Technical indicators: what peer-reviewed research actually says

also called: golden cross, death cross, trading-range breakout, MACD as trend filter

Where it comes from. The oldest tested family. Charles Dow's editorials (1900s) informalized trend; the first rigorous academic test was Fama & Blume (1966) on filter rules, which found nothing after costs. The modern debate starts with Brock, Lakonishok & LeBaron (1992), who found simple MA and breakout rules genuinely predictive on 90 years of Dow data.

What the research supports. On 1897–1986 data, MA rules produced buy signals that reliably preceded higher returns than sell signals (Brock et al. 1992) — the single most-cited pro-TA result in finance. Technical indicators also carry real forecasting information for the aggregate equity risk premium, especially around business-cycle peaks (Neely, Rapach, Tu & Zhou 2014).

What it does not support. The edge largely dies out of sample. Correcting the same rule universe for data snooping erases most significance (Sullivan, Timmermann & White 1999); measured trading costs exceed the break-even costs of the BLL rules (Bessembinder & Chan 1998); and rules that predicted small-cap and NASDAQ indexes stop working after ETFs made those indexes cheap to arbitrage (Hsu, Hsu & Kuan 2010). Nobody has shown a simple public MA rule beating costs in modern large-cap equities.

Sources: Fama & Blume (1966) · Brock, Lakonishok & LeBaron (1992) · Sullivan, Timmermann & White (1999) · Bessembinder & Chan (1998) · Hsu, Hsu & Kuan (2010) · Neely, Rapach, Tu & Zhou (2014)

also called: time-series momentum, cross-sectional momentum, 'the trend is your friend'

Where it comes from. Not a chart pattern but a return regularity: assets that performed well keep performing well for months. Documented in stocks by Jegadeesh & Titman (1993) and generalized across 58 futures/FX/bond markets as time-series momentum by Moskowitz, Ooi & Pedersen (2012).

What the research supports. This is the best-supported idea 'technical' trading points at. Buying 3–12-month winners and selling losers earned significant excess returns in US stocks (Jegadeesh & Titman 1993); 12-month time-series momentum is positive in nearly every liquid futures market (Moskowitz, Ooi & Pedersen 2012); and a reconstruction back to 1880 finds positive trend-following returns in every decade since (Hurst, Ooi & Pedersen 2017).

What it does not support. It is not a free lunch and not a precise entry signal. Momentum suffers rare, violent crashes — losing over 70% in months during 1932 and 2009 rebounds (Daniel & Moskowitz 2016) — and the academic effect is a diversified portfolio phenomenon at monthly horizons, not a promise that any single chart's trend will continue.

Sources: Jegadeesh & Titman (1993) · Moskowitz, Ooi & Pedersen (2012) · Hurst, Ooi & Pedersen (2017) · Daniel & Moskowitz (2016)

also called: RSI 30/70, mean-reversion timing, 'overbought bounce'

Where it comes from. RSI, ATR and ADX come from J. Welles Wilder's 1978 trade book — engineering heuristics, never peer-reviewed at birth. The phenomenon they gesture at, short-horizon reversal, IS academic: securities that fell over days-to-a-month tend to bounce (Jegadeesh 1990; Lehmann 1990).

What the research supports. Short-term reversal is a real, strongly significant return regularity (Jegadeesh 1990; Lehmann 1990) — the statistical soil oscillators grow in. On 60 years of the London FT30, mechanical RSI and MACD rules beat buy-and-hold before costs in most specifications (Chong & Ng 2008).

What it does not support. The reversal profits live in small, high-turnover trades that transaction costs consume — Lehmann himself flagged the cost sensitivity — and the specific 30/70 thresholds have no derivation; they are Wilder's round numbers. No robust study validates RSI levels as a standalone profitable signal in modern, cost-realistic conditions.

Sources: Wilder (1978) · Jegadeesh (1990) · Lehmann (1990) · Chong & Ng (2008)

also called: round numbers, prior highs/lows, 'levels the market respects'

Where it comes from. As old as charting itself. The credible mechanism arrived when researchers looked at actual order books: customer stop-loss and take-profit orders cluster heavily at round numbers, which mechanically creates bounce points and breakout accelerations.

What the research supports. Support/resistance levels published by major FX dealers had genuine intraday predictive content — prices bounced off them more often than chance (Osler 2000). The mechanism is documented: take-profit orders cluster ON round numbers and stop-losses just BEYOND them, so trend reversals at round levels and faster moves after breaks are real order-flow effects, not chart mysticism (Osler 2003).

What it does not support. Predictive content is not a trading system: the documented effects are intraday, small, and strongest in FX where the order data lives. Nothing supports precise 'retest' entry rituals or the idea that drawn lines on any chart carry power beyond where orders actually cluster.

Sources: Osler (2000) · Osler (2003)

also called: classical charting, pattern trading

Where it comes from. Codified by Edwards & Magee in 1948 from 1930s–40s practice. Untested for half a century, then examined with pattern-recognition algorithms in two landmark studies.

What the research supports. Patterns are not pure noise: detected algorithmically (kernel regression) across thousands of US stocks, several classical patterns coincide with statistically distinct return distributions — they carry SOME information (Lo, Mamaysky & Wang 2000). Head-and-shoulders rules in dollar exchange rates were profitable for some currencies over 1973–1994 (Chang & Osler 1999).

What it does not support. Information is not profit: Lo et al. explicitly do not show pattern trading makes money. And the head-and-shoulders result comes with a sting — it was dominated by much simpler momentum rules; pattern traders would have earned less than trend followers taking a fraction of the effort (Chang & Osler 1999).

Sources: Lo, Mamaysky & Wang (2000) · Chang & Osler (1999)

also called: doji, engulfing, hammer, 'price action' candle signals

Where it comes from. Attributed to 18th-century Japanese rice trading and popularized in the West in the 1990s. The first robust academic test came only in 2006.

What the research supports. Nothing robust. This is the cleanest negative result in the indicator literature.

What it does not support. Tested across the full menu of bullish and bearish candlestick signals on DJIA stocks (1992–2002) with bootstrap methods, candlestick strategies created no value for investors — returns were statistically indistinguishable from chance (Marshall, Young & Rose 2006).

Sources: Marshall, Young & Rose (2006)

also called: volume precedes price, OBV-style logic

Where it comes from. An old floor-trading maxim that acquired a real theoretical footing: if traders learn from markets, the SEQUENCE of prices alone throws away information that volume preserves.

What the research supports. In a formal model, volume carries information about the quality of price signals that price alone cannot reveal — rational traders can genuinely learn from volume, which is the strongest theoretical case any 'technical' input has (Blume, Easley & O'Hara 1994).

What it does not support. A theoretical justification is not a validated trading rule. Specific volume indicators (OBV lines, divergence rituals) have no robust peer-reviewed profitability record.

Sources: Blume, Easley & O'Hara (1994)