Linear regression · TradersWeek

Skip to main content

Output: Conditional forecast or research filter
Input: Ordered price, volume or breadth observations
Horizon: A defined sampling interval and lookback
Best use: Compare an explicit quantitative baseline with an out-of-sample result.

Input: Ordered price, volume or breadth observations.
Output: forecast.
Use boundary: Compare an explicit quantitative baseline with an out-of-sample result.

The graph8

How the method is built, and where it has been read

Depends on

Often reviewed together

Alpha coefficient4 readings

Often reviewed together

Moving-average crossover5 readings

Often reviewed together

Trendline6 readings

Often reviewed together

Exponential smoothing7 readings

Often reviewed together

Price channel7 readings

Often reviewed together

Bollinger Bands7 readings

Often reviewed together

Correlation analysis8 readings

Often reviewed together

Walk-forward analysis9 readings

Read in the archive24 of 135 readings

1985Beta and alpha as chosen regression parametersPortfolio construction 1986Constructing a commodity channel index and a regression price channelTrend and channels 1988Serial correlation is not an independence testStatistical tests 1988Constructing breadth and average trend statesMarket breadth 1988Least-squares construction of channel trendlinesTrend and channels 1988Treat a suspected bend as a construction testTrend and channels 1989A precious-metal price as a changing intermarket equationIntermarket and spreads 1989Evaluating technical-fund open interest and daily volatilityIntermarket and spreads 1990Constructing dollar baselines from rates, inflation, and residualsIntermarket and spreads 1990Two clocks for copper: a factor regime, a regression baseline, and leftover moving-average timingTime series and forecasting 1990Constructing a nominal index price from earnings and a fitted yieldTime series and forecasting 1990Constructing a nominal index value from forward earnings and fitted yieldTime series and forecasting 1990Buying-share scale with on-balance volumeIndicators and filters 1990Endpoint-pinned price paths are not forecastsIndicators and filters 1990Constant-dollar regimes, the value line, and nested cyclesSeasonality and regimes 1990Earnings yield, rate correlation and regression for equity valueTime series and forecasting 1990Constructing least-squares polynomial smoothersIndicators and filters 1991Out-of-sample checks for linear growth fitsTime series and forecasting 1991Endpoint growth rates versus linear-regression consistencyStatistical tests 1991Trend as persistence, not a straight lineTrend and channels 1991Name the window, then combine leadersTime series and forecasting 1991Time-origin offset and residual-price divergence on a quadratic least-squares fitIndicators and filters 1991Quadratic trend, residual oscillator, and a secondary cycle calendarTime series and forecasting 1991Earnings-price reliability as a first gate for growth-sleeve constructionPortfolio construction

This registry entry describes a research method. It is not investment advice and does not make a performance claim.