beta

beta(Y, X, [intercept=true])

Return the coefficient estimate of an ordinary-least-squares regression of Y on X (with intercept).

Difference from Python’s scipy.stats.beta: scipy.stats.beta is a beta continuous random variable object for calculating probability density, distribution functions, random variates, and related statistics. DolphinDB’s beta is a statistical regression function that returns the OLS regression coefficient of Y on X.

Difference from Python TA-Lib’s BETA: TA-Lib’s BETA(high, low, timeperiod=5) is a rolling technical-analysis statistic. It calculates beta on the rate-of-change series of high and low over each window and does not support specifying whether to include an intercept term. DolphinDB’s beta(Y, X) calculates one OLS regression coefficient over the full input when vectors are specified and supports specifying whether to include an intercept term via the intercept parameter. To reproduce TA-Lib’s indicator behavior, use DolphinDB’s TA module ta::beta.

Y and X are numeric vectors of the same length, matrices of the same dimensions, or tables. If X is a table, only its numeric and Boolean columns are used in the calculation.

intercept (optional) is a BOOL scalar, default true. It specifies whether the linear regression includes an intercept term. If set to false, the intercept is fixed at 0, resulting in a regression through the origin.

A DOUBLE scalar/vector/table.

x=1 3 5 7 11 16 23
y=0.1 4.2 5.6 8.8 22.1 35.6 77.2;

beta(y,x);
// output: 3.378632

x=1 3 5 7 11 16 23
y=0.1 4.2 5.6 8.8 22.1 35.6 77.2;

beta(y,x);
// output: 3.378632

// By default, intercept=true, which includes an intercept term.
beta(y, x, true)
// output: 3.378632

// intercept=false excludes the intercept term (regression through the origin).
beta(y, x, false)
// output: 2.717778