Correlation of Currencies - Normal and Stressed

Correlations can be useful tools.

FX Traders often use them to confirm movements following an announcement. For example, if a trader is expecting the EUR to appreciate following a retail sales announcement and the EUR has a negative correlation with the CHF and a positive relationship with the GBP then these currencies might be tracked to make sure the movement in the EUR is one to take advantage of.

Correlations are useful but can change in stressful times. In times of extreme financial stress correlations head toward 1 and -1. This is the contagion effect, when safe harbours disappear.

When economic news affects financial markets correlations strengthen as volatilities rise. It is important then that market participants use the right correlation for the right situation.

A while ago I posted some correlations that looked at FX rates a few minutes after major announcements. Here is the link to these posts.

Tables at mataf.net (Currencies Price Provided by the Swiss broker RealtimeForex) give correlation of currencies in more normal times. According to the website:

• If the correlation is high (above 0.8) and positive then the currencies move in the same way.
• If the correlation is high (above 0.8) and negative then the currencies move in the opposite way.
• If the correlation is low (below 0.6) then the currencies don't move in the same way.

These correlations for 5, 20 and 100 day periods will tend to average out the extremes that are experienced during announcement days and so will tend to be lower.

So correlations tend to be higher at times of stress and following economic announcements. Here is the proof.

I have taken the average correlations (currency pairs of currencies shown below with the USD vs. EUR/USD) following four major U.S. economic announcements: CPI, initial jobless claims, nonfarm payrolls, and retail sales. The correlations are plotted for data 1, 5, 10, 20, and 30 minutes following these announcements. Using the mataf.net data I also plot the 5, 20, and 100 day correlations alongside:The correlations on the right hand side of the chart are for more "normal" times.

The correlations on the left hand side of the chart are for more "stressful" times.

Notice how currencies that tend not to move together at the daily frequency do move together after annoucements. Also there is a trend towards greater positive or negative correlation the closer one gets to the announcement.

If anyone would like a spreadsheet of my calculation of the 1, 5, 10, 20 and 30 minute return correlation matrices for the U.S. announcements of nonfarm payrolls, initial jobless claims, retail sales, and CPI, please send me an email to john.parker at relevanteconomics.com.

Thursday, April 5, 2007

TABE Luncheon, Thursday, April 5, 2007

The Impact of Economic News on Financial Markets

John Parker, Principal, Relevant Economics

It is not news that news moves financial markets. In the past, research into the impact of economic announcements on financial markets has used surveys of economists to gauge market sentiment. The extent to which the actual number differs from the survey is taken as the news component that drives markets following the announcement. Recently two developments have occurred that have allowed us to quantify how much, when, and in what direction financial markets move in response to news. Firstly, economic derivatives, auctions of derivatives on economic releases allow us to get a much better read on market sentiment than comes from surveys. Secondly real-time financial markets data has allowed the effect of the announcement to be isolated and separated from other influences.

John Parker will present his research on the impact of economic news on financial markets using economic derivatives and real-time financial data. He will answer questions such as: which economic announcements move markets most; which markets respond most quickly; do good news and bad news have asymmetric effects; and, do data revisions matter?

John has an M.Phil. from Oxford, a B.A. from UWO and 25 years experience as an economist, in the fields of energy markets, financial markets, and business forecasting. His experience in financial markets includes working at the central bank and a risk management software company.

Location: BMO Boardroom, 21^st Floor, 1 First Canadian Place, Toronto

Date: Thursday, April 5th, 2007

Time: 12 noon to 2 p.m.

Cost: TABE and CABE members in good standing $25, Others $45. A light lunch will be available.

PLEASE USE THE WEB SITE FOR REGISTRATIONS www.cabe.ca/chapters/TABE . Only if absolutely necessary, to register, you can call 905-845-3102 or E-Mail tabe@cabe.ca. Registration closes 2 p.m. Tuesday, April 3rd.

Members (only) may pay cash or cheque at the door, non-members and credit card payments (VISA, Diners/EnRoute, MasterCard, or American Express) are to be prepaid VIA THE WEB SITE. No-shows will be invoiced. Charges include GST. (TABE GST number: R124389990)

Meeting arranged by Paul Ferley

Charts for Survey vs. Derivatives Based Forecast Comparisons

In the last few posts I showed the statistics that show that the economic derivatives forecast outperforms the consensus for the nonfarm payrolls announcement. Here are the charts that go with the stats. First, here is the chart of Actual (U.S. nonfarm payrolls or NFP) versus the economic derivatives or market-based forecast for the last 54 months (2002:01 - 2007:03). Here is the same chart for the Consensus or survey-based forecast: And side-by-side:And here are all three as a time series plot: Here are the forecast errors for the economic derivative or auction market forecasts compared with a fitted normal distribution (you'd hope that the errors were random and reasonably normal in their distribution): And here are the Consensus or survey-based forecast errors: Conclusion? You can't see much from the charts as the two forecast series both track the actual quite well and eye-balling the charts does not suggest one is better than another. However, the statistics of MAE, RMSE, correlation and especially the horse-race regression confirm that the economic derivative or auction market-based forecast outperforms the survey or Consensus forecast and that the latter adds nothing once you have the former.

NFP: Superior Derivatives-Based Forecasts - Confirmed

Refet S. Gürkaynak and Justin Wolfers compared the Consensus of Economists or survey-based forecasts with the economic derivatives or market-based forecast using data from Oct. 2002 to Jul. 2005 (33 NFP observations). The results shown are shown below (in the GW columns).

I have replicated their study using more, and overlapping, data from Oct. 2002 to Mar. 2007 (64 observations). My results are shown in the table by the JCP columns.

The conclusion? Again the economic derivatives or auction market-based forecast dominates the Economist survey or Consensus forecast.

Details are found in the table below which looks at measures of forecast accuracy, the mean absolute error (MAE) and the root mean squared error (RMSE). There is also a correlation of each forecast with the actual (NFP release) and a regression-based test of the information content of each forecast using the Fair and Shiller method.

As with the smaller sample in GW, the MAE and RMSE are lower for the economic derivatives forecast. The correlation with the actuals is also higher than the Consensus-based forecast.

The coefficient in the regression should be unity for a good forecast. For the Derivatives or auction market-based forecast the test of the coefficient being equal 1 could not be rejected by GW. The evidence is not as strong now, as the test statistic is: F(1, 51) = 0.235477, with p-value = 0.62957.

The test that the Consensus or survey-based forecast is zero (that is that this forecast adds nothing to explanatory power of the other forecast, or conditioning on the market-based forecast renders the survey forecast uninformative) is: Test statistic: F(1, 51) = 5.62732, with p-value = 0.0214933. So the Consensus adds no information beyond the economic derivative forecast.

Not only that but the perverse negative coefficient found by GW persists with the longer data set.

Again, it seems “likely that the improved performance is due to the market effectively weighting a greater number of opinions, or more effective information aggregation as market participants are likely more careful when putting their money where their mouth is.”

	JCP	JCP	GW	GW
	Consensus	Economic Derivatives	Consensus	Economic Derivatives
Mean Absolute Error (MAE)	0.812	0.809	0.743	0.723
Root Mean Squared Error (RMSE)	1.036	1.023	0.929	0.907
Correlation of Forecast with Actual	0.7025	0.7026	0.677	0.700
Horse Race Regression (Fair-Shiller)	-0.42	1.26	-0.14	1.06
standard error	0.56	0.53	0.89	0.78
t-statistics	-0.75	2.38	-0.16	1.36
significant at 10% (*), 5% (**), or 1% (***) level		**
R2		0.50		0.46
obs.		54		33
range of data	Oct. 2002 - Mar. 2007		Oct. 2002 - Jul. 2005

Forecast errors normalized by historical (Oct. 2002 to Mar. 2007) standard deviation of survey-based forecasts of 90.31.

Fair-Shiller - Fair, Ray C. and Robert J. Shiller (1990), “Comparing Information in Forecasts from Econometric Models,” American Economic Review, 80(3), 375-89.

GW - Refet S. Gürkaynak and Justin Wolfers (2005), "Macroeconomic Derivatives: An Initial Analysis of Market-Based Macro Forecasts, Uncertainty, and Risk"

A Consensus of Economists

How well do economists predict the U.S. nonfarm payrolls? I picked up the consensus forecast for the NFP from the NASDAQ website (from Econoday). The latest report is here.

There are 63 monthly reports back to January 2002 (there may be more but this is all I pulled for analysis), all have actual and the consensus forecast. The most recent 4o reports have the range of the forecasts as well.

The average error was 24,000.

This appears to be a biased forecast (on average the error should be zero. With a standard error or 10,000, this is significantly different from zero at the 95% level). So despite studying the dismal science, economists are overall an optimistic bunch. In fact they are overly optimistic.

The biggest oopsie was 328,000 (in March 2003 when the actual was -308,000 and the expected was 20,000).

In the last 40 months the actual fell within the range of the expectations 20 times. So 50% of the time the actual was inside the range. That is not a great record.

Next, I'll look at the economic derivatives forecast performance and provide some comparisons.

Nonfarm payroll employment - whose better?

Nonfarm payrolls for February 2007 (released today, Friday March 9th at 8:30am) continued to trend up (+97,000). Details are here. Yesterday I noted that as of yesterday, the Economists' consensus was 100,000 and the CME Auction Market participants' consensus was 82,500. So who is the better forecaster? In this instance the Economists were better (error of 3,000 versus the derivatives auction results error of 14,500). For the Nonfarm payrolls (NFP) there are several forecasts that come from the CME auctions There was one more auction and therefore one more forecast before the release at 8:30am this morning. This auction gave an implied market forecast that was even more off the mark (75,500). I have maintained that, based on my research, over time the CME Auction Market participants' consensus outperforms the Economists' consensus. Gürkaynak and Wolfers (2006) conclude that “The evidence presented … shows that economic derivatives option prices are accurate and efficient predictors of the densities of underlying events” (p. 29). Seems it is time to test that hypothesis again. Here's what I'd like to do. Test:

• Which forecast best predicts the actual outcome, CME economic derivatives auctions or the Economists' consensus?
• Since, for the NFP there are several forecasts from economic derivatives auctions, do auctions closer to the release perform better than forecasts that are more stale?
• Does averaging the auction results produce a superior forecast?

There are a couple of definitions of a better forecast that may be pertinent here. One might be, as implied above, that is which forecast predicts the outcome better. However this assumes that the variable you are interested in is in fact the economic release (such as the NFP). But who really cares about the NFP? What most people care about is what it means to them. These economic statistics are indicators. Most investors care about how these indicators affect their portfolio of holdings. So one definition of a better forecast of NFP might be one that more accurately explains (or forecasts) movements in the financial variable of interest. I'm not sure the data will allow for a definitive test on all of these points, but this is my goal.

1. Gürkaynak, Refet S., Wolfers, Justin, (2006) “Macroeconomic Derivatives: An Initial Analysis of Market-Based Macro Forecasts, Uncertainty and Risk” NBER Working Paper Series, NBER Working Paper 11929, January 2006.

What Can You Expect from the March Nonfarm Payroll Release?

As I have discussed before in this blog, the best information about an upcoming nonfarm payrolls release comes from the economic derivatives auctions held by the Chicago Mercantile Exchange, Longitude, and ICAP. From the CME: March Nonfarm Payroll Release - Friday, March 9 at 8:30 a.m. EST

Economists' consensus - 100,000

CME Auction Market participants' consensus - 82,500

Based on previous auctions that occurred Tuesday, March 6, Wednesday, March 7 and earlier this morning, CME Auction Market participants predict U.S. employers added 82,500 jobs last month, which is significantly lower than economists' forecasts of 100,000 jobs.

Chart from this morning's CME Auction (March 8, 7:30 a.m. - 8:15 a.m. EST)

Chart from yesterday's CME Auction (March 7, 7:30 a.m. - 8:15 a.m. EST)

Chart from Tuesday's CME Auction (March 6, 7:30 a.m. - 8:15 a.m. EST)