Objective research to aid investing decisions

Value Investing Strategy (Strategy Overview)

Allocations for December 2022 (Final)

Momentum Investing Strategy (Strategy Overview)

Allocations for December 2022 (Final)
1st ETF 2nd ETF 3rd ETF

Technical Trading

Does technical trading work, or not? Rationalists dismiss it; behavioralists investigate it. Is there any verdict? These blog entries relate to technical trading.

Machine-assisted Stock Price Pattern Analysis

Can machine learning software discover predictive stock price patterns? In their December 2020 paper entitled “(Re-)Imag(in)ing Price Trends”, Jingwen Jiang, Bryan Kelly and Dacheng Xiu apply convolutional neural network machine learning software to analyze stock price series images (depicting daily open, high, low, close and moving average prices and trading volume) in search of the patterns most predictive of future returns. Their model standardizes price series scales, recursively smooths and accentuates certain shape elements of images of the last 5, 20 and 60 days trading to isolate patterns that predict returns over the next 5, 20 and 60 days. They translate predictions into hedge portfolio performance by each month going long (short) the tenth, or decile, of stocks with the strongest (weakest) return forecasts. They benchmark performance against hedge portfolios for conventional momentum (return from 12 months ago to one month ago), 1-month short-term reversal and 1-week short-term reversal. Using daily price and volume series for all listed U.S. stocks during January 1993 through December 2019, they find that: Keep Reading

QQQ:IWM for Risk-on and GLD:TLT for Risk-off?

A subscriber asked about a strategy that switches between an equal-weighted portfolio of Invesco QQQ Trust (QQQ) and iShares Russell 2000 ETF (IWM) when the S&P 500 Index is above its 200-day simple moving average (SMA200) and an equal-weighted portfolio of SPDR Gold Shares (GLD) and iShares 20+ Year Treasury Bond ETF (TLT) when below. Also, more generally, is an equal-weighted portfolio of GLD and TLT (GLD:TLT) superior to TLT only for risk-off conditions? To investigate, we (1) backtest the switching strategy and (2) compare performances of GLD:TLT versus TLT when the S&P 500 Index is below its SMA200. We consider both gross and net performance, with the latter accounting for 0.1% portfolio switching frictions 0.001% daily portfolio rebalancing frictions (rebalancing one hundredth of portfolio value). As benchmarks, we consider buying and holding SPDR S&P 500 ETF Trust (SPY) and a strategy that holds SPY (TLT) when the S&P 500 Index is above (below) its SMA200. Using daily S&P 500 Index levels starting February 5, 2004 and daily dividend-adjusted levels of QQQ, IWM, GLD, TLT and SPY starting November 18, 2004 (limited by inception of GLD), all through November 25, 2020, we find that:

Keep Reading

Combining Economic Policy Uncertainty and Stock Market Trend

A subscriber requested, as in “Combine Market Trend and Economic Trend Signals?”, testing of a strategy that combines: (1) U.S. Economic Policy Uncertainty (EPU) Index, as described and tested separately in “Economic Policy Uncertainty and the Stock Market”; and, (2) U.S. stock market trend. We consider two such combinations. The first combines:

  • 10-month simple moving average (SMA10) for the broad U.S. stock market as proxied by the S&P 500 Index. The trend is bullish (bearish) when the index is above (below) its SMA10 at the end of last month.
  • Sign of the change in EPU Index last month. A positive (negative) sign is bearish (bullish).

The second combines:

  • SMA10 for the S&P 500 Index as above.
  • 12-month simple moving average (SMA12) for the EPU Index. The trend is bullish (bearish) when the EPU Index is below (above) its SMA12 at the end of last month.

We consider alternative timing strategies that hold SPDR S&P 500 (SPY) when: the S&P 500 Index SMA10 is bullish; the EPU Index indicator is bullish; either indicator for a combination is bullish; or, both indicators for a combination are bullish. When not in SPY, we use the 3-month U.S. Treasury bill (T-bill) yield as the return on cash, with 0.1% switching frictions. We assume all indicators for a given month can be accurately estimated for signal execution at the market close the same month. We compute average net monthly return, standard deviation of monthly returns, net monthly Sharpe ratio (with monthly T-bill yield as the risk-free rate), net compound annual growth rate (CAGR) and maximum drawdown (MaxDD) as key strategy performance metrics. We calculate the number of switches for each scenario to indicate sensitivities to switching frictions and taxes. Using monthly values for the EPU Index, the S&P 500 Index, SPY and T-bill yield during January 1993 (inception of SPY) through September 2020, we find that:

Keep Reading

SPY 30-day/9-month SMA Crossover Test

A subscriber requested testing of a dual simple moving average (SMA) crossover strategy that holds SPDR S&P 500 (SPY) when its 30-day SMA (SMA30d, using 30 trading days) is above its 9-month SMA (SMA9m) and otherwise holds cash with yield that of 3-month U.S. Treasury bills (T-bills). To investigate, we calculate SPY SMA30d and SMA9m at the end of each month over the history of SPY and hold SPY or cash the next month as specified. As benchmarks, we consider buying and holding SPY and a strategy that is each month in SPY (cash) when SPY is above (below) its SMA9m at the end of the prior month. We focus on compound annual growth rate (CAGR) and maximum drawdown (MaxDD) as key performance metrics. We also perform some sensitivity testing on the choices of 30-day and 9-month SMAs. Using daily dividend-adjusted prices for SPY and monthly T-bill yields during January 1993 through September 2020, we find that: Keep Reading

Distinct and Predictable U.S. and ROW Equity Market Cycles?

A subscriber asked: “Some pundits have noted that U.S. stocks have greatly outperformed foreign stocks in recent years. What does the performance of U.S. stocks vs. foreign stocks over the last N years say about future performance?” To investigate, we use the S&P 500 Index (SP500) as a proxy for the U.S. stock market and the ACWI ex USA Index as a proxy for the rest-of-world (ROW) equity market. We consider three ways to relate U.S. and ROW equity returns:

  1. Lead-lag analysis between U.S. and ROW annual returns to see whether there is some cycle in the relationship.
  2. Multi-year correlations between U.S. and next-period ROW returns, with periods ranging from one to five years.
  3. Sequences of end-of-year high water marks for U.S. and ROW equity markets.

For the first two analyses, we relate the U.S. stock market to itself as a control (to assess whether ROW market behavior is distinct). Using end-of-year levels of the S&P 500 Index and the ACWI ex USA Index during 1987 (limited by the latter) through 2019, we find that: Keep Reading

Optimal SMA Lookback Interval?

Is a 10-month simple moving average (SMA10) the best SMA for long-term crossing signals? If not, is there some other optimal SMA lookback interval? To check, we compare performance statistics for SMA crossing signals generated by lookback intervals ranging from 2 (SMA2) to 48 months (SMA48), as applied to the S&P 500 Index. Using monthly S&P 500 Index closes, monthly S&P 500 Composite Index dividend data from Robert Shiller and monthly average yields for 3-month Treasury bills (T-bills) during January 1928 (except January 1934 for T-bills) through June 2020, we find that: Keep Reading

Mitigating Impact of Price Turning Points on Trend Following

Is there a way to mitigate adverse impact of price trajectory turning points (trend changes) on performance of intrinsic (absolute or time series) momentum strategies? In their May 2020 paper entitled “Breaking Bad Trends”, Ashish Garg, Christian Goulding, Campbell Harvey and Michele Mazzoleni measure impact of turning points on time series momentum strategy performance across asset classes. They define a turning point as a month for which slow (12-month or longer lookback) and fast (3-month or shorter lookback) momentum signals disagree on whether to buy or sell. They test a dynamic strategy to mitigate trend change impact based on turning points defined by disagreement between 12-month (slow) and 2-month (fast) momentum signals. Specifically, their dynamic strategy each month:

  1. For each asset, measures slow and fast momentum as averages of monthly excess returns over respective lookback intervals.
  2. Specifies the trend condition for each asset as: (1) Bull (slow and fast signals both non-negative); (2) Correction (slow non-negative and fast negative); Bear (slow and fast both negative); and, Rebound (slow negative and fast non-negative). For Bull and Bear (Correction and Rebound) conditions, next-month return is the same (opposite in sign) for slow and fast signals.
  3. After trend changes (Corrections and Rebounds separately), empirically determines with at least 48 months of historical data optimal weights for combinations of positions based on slow and fast signals.

They compare performance of this dynamic strategy with several conventional (static) time series momentum strategies, with each competing strategy retrospectively normalized to 10% test-period volatility. They test strategies on 55 futures, forwards and swaps series spanning four asset classes, with returns based on holding the nearest contract and rolling to the next at expiration. Using monthly returns for futures, forwards and swaps for 12 equity indexes, 10 bond indexes, 24 commodities and 9 currency pairs as available during January 1971 through December 2019, they find that:

Keep Reading

Combining Market Trend and Chicago Fed NFCI Signals

In response to “Exploiting Chicago Fed NFCI Predictive Power”, which tests practical use of the Federal Reserve Bank of Chicago’s National Financial Conditions Index (NFCI) for U.S. stock market timing, a subscriber suggested combining this strategy with stock market trend as in “Combine Market Trend and Economic Trend Signals?”. To investigate, we use the 40-week simple moving average (SMA40) for the S&P 500 Index to measure stock market trend. We then test two strategies that are each week in SPDR S&P 500 (SPY) or cash (U.S. Treasury bills, T-bills), as follows:

  1. Combined (< Mean): hold SPY (cash) when either: (a) prior-week S&P 500 Index is above (below) its SMA40; or, (b) prior-week change in NFCI is below (above) its mean since since the beginning of 1973.
  2. Combined (< Mean+SD): hold SPY (cash) when either: (a) prior-week S&P 500 Index is above (below) its SMA40; or, (b) prior-week change in NFCI is below (above) its mean plus one standard deviation of weekly changes in NFCI since the beginning of 1973.

The return week is Wednesday open to Wednesday open (Thursday open when the market is not open on Wednesday) per the NFCI release schedule. SMA40 calculations are Tuesday close to Tuesday close to ensure timely availability of signals before any Wednesday open trades. We assume SPY-cash switching frictions are a constant 0.1% over the sample period. Using weekly NFCI data since January 1973, weekly S&P 500 Index levels since April 1992, weekly dividend-adjusted opens of SPY and weekly T-bill yield since February 1993 (limited by SPY), all as specified through April 2020, we find that:

Keep Reading

10-month vs. 40-week vs. 200-day SMA

A reader proposed: “I would love to see a backtest pitting a 10-month simple moving average (SMA) against a 200-day SMA for SPDR S&P 500 (SPY). I assume trading costs would go through the roof on the latter, but do performance gains offset additional costs?” Others asked about a 40-week SMA. To investigate, we use the three SMAs to time SPY since its inception and compare results. Specifically, we buy (sell) SPY at the close as it crosses above (below) the SMA, anticipating crossing signals such that trades occur at the close on the signal day (assuming calculations can occur just before the close). The baseline SMA calculation series is dividend-adjusted, but we also check use of unadjusted prices and underlying S&P 500 Index levels. We assume return on cash is the 3-month U.S. Treasury bill (T-bill) yield (ignoring settlement delays). We use a baseline 0.1% one-way SPY-cash switching frictions and test sensitivity to frictions ranging from 0.0% to 0.5% (but assume dividend reinvestment is frictionless). Using daily dividend-adjusted and unadjusted closes for SPY, daily closes of the S&P 500 Index and daily T-bill yield from the end of January 1993 through mid-April 2020, we find that:

Keep Reading

SMA Signal Effectiveness Across Stock ETFs

Simple moving averages (SMA) are perhaps the most widely used and simplest market regime indicators. For example, many investors estimate that a stock index, exchange-traded fund (ETF) or individual stock priced above (below) its 200-day SMA is in a good (bad) regime. Do SMA signals/signal combinations usefully and consistently distinguish good and bad regimes across different kinds of U.S. stock ETFs? To investigate, we test regime signals of 50-day, 100-day and 200-day SMAs and combinations of them across broad equity market (DIASPYIWBIWM and QQQ), equity style (IWDIWFIWN and IWO) and equity sector (XLBXLEXLFXLIXLKXLPXLUXLV and XLY) ETFs. We consider also three individual stocks: Apple (AAPL), Berkshire Hathaway (BRK-B) and Wal-Mart (WMT). We focus on compound annual growth rate (CAGR) for comparisons, but also look at a few other performance metrics. Using daily dividend-adjusted closes of these 18 ETFs and three stocks during late July 2000 (limited by IWN and IWO) through late April 2020, we find that: Keep Reading

Daily Email Updates
Filter Research
  • Research Categories (select one or more)