Although investment opportunities are not constant, virtually all forecasting techniques rely on notions of central tendency, toward which opportunities tend to revert over time. This fact means that although asset prices, risk premiums, volatilities, valuation ratios, and other metrics may exhibit momentum, persistence, and clustering in the short run, over sufficiently long horizons, they tend to converge to levels consistent with economic and financial fundamentals.

Forecasting returns requires not only assessing expected returns, variances and correlations, but also understanding that time horizons are important.

At a very high level, there are essentially three approaches to forecasting: (1) formal tools, (2) surveys, and (3) judgment. Formal tools are established research methods amenable to precise definition and independent replication of results.

**Surveys** involve asking a group of experts for their opinions.

**Judgment** can be described as a qualitative synthesis of information derived from various sources and filtered through the lens of experience.

The use of **formal tools** helps the analyst set capital market expectations. When applied to reputable data, formal tools provide forecasts replicable by other analysts. The formal tools we examine are statistical methods, discounted cash flow models, and risk premium models.

**Statistical methods** involve sample statistics, shrinkage estimation, and time series estimation.

**Sample statistics**use well-known data, including means, variance, and correlation, to forecast future data. This is the clearest approach in forecasting, but it can be imprecise.- A
**shrinkage estimate**can be applied to the historical estimate if the analyst believes simple historical results do not fully reflect expected future conditions. A shrinkage estimate is a weighted average estimate based on history and some other projection. - A
**time series estimate**can also be used to make forecasts. A time series estimate forecasts a variable using lagged values of the same variable and combines it with lagged values of other variables, which allows for incorporating dynamics (volatilities) into the forecasts.

**Discounted cash flow** models express the intrinsic value of an asset as the present value of future cash flows. The advantage of these models is their correct emphasis on the future cash flows of an asset and the ability to back out a required return.

An alternative to estimating expected return is a **risk premium** or buildup model. Risk premium approaches can be used for both fixed income and equity. The approach starts with a risk-free interest rate and then adds compensation for *priced risks*, or risks for which an investor would want to be compensated. Risk premium models include equilibrium models (e.g., the Capital Asset Pricing Model), a factor model, and building blocks.