Forecasting exchange rate volatility: The superior performance of conditional combinations of time series and option implied forecasts

This paper provides empirical evidence that combinations of option implied and time series volatility forecasts that are conditional on current information are statistically superior to individual models, unconditional combinations, and hybrid forecasts. Superior forecasting performance is achieved by both, taking into account the conditional expected performance of each model given current information, and combining individual forecasts. The method used in this paper to produce conditional combinations extends the application of conditional predictive ability tests to select forecast combinations. The application is for volatility forecasts of the Mexican peso–US dollar exchange rate, where realized volatility calculated using intraday data is used as a proxy for the (latent) daily volatility.     

Rational Expectations and Security Analysts' Earnings Forecasts

This paper investigates the rationality of security analysts' forecasts. The forecasts of analysts participating in Lynch, Jones, and Ryan's Institutional Brokers Estimate System (I/BE/S) data base are evaluated relative to past values of their own forecast errors, past values of forecasted earnings per share, and quarterly percentage changes in publicly available macroeconomic and financial time series. The publicly available series include the consumer price index, unemployment rate, oil prices, stock prices, gross national product, and corporate profits. The authors conduct a generalized orthogonality test and include only information available to analysts at the time the forecasts are made. The empirical results reject analyst forecast rationality, but not without exception.     

On the Use of Intra-Industry Information to Improve Earnings Forecasts

We investigate whether earnings forecasts are improved by earlier earnings disclosures by firms in the same industry. We find improvements for time series forecasts, but not for analysts' forecasts. Considering prior earnings announcements reduces correlations between forecast errors and security price reactions to earnings announcements, even when incorporating these announcements improves forecast accuracy. Our explanation for this anomaly, which is supported by additional analysis, is that intra-industry information facilitates predicting transitory, rather than permanent, earnings components. The question of whether information transfers improve earnings forecasts provides the context for the analysis, but the primary contribution is the documentation of intra-industry information transfers in a setting other than capital markets.     

Forecasting stock price with the residual income model

The main purpose of this paper is to demonstrate a method to forecast stock price using analyst earnings forecasts as essential signals of firm valuation. The demonstrated method is based on the residual income model (RIM), with adjustment for autocorrelation. Over the past decade, the RIM has been widely accepted as a theoretical framework for equity valuation based on fundamental information from financial reports. This paper shows how to implement the RIM for forecasting and how to address autocorrelation to improve forecast accuracy. Overall, this paper provides a method to forecast stock price that blends fundamental data with mechanical analyses of past time series.     

An evaluation of the professional forecasts of U.S. long-term interest rates

This paper evaluates the multiperiod forecasts of Moody's Aaa corporate and the 10-year Treasury bond rates from the Survey of Professional Forecasters (SPF). We show that the SPF forecasts are not rational since they fail to be unbiased and, in some cases, do not fully incorporate the information in the past actual rates. These forecasts, however, are useful, since they are able to accurately predict the direction of change in the actual series. We also formulate a model that utilizes the information in the SPF forecasts of the unemployment rate. Comparable four-quarter-ahead forecasts of the two interest rates from this model are shown to be significantly more accurate than the corresponding SPF forecasts for 2001.1-2004.4.     

Forecasting government bond yields with large Bayesian vector autoregressions

We propose a new approach to forecasting the term structure of interest rates, which allows to efficiently extract the information contained in a large panel of yields. In particular, we use a large Bayesian Vector Autoregression (BVAR) with an optimal amount of shrinkage towards univariate AR models. The optimal shrinkage is chosen by maximizing the Marginal Likelihood of the model. Focusing on the US, we provide an extensive study on the forecasting performance of the proposed model relative to most of the existing alternative specifications. While most of the existing evidence focuses on statistical measures of forecast accuracy, we also consider alternative measures based on trading schemes and portfolio allocation. We extensively check the robustness of our results, using different datasets and Monte Carlo simulations. We find that the proposed BVAR approach produces competitive forecasts, systematically more accurate than random walk forecasts, even though the gains are small.     

预测中国宏观经济变量:专家与模型的组合预测

本文使用组合预测方法,探究以“朗润预测”为代表的专家预测以及计量模型对于中国宏观经济变量的预测效果,并研究对不同预测进行组合预测是否有助于改进预测效果。本文发现,对我国CPI和GDP的增长率,专家预测效果总体上优于模型预测。从原因看,一方面,专家在预测时已经考虑了计量模型的预测信息;另一方面,在经济出现“拐点”的时期,专家通过对实际经济环境和政策的把握,得出更准确的经济预测。组合预测有助于提升预测精度,对专家预测进行组合得到的预测效果优于大多数的专家预测,“模型—专家”组合预测的效果也优于所有的模型和大部分专家预测。     

Information misweighting and the cross-section of stock recommendations

This paper provides evidence that analysts whose earnings forecast revisions showed signs of greater exaggeration in the past make recommendation changes that lead to lower abnormal returns than their peers. Interpreting stock recommendations as a forecast of future abnormal returns, I show that this evidence is consistent with the hypothesis that analysts who typically exaggerate or overstate the weight of their private information when issuing forecasts also do so when making recommendations. The paper also shows that past earnings forecasts provide incremental information about analysts' recommending behavior beyond that contained in past recommendations.     

Interest Rates,Uncertainty and the Livingston Data

The observed relationship between the standard deviation of forecasts and past forecast errors as found in the Livingston survey suggests the interpretation of the standard deviation as a measure of inflation uncertainty. The mean and the standard deviation for the inflation rate forecast found in the Livingston survey, furthermore, are used as regressors in a reduced-form interest rate equation. The results indicate a large negative effect of such uncertainty on interest rates. The inclusion of the uncertainty measure and commonly omitted lagged values of all variables in our analysis of data leads to more theoretically plausible estimated effects of money growth and expected inflation on interest rates than do standard estimates.     

Accuracy of International Interest Rate Forecasts

This study exploits a unique data source with contemporaneous forecasts of three-month Euromarket interest rates for five different countries. Professional forecasts are explored in a way that avoids two limitations of previous research. First, rather than being restricted to just U.S. interest rates, data are used for five different countries: the United States, Germany, the United Kingdom, Japan, and Switzerland. Second, the study relies upon data gathered on a single date, rather than over a period of weeks. Consensus forecasts are evaluated against two naive models: a no-change model and a forward rate forecast. In general, the consensus forecasts prove superior to the no-change forecast. The consensus measures, though, are found to be inferior to the forward rate forecast. This is true even considering the dramatic success of the banks in forecasting U.S. rates in this period. However, if the spectacular, and perhaps uniquely successful U.S. results are excluded from consideration, the banks proved dramatically inferior to the forward rate of interest in forecasting interest rates. Thus, the ability of these banks to forecast three-month interest rates for these five countries exceeds that of a no-change forecast, but falls below the forecasting ability of the forward rate.     

Announcements of Interest Rate Forecasts: Do Policymakers Stick to Them?

If central banks value the ex post accuracy of their published forecasts, previously announced interest rate paths might influence the current policy rate. We explore if “forecast adherence” has affected monetary policy in New Zealand and Norway, where central banks have published their interest rate forecasts the longest. We derive and estimate policy rules with separate weights on past interest rate forecasts and find that they have explanatory power for current policy decisions, over and above their correlation with other conventional interest rate rule arguments.     

Institutional effects on information content of US and French management earnings forecasts: Evidence from market reactions and analyst revisions

The United States and France are both most developed economies in the world. Their socio-economic institutions, however, are very different. These differences are indications of their dichotomous legal regimes: common law in the US versus code law in France. The political influence of these legal regimes, in turn, leads to a dichotomized classification of accounting systems: the British-American Model and the French Continental Model. This study extends these institutional effects into the field of management earnings forecast. We find that earnings forecasts by French firms are less informative than those made by US firms matched-up by industry and firm size. We also compare US and French financial analysts' revisions of their forecasts following the management forecasts. We find that revisions by French analysts are more influenced by management forecasts. Our findings are consistent with prior studies that argue that information asymmetry in code-law countries is largely resolved through private information channels, rendering less information content in management announcements and less demand and incentives for original research by financial analysts.     

The information in the term structure

This paper presents a regression approach to measuring the information in forward interest rates about time varying premiums and future spot interest rates. Like earlier work, the regressions identify variation in the expected premiums on longer-maturity Treasury bills. The more novel evidence concerns the forecasts of future spot rates in forward rates. The regressions provide evidence that the one-month forward rate has power to predict the spot rate one month ahead. During periods preceding 1974, forward rates have reliable forecast power for one-month spot rates up to five months in the future.     

The jump component of S&P 500 volatility and the VIX index

Much research has investigated the differences between option implied volatilities and econometric model-based forecasts. Implied volatility is a market determined forecast, in contrast to model-based forecasts that employ some degree of smoothing of past volatility to generate forecasts. Implied volatility has the potential to reflect information that a model-based forecast could not. This paper considers two issues relating to the informational content of the S&P 500 VIX implied volatility index. First, whether it subsumes information on how historical jump activity contributed to the price volatility, followed by whether the VIX reflects any incremental information pertaining to future jump activity relative to model-based forecasts. It is found that the VIX index both subsumes information relating to past jump contributions to total volatility and reflects incremental information pertaining to future jump activity. This issue has not been examined previously and expands our understanding of how option markets form their volatility forecasts.     

Properties of Market Expectations of Accounting Earnings by Financial Analysts: UK versus US

This paper compares patterns and properties of financial analysts' forecasts (FAFs) of earnings between the UK and the US. Using 299 UK and 400 US firms from the same data source—Institutional Brokers Estimate System tapes—the accuracy of forecasts is examined and the sources of errors analysed. The results reveal that FAFs errors in the UK are much smaller than those in the US, and that this disparity persists even after controlling for firm size and industry effects. Further, FAFs of US firms demonstrate consistent overestimation of earnings over the sample period 1988–1990, while UK firms show overestimation in only one of three years. A model developed to test the determinants of forecast error reveals that forecasters of UK firms are influenced in a somewhat different fashion from those of US firms. While dispersion, predisclosure information (market capitalisation or number of analysts), and industry are common determinants of forecast error for both countries, the percentage of forecasts revised is a major determinant only for UK firms.     

The forecasting ability of correlations implied in foreign exchange options

This paper evaluates the forecasting accuracy of correlations derived from implied volatilities in dollar-mark, dollar-yen, and mark-yen options from January 1989 to May 1995. As a forecast of realized correlation between the dollar-mark and dollar-yen, implied correlation is compared against three alternative forecasts based on time series data: historical correlation, RiskMetrics' exponentially-weighted moving average correlation, and correlation estimated using a bivariate GARCH(1,1) model. At the 1-month and 3-month forecast horizons, we find that implied correlation outperforms, often significantly, these alternative forecasts. In combinations, implied correlation always incrementally improves the performance of other forecasts, but not the converse; in certain cases, historically-based forecasts contribute no incremental information to implied forecasts. The superiority of the implied correlation forecast holds even when forecast errors are weighted by realized variances, reflecting correlation's contribution to the dollar variance of a multicurrency portfolio.     

Forecasting exchange rates: Do banks know better?

We first evaluate the performance of major commercial banks in forecasting future spot exchange rates, using the random-walk model as the benchmark. We then investigate the sources of forecast errors, and the forecasting tendencies of banks. Our analysis is based on the forecasts made for the US dollar exchange rates of the British pound (BP), German mark (DM), Swiss franc (SF), and Japanese yen (JY), over 3-, 6-, 9-, and 12-month forecast horizons. Key findings include: first, a majority of banks shows some evidence of outperforming the random-walk model for the three currencies other than the JY. Second, the imperfect correlation between predicted and actual exchange rate changes is the dominant source of prediction errors of banks. Third, the home-country bank generally forecasts the country's currency rate more accurately than the other banks, suggesting a degree of information asymmetry. Fourth, the forecasts of a majority of banks exhibit a bandwagon type effect. That is, most banks are momentum forecasters, tending to extrapolate the recent currency changes. Interestingly, a “contrarian” bank is found to outperform the other banks.     

Martingales and efficient forecasts of effective mortgage rates

Economic theory and empirical evidence indicate that the optimal near-term forecast of a long-term rate is (approximately) today's rate; the no-change model should provide excellent near-term forecasts of a long-term rate. This article estimates the longest forecast horizon over which no-change predictions of each of three mortgage-related interest rates pass a series of quality tests. The empirical results reject the optimality of no-change predictions of the one-year Treasury bill rate for all forecast horizons. Since October 1979, the tests support the hypothesis that no-change predictions of the 30-year conventional home mortgage and GNMA rates are optimal for forecast horizons of up to three-quarters-ahead.     

Improving the Precision of Analysts' Earnings Forecasts by Adjusting for Predictable Bias

This research demonstrates that publicly-available information can be used to develop estimates of analysts' optimistic bias in earnings forecasts. These bias estimates can be used to produce more accurate forecasts, resulting in significant reductions of both cross-sectional mean forecast error and error variance. When bias estimates are based on past observations of forecast error alone, however, reductions in mean forecast error are smaller, and forecast precision is unimproved. Further tests provide evidence of a significant association between returns and the bias predictable from contemporaneously-available information, suggesting that predictable bias is only partially discounted by market participants. This study has significant implications for researchers and investors. The pricing of predictable bias in analysts' forecasts may add error toinferences which are based on the association between returns and analyst forecast errors, and knowledge of the market's partial discounting of predictable bias may help investors to make more efficient resource allocations.