Biases in Analysts’ Methods

The methods analysts use to estimate future returns tend to be influenced by data mining and time period biases.

Data mining refers to the fact that given enough data, certain relationships may appear due to randomness yet have no real relationship that will apply in future periods. Such relationships are not meaningful. One way to identify potential spurious correlations is to question why such a relationship would exist. “No story, no future.”

Time period bias reflects the fact that many research findings are sensitive to the start and end dates of the period measured. If a certain asset had fifty poor years followed by two very good ones, the inclusion or exclusion of those two years could have a significant impact on the results of the study.

For more information, see all articles on: Asset Allocation, FInancial Planning, Investment Returns, Portfolio Management

See also:
  • Data Measurement Errors and Biases
  • Why Sell Short?
  • Limitations of Economic Data
  • What is Earnings Quality?
  • Index Weighting Methods
  • Technical Analysis Explained : The Successful Investor's Guide to Spotting Investment Trends and Turning Points

    The Intelligent Investor: The Classic Text on Value Investing

    Financial Statement Analysis: A Practitioner's Guide, 3rd Edition

    Managing Investment Portfolios: A Dynamic Process (CFA Institute Investment Series)

    Leave a Reply

    You must be logged in to post a comment.