Garbage in, garbage out with Monte Carlo analysis
“People use this technique in retirement planning to figure out what their retirement [could] look like,” Stammers says. It helps them determine the likelihood they will have saved enough money.
Executing a meaningful Monte Carlo analysis requires financial and economic savvy. Specifically, if the data and assumptions entered into the model aren’t realistic, then the results won’t provide a meaningful insight. “It’s garbage in, garbage out,” Stammers adds. “If you put in bad information — like bad probabilities, if your expectations are bad — then you’ll get bad outputs.”
That raises another issue: how to identify the appropriate data and assumptions. These can include forecasts of future stock returns, inflation rates and interest rates. Even veteran Wall Street professionals can find it challenging to make forecasts in this field. Selecting appropriate variables requires the specialized skills of an experienced analyst.
Those who do possess such skills use their knowledge and experience to make changes to the Monte Carlo inputs. They base those adjustments on fluctuating market circumstances and the economy’s health. In this way, the results of the simulation may reflect reasonable assumptions and are more likely to be useful.
A key variable used in Monte Carlo analysis for investors is the value of stocks relative to their earnings — the price-to-earnings ratio. Based on this metric, some financial analysts might forecast lower future stock returns when stock values are relatively higher. They might also increase their expected stock returns when valuations look low. “We go into the software, and we adjust forward returns based on a valuation metric,” says Richard Rosso, director of financial planning at RIA Advisors.