Investing Research Articles

Page 1 of 18712345678910...Last »

Models, Trading Calendar and Momentum Strategy Updates

We have updated the Earnings Forecast to incorporate preliminary actual S&P 500 operating earnings for the second quarter of 2014.

We have updated the S&P 500 Market Models summary as follows:

  • Extended Market Models regressions/rolled projections by one month based on data available through July 2014.
  • Updated Market Models backtest charts and the market valuation metrics map based on data available through July 2014.

We have updated the Trading Calendar to incorporate data for July 2014.

We have updated the the monthly asset class momentum winners and associated performance data at Momentum Strategy.

Preliminary Momentum Strategy Update

The home page and “Momentum Strategy” now show preliminary asset class momentum strategy positions for August 2014. The differences in past returns among the top four places are large enough that they are unlikely to change order by the close.

Mutual Fund Hot Hand Performance Robustness Test

“Mutual Fund Hot Hand Performance” tests a “hot hand” strategy that each year picks the top performer from the Vanguard family of diversified equity mutual funds (not including sector funds) and holds that winner the next year. A subscriber suggested a robustness test using the Fidelity family of diversified equity mutual funds. To support the test, we select all Fidelity diversified U.S. and international equity mutual funds that bear no transaction fee, are open to new investors and have a history of at least three years. We consider the total return on the S&P 500 Index (with dividends estimated from Robert Shiller’s data) and SPDR S&P 500 (SPY) as as benchmarks. As in the prior analysis of Vanguard funds, we pick end of June to end of the next June for annual return measurement intervals. To simplify analysis, we assume the “hot hand” mutual fund on the next-to-last trading day of June is the same as that for the end of June. We assume that there are no costs or holding period constraints/delay for switching from one fund to another. Using annual returns for the S&P 500 Index plus Shiller’s dividend data and annual returns for SPY and Fidelity diversified equity mutual funds as available from Yahoo!Finance during June 1980 through June 2014, we find that: Keep Reading

Sharper Sharpe Ratio?

Is there some tractable investment performance metric that corrects weaknesses commonly encountered in financial markets research? In the July 2014 version of their paper entitled “The Deflated Sharpe Ratio: Correcting for Selection Bias, Backtest Overfitting and Non-Normality”, David Bailey and Marcos Lopez de Prado introduce the Deflated Sharpe Ratio (DSR) as a tool for evaluating investment performance that accounts for both non-normality and data snooping bias. They preface DSR development by noting that:

  • Many investors use performance statistics, such as Sharpe ratio, that assume test sample returns have a normal distribution.
  • Fueled by high levels of randomness in liquid markets, testing of a sufficient number of strategies on the same data essentially guarantees discovery of an apparently profitable, but really just lucky, strategy.
  • The in-sample/out-of-sample hold-out approach does not eliminate data snooping bias when multiple strategies are tested against the same hold-out data.
  • Researchers generally publish “successes” as isolated analyses, ignoring all the failures encountered along the road to statistical significance.

The authors then transform Sharpe ratio into DSR by incorporating sample return distribution skewness and kurtosis and by correcting for the bias associated with the number of strategies tested in arriving at “winning” strategy. Based on mathematical derivations and an example, they conclude that:

Keep Reading

Dark Hedge Fund Performance

How do hedge funds electing not to report to a commercial database differ from those that do? In their July 2014 paper entitled “What Happens ‘Before the Birth’ and ‘After the Death’ of a Hedge Fund?”, Vikas Agarwal, Vyacheslav Fos and Wei Jiang compare performances of equity hedge funds before they begin self-reporting, while they are self-reporting; and after they stop self-reporting to commercial databases. They develop a sample of hedge funds that do and do not self-report by matching hedge fund Securities and Exchange Commission (SEC) Form 13F filings to listings of hedge funds that self-report to any of five major hedge fund commercial databases. They then identify subsamples of hedge funds that: (1) initially do not but later do self-report; and, (2) initially do but later do not self-report. They then use the long-only equity holdings in series of Form 13F to analyze performances and characteristics within subsamples. Using 1,199 series of Form 13Fs for firms that are clearly hedge funds during 1980 through 2008 and contemporaneous data for hedge funds self-reporting to commercial databases, they find that: Keep Reading

Individual Investor Equity Market Timing

Should investors believe that they can usefully time the stock market? If so, how big might “usefully” be? In their July 2014 paper entitled “Can Individual Investors Time Bubbles?”, Jussi Keppo, Tyler Shumway and Daniel Weagley investigate persistence in the ability of individual Finnish investors to time the stock market, with focus on timing of two bubbles/crashes. They measure investor timing performance by relating monthly flows into and out of the investor’s portfolio to next-month and next-quarter returns of the value-weighted HEX 25 Index (now the OMX Helsinki 25). They test for persistence by comparing an investor’s relative timing performance in the first half of the sample period (January 1995 through March 2002) to that in the second half (April 2002 through June 2009). They treat January 2000 and October 2007 as beginnings of market crashes and focus on whether an investor performed well during the 12 months before and after each peak. Using data on all trades by 1,386,540 individual Finnish investors during January 1995 through June 2009, they find that: Keep Reading

Weekly Summary of Research Findings: 7/21/14 – 7/25/14

Below is a weekly summary of our research findings for 7/21/14 through 7/25/14. These summaries give you a quick snapshot of our content the past week so that you can quickly decide what’s relevant to your investing needs.

Subscribers: To receive these weekly digests via email, click here to sign up for our mailing list. Keep Reading

GDP Growth and Stock Market Returns

Many stock market commentators cite Gross Domestic Product (GDP) growth as an indicator of stock market prospects, and the financial media dutifully report advance, preliminary and final U.S. GDP growth rates each month on a quarterly cycle. Does GDP or any of its Personal Consumption Expenditures (PCE), Private Domestic Investment (PDI) and government spending components usefully predict stock market returns? Using quarterly and annual seasonally adjusted nominal (final) GDP data as available from the Bureau of Economic Analysis (BEA) during January 1929 through March 2014 (about 84 years) and contemporaneous levels of the S&P 500 Index (since 1950) and the Dow Jones Industrial Average (DJIA), we find that: Keep Reading

Sources of Active Equity Mutual Fund Risk

Are the sources of active mutual fund risk mostly common (systematic) or unique (idiosyncratic)? In his July 2014 paper entitled “Components of Portfolio Variance: R2, SelectionShare and TimingShare”, Anders Ekholm decomposes mutual fund return variance (risk) into three sources: (1) passive systematic factor exposure (R-squared); (2) active security selection or stock picking (SelectionShare); and, (3) active systematic factor timing (TimingShare). He demonstrates estimation of these three components based on mutual fund returns (reflecting daily manager actions) rather than holdings (known only via quarterly snapshots). He employs the widely used four-factor (market, size, book-to-market, momentum) model of stock returns to define systematic risk. Using daily returns for a broad sample of actively managed U.S. equity mutual funds and for the four factors during 2000 through 2013, he finds that: Keep Reading

Composite Stock Market Valuation Model

Is there some better predictor of long-term stock market return than the widely cited cyclically adjusted price-earnings ratio (P/E10 or CAPE)? In the July 2014 version of his paper entitled “Forecasting Equity Returns: An Analysis of Macro vs. Micro Earnings and an Introduction of a Composite Valuation Model”, Stephen Jones compares how well several fundamental and economic factors predict real long-term (10-year) equity market total return, with focus on Market Value/Gross Domestic Product (MV/GDP). He compares the predictive power of MV/GDP to those of P/E10 and Tobin’s q. He then constructs a multi-variable forecasting model that includes MV/GDP, a demographic metric and personal income-related variables. Using U.S. data since 1954 for different input variables, he finds that: Keep Reading

Page 1 of 18712345678910...Last »
Avoiding Investment Strategy Flame-outs eBook
Login
Current Momentum Winners

ETF Momentum Signal
for August 2014 (Final)

Momentum ETF Winner

Second Place ETF

Third Place ETF

Gross Momentum Portfolio Gains
(Since August 2006)
Top 1 ETF Top 2 ETFs
213% 220%
Top 3 ETFs SPY
211% 75%
Strategy Overview
Recent Research
Popular Posts
Popular Subscriber-Only Posts