The efficient markets hypothesis is one of the most controversial and hotly contested ideas in all the social sciences. It is disarmingly simply to state, has far-reaching consequences for academic pursuits and business practice, and yet is surprisingly resilient to empirical proof or refutation. Even after three decades of research and literally thousands of journal articles, economists have not yet reached a consensus about whether markets - particularly financial markets - are efficient or not.

In the ’50s and ’60s, just as the era of the professional portfolio manager was dawning, financial economists were telling anyone who would listen that active management was probably a big mistake—a waste of time and money. Their research demonstrated that historical prices were of little use in helping to predict where future prices would go. Prices simply took a “random walk.” The better part of wisdom, they advised, was to be a passive investor. At first, not too many of the people who influence the way money is managed (those who select managers of large portfolios) listened. But as time went on, it became apparent that they should have. Because of fees and turnover, the managers they picked typically underperformed the market. And the worse an active manager did relative to a market index, the more attractive seemed the low cost alternative of buying and holding the index itself. But as luck would have it, just as indexing was gaining ground, a new wave of academic research was being published that weakened some of the results of the earlier research and thereby undercut part of the justification for indexing. It didn’t obviate all the reasons for indexing (indexing was still a low-cost way to create diversification for an entire fund or as part of an active/passive strategy), but it did tend to silence the index-because-you-can’t-do better school.

The practice of risk management starts with an understanding of the statistical behavior of financial asset prices over time. Models such as the random walk hypothesis, the martingale model, and geometric Brownian motion are fundamental to any analysis of financial risks and rewards, particularly for longer investment horizons. Recent empirical evidence has cast doubt on some of these models, and this article provides an overview of such evidence. I begin with a review of the random walk hypothesis and related models, including a discussion of why such models perform so poorly, and then turn to some current research on alternative models such as long-term memory models and stable distributions.

While financial economics is still in its infancy when compared to the mathematical and natural sciences, it has enjoyed a spectacular period of growth over the past three decades, thanks in part to the mathematical machinery that Wiener, Ito, and others pioneered. In this review article, I shall present a survey of some recent research in this exciting area—more specifically, in empirical finance and financial econometrics—including a discussion of the random walk hypothesis, long-term memory in stock market prices, performance evaluation, and the statistical estimation of diffusion processes. It is my hope that such a survey will serve both as a tribute to the amazing reach of Nobert Wiener's research, and as an enticement to those in the "hard" sciences to take on some of the challenges of modern finance.

We construct portfolios of stocks and of bonds that are maximally predictable with respect to a set of ex ante observable economic variables, and show that these levels of predictability are statistically significant, even after controlling for data-snooping biases. We disaggregate the sources for predictability by using several asset groups—sector portfolios, market-capitalization portfolios, and stock/bond/utility portfolios—and find that the sources of maximal predictability shift considerably across asset classes and sectors as the return-horizon changes. Using three out-of-sample measures of predictability—forecast errors, Merton's market-timing measure, and the profitability of asset allocation strategies based on maximizing predictability—we show that the predictability of the maximally predictable portfolio is genuine and economically significant.

The regulation of financial markets has for years been the domain of lawyers, legislators, and lobbyists. In this unique volume, experts in industrial organization, finance, and law, as well as members of regulatory agencies and the securities industry, examine the securities industry from an economic viewpoint.

Ten original essays address topics including electronic trading and the "virtual"stock exchange; trading costs and liquidity on the London and Tokyo Stock Exchanges and in the German and Japanese government bond markets; international coordination among regulatory agencies; and the impact of changing margin requirements on stock prices, volatility, and liquidity.

This clear presentation of groundbreaking research will appeal to economists, lawyers, and legislators who seek a refreshingly new perspective on policy issues in the securities industry.

A securities transactions tax is likely to have far-reaching and profound implications for the financial systems and institutions. We evaluate the effect that a transactions tax will have on the financial system's role in transferring resources over time and in allocating risk efficiently across individuals and sectors. In particular, we examine the impact of a transactions tax on individual investors due to the reduction in the rate of return on savings, the reduction in trading, and the likely reduction in the value of stocks. We also consider the possible effects of a transactions tax on market liquidity. By reducing the informational role of prices and reducing market liquidity, a transactions tax may result in higher market volatility. We provide a simple numerical example that illustrates the enormous impact such a tax will have on the derivatives markets, where participants rely heavily on dynamic trading strategies to control risk. This sector of the financial system, along with its jobs, revenues, and risk-management capabilities are likely to move offshore in response to the tax.

The predictability of an asset's returns will affect option prices on that asset, even though predictability is typically induced by the drift which does not enter the option pricing formula. For discretely-sampled data, predictability is linked to the parameters that do enter the option pricing formula. We construct an adjustment for predictability to the Black-Scholes formula and show that this adjustment can be important even for small levels of predictability, especially for longer-maturity options. We propose several continuous-time linear diffusion processes that can capture broader forms of predictability, and provide numerical examples that illustrate their importance for pricing options.

Data-snooping—finding seemingly significant but in fact spurious patterns in the data—is a serious problem in financial analysis. Although it afflicts all non-experimental sciences, data-snooping is particularly problematic for financial analysis because of the large number of empirical studies performed on the same datasets. Given enough time, enough attempts, and enough imagination, almost any pattern can be teased out of any dataset. In some cases, these spurious patterns are statistically small, almost unnoticeable in isolation. But because small effects in financial calculations can often lead to very large differences in investment performance, data-snooping biases can be surprisingly substantial. In this review article, I provide several examples of data-snooping biases, explain why it is impossible to eliminate them completely, and propose several ways to guard against the most extreme forms of data-snooping in financial analysis.

Although they are only one of the many types of statistical tools for modeling nonlinear relationships, neural networks seem to be surrounded by a great deal of mystique and, sometimes, misunderstanding. Because they have their roots in neurophysiology and the cognitive sciences, neural networks are often assumed to have brain-like qualities: learning capacity, problem-solving abilities, and ultimately, cognition and self-awareness. Alternatively, neural networks are often viewed as "black boxes" that can yield accurate predictions with little modeling effort. In this review paper, I hope to remove some of the mystique and misunderstandings about neural networks by providing some simple examples of what they are, what they can and cannot do, and where neural nets might be profitably applied in financial contexts.

We propose a nonparametric method for estimating the pricing formula of a derivative asset using learning networks. Although not a substitute for the more traditional arbitrage-based pricing formulas, network pricing formulas may be more accurate and computationally more efficient alternatives when the underlying asset's price dynamics are unknown, or when the pricing equation associated with no-arbitrage condition cannot be solved analytically. To assess the potential value of network pricing formulas, we simulate Black-Scholes option prices and show that learning networks can recover the Black-Scholes formula from a six-month training set of daily options prices, and that the resulting network formula can be used successfully to both price and delta-hedge options out-of-sample. For purposes of comparison, we perform similar simulation experiments for four other methods of estimation: OLS, kernel regression, projection pursuit, and multilayer perceptron networks. To illustrate the practical relevance of our network pricing approach, we apply it to the pricing and delta-hedging of S&P 500 futures options from 1987 to 1991.

The non-trading or non-synchronous effect arises when time series, usually financial asset prices, are taken to be recorded at time intervals of one length when in fact they are recorded at time intervals of another, possibly irregular, lengths. For example, the daily prices of securities quoted in the financial press are usually "closing" prices, prices at which the last transaction in each of those securities occurred on the previous business day. these closing prices generally  do not occur at the same time each day, but by calling them "daily" prices, we have implicitly and incorrectly assumes that they are equally spaces at 24-hour intervals. Such an assumption can generate spurious predictability in price changes and returns even if true price changes or returns are statistically independent. The non-trading effect induces potentially serious biases in the moments and co-moments of asset returns such as their means, variances, covariances, and autocorrelation and cross-autocorrelation coefficients.

The pricing of options, certificates, and other derivatives or assets—financial assets whose payments depend on the prices of other assets—is one of the great successes of modern financial economics. Although the pricing of derivatives is computationally intensive, there is little done in terms of the traditional empirical analysis since by the very nature of the determination of prices and arbitrage there is no error term to minimize. There are, however, many issues of statistical inference that affect the pricing of options and other derivatives. This paper analyzes two of the most common issues neglected in the literature: reduced form empirical instruments for the determination of prices and how to use Monte Carlo simulations to calculate option prices depend on a path.

We estimate the conditional distribution of trade-to-trade price changes using ordered probit, a statistical model for discrete random variables. This approach recognizes that transaction price changes occur in discrete increments, typically eighths of a dollar, and occur at irregularly-spaced time intervals. Unlike existing models of discrete transaction prices, ordered probit can quantify the effects of other economic variables like volume, past price changes, and the time between trades on price changes. Using 1988 transactions data for over 100 randomly chosen U.S. stocks, we estimate the ordered probit model via maximum likelihood and use the parameter estimates to measure several transaction-related quantities, such as the price impact of the trades of a given size, the tendency towards price reversals from one transaction to the next, and the empirical significance of price discreteness.

A test for long-run memory that is robust to short-range dependence is developed. It is an extension of the "range over standard deviation" or R/S statistic, for which the relevant asymptotic sampling theory is derived via functional central limit theory. This test is applied to daily and monthly stock returns indexed over several time periods and, contrary to previous findings, there is no evidence of long-range dependence in any of the indexes over any sample period or sub-period once short-range dependence is taken into account. Illustrative Monte Carlo experiments indicate that the modified R/S test has power against at least two specific models of long-run memory, suggesting that stochastic models of short-range dependence may adequately capture the time series behavior of stock returns.