At vero eos et accusamus et iusto odio dignissimos ducimus qui blanditiis praesentium voluptatum deleniti atque corrupti quos dolores et quas molestias excepturi sint occaecati cupiditate non provident, similique sunt in culpa qui officia deserunt mollitia animi, id est laborum et dolorum fuga.
Et harum quidem rerum facilis est et expedita distinctio. Nam libero tempore, cum soluta nobis est eligendi optio cumque nihil impedit quo minus id quod maxime placeat facere possimus, omnis voluptas assumenda est, omnis dolor repellendus.
Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat.
One way is to use a top-down revenue forecast for the entire market, and infer your company's growth given a fixed or growing market penetration rate relative to the market. For example, if you are valuing an automobile manufacturer, you could obtain historical and forecast U.S. automobile unit production for the entire market. Over the historical period, you could compute your company's overall market share. Over the forecast period, you could infer unit production (or revenue) at the same constant market share or assume additional market penetration; that is, if the unit production for the market is 1 million units and your company manufactures 100,000 units in the prior year (10%), then you revenue forecast would be 10% of forecast unit production on a going forward basis in stable market share scenario. You could assume the market share increased to 12.5% or some other percentage depending upon the competitive dynamics of the market and your firm.
I generally prefer to think in terms of the broader market first because the overall market is easier to forecast (subject to less statistical noise) than the individual companies revenues. It then creates a frame of reference for your company, placing your company within the context of the size of overall market. You can then determine the true prospects for growth (i.e. organize industry growth, market share penetration, etc.). That type of analysis is generally more meaningful (at least in my opinion), than just extrapolating a historical growth rate.
Also, you should put the firm in the context of its product life cycle, because firms generally do not continue to increase there revenues in a linear fashion. Hence, regression is not a great proxy for a firm.
Thanks for your answer. One question I have is about putting the firm in its product cycle. It does make sense to predict the revenue in a non-linear fashion, because I am valuing a highly volatile technology firm whose revenue growth fluctuates in the range between 30% and 80%. However, if I let the revenue prediction fluctuate, my cap ex and depreciation also needs to change on a consistent basis, as well as my beta. Won’t that make my prediction subject to more errors?
I suppose. But the reality is business valuation is in inexact science either way. With a highly risky technology company your prediction will always be subject to significant forecasting error, otherwise the investment wouldn't be risky. So, yes you are correct, your forecasting will be subject to error. Either way, your cash flow stream should provide an expectation of future after-tax cash flows that are grounded in economic reality. So, you should probably use a three-stage discount model, projection accelerating, moderating, and sustainable growth rates in each stage, tie your capital expenditure projections to support the revenue growth, and, adjust your discount rate, say, at each stage of the DCF.