well. In terms of forecasting, the Coincident Index fit well in-sample but not forecasting out of sample (charts and results shown are for the non-seasonally adjusted regressions):

In-Sample Forecast (2005:1 to 2008:4):



LOG(RGDP_2005) = -0.63*LOG(IND_COIN) + 2.38*LOG(IND_COIN(-1)) + 3.36 + 0.01*D2 + 0.04*D3 + 0.03*D4

Out of Sample Forecast (2005:1 to 2007:4; dynamic forecast to 2009:1):



LOG(RGDP_2005) = 1.6729687*LOG(IND_COIN) + 3.69 + 0.01*D2 + 0.04*D3 + 0.04*D4

The Leading Index on the other hand is remarkably accurate:

In-Sample Forecast (2005:1 to 2008:4):



LOG(RGDP_2005) = 1.01*LOG(IND_LEAD) + 6.67 + 0.01*D2 + 0.04*D3 + 0.03*D4

Out of Sample Forecast (2005:1 to 2007:4; dynamic forecast to 2009:1):



LOG(RGDP_2005) = 1.02*LOG(IND_LEAD) + 6.63 + 0.01*D2 + 0.03*D3 + 0.03*D4

I admit to being surprised by these results. I would've thought the Lagging Index to be most accurate, and the Leading Index the least accurate - it turns out the opposite is true. The forecast standard error for the Leading Index is actually half that of the Coincident Index. I'd caution however that the above analysis is based on a rather short sample (reminder to self: a trip to DOS seems warranted). I'd love to know the exact composition of the Indexes and the source data - cointegration analysis would give a good idea of short term dynamics, as well as the relative importance of each component.

What does the Leading Index forecast say about 2009:1Q GDP? Based on the full sample:

Point forecast: RM128,236.1
Upper Bound: RM130,497.9
Lower Bound: RM125,974.4

The point forecast is equivalent to -0.7% growth y-o-y, and -9.5% growth q-o-q annualised, both down from 4Q 2008 growth but rather better than I expected. We'll see how accurate this is when the 1Q 2009 report comes out at the end of this month.