Do Timber Prices Follow a Random Walk or are They Mean-Reverting?

Timber price forecasts are important components of timberland investment analysis. Two techniques are widely used in forecasting. Econometric models use one or more independent variables to predict a dependent variable. Time series analysis or autoregression techniques use the prior observations of a variable, and only those prior observations, to make predictions of that variable. Either technique could be used in making timber price forecasts. However, when forecasting prices for many different timber species and products, time series techniques may be more cost effective. Econometric models used in forecasting timber prices can be complex because demand for timber is derived through demand for other products such as paper and housing. In contrast to econometric methods, time series techniques allow price forecasts to be made from the timber price series themselves. A necessary condition for using time series techniques is that the timber price series be mean-reverting or stationary. The null hypothesis in this study was that timber prices would not be stationary and time series techniques could not be applied to their analysis. Stationarity tests indicated that all of the price series were either first or second difference stationary. However, these tests tested only for a constant mean, and not for a constant variance. Charts of all the price series indicate that the variability of each series has changed over time. Since a constant variance is a required condition of stationarity, this result suggests the primary hypothesis should not be rejected. Process control charts were used to analyze the changing variances and to determine if recent subsets with fixed mean and variance existed. All price series and natural logs of those price series were first difference stationary over some recent subset of years. The null hypothesis—that timber prices follow random walks—can be rejected for the most recent subsets of all the price series tested. 1 Forest Economist, Hancock Timber Resource Group, 99 High Street, 26 Floor, Boston, MA 02110 2 This paper is adapted from Lutz, Jack. 1998. Timber Price Trends. unpublished PhD dissertation. University of New Hampshire. Durham, NH. INTRODUCTION Timber price forecasts are an important component in timberland investment decisions. Examples of the decisions depending in part on timber prices are: 1. Acquisitions—what price should be paid for a property? 2. Hold/Sell Decisions—is a property providing adequate returns (hold) or are the returns too low (sell)? 3. Strategic Dispositions—when dispositions are due to an imbalance in a portfolio or the cash needs of a client, which property or properties should be sold and what price should be received for this property? 4. Forest Management Planning—how can operating plans and budgets be fine-tuned to maximize returns in anticipation of fluctuations in timber prices? Most timberland investment decisions are based on a projected rate of return—usually an internal rate of return (IRR)—for the property. The projected IRR is calculated from the actual or hypothetical investment in the property and projected cash flows. The cash flows consist of two pieces: annual revenues and a “residual” value. The annual revenues are primarily generated by timber sales. The “residual” value is the value of the property at the end of the investment period, and represents the cash received from the actual or hypothetical sale of the property. A substantial portion of this “residual” value is the value of the standing timber on the property at that time.