Correlation Coefficient

get_correlation(quotes_a, quotes_b, lookback_periods)

Parameters

name type notes
quotes_a Iterable[Quote] Iterable of the Quote class or its sub-class.
See here for usage with pandas.DataFrame
quotes_b Iterable[Quote] Historical quotes (B) must have at least the same matching date elements of quotes_a.
lookback_periods int Number of periods (N) in the lookback period. Must be greater than 0 to calculate; however we suggest a larger period for statistically appropriate sample size.

Historical quotes requirements

You must have at least N periods for both versions of quotes to cover the warmup periods. Mismatch histories will produce a InvalidQuotesException. Historical price quotes should have a consistent frequency (day, hour, minute, etc).

quotes_a is an Iterable[Quote] collection of historical price quotes. It should have a consistent frequency (day, hour, minute, etc). See the Guide for more information.

Return

CorrelationResults[CorrelationResult]

CorrelationResult

name type notes
date datetime Date
variance_a float, Optional Variance of A based on N lookback periods
variance_b float, Optional Variance of B based on N lookback periods
covariance float, Optional Covariance of A+B based on N lookback periods
correlation float, Optional Correlation R based on N lookback periods
r_squared float, Optional R-Squared (R²), aka Coefficient of Determination. Simple linear regression models is used (square of Correlation).

Utilities

See Utilities and Helpers for more information.

Example

from stock_indicators import indicators

# This method is NOT a part of the library.
quotes_spx = get_history_from_feed("SPX")
quotes_tsla = get_history_from_feed("TSLA")

# Calculate 20-period Correlation
results = indicators.get_correlation(quotes_spx, quotes_tsla, 20)

About Correlation Coefficient

Correlation Coefficient between two quote histories, based on Close price. R-Squared (R²), Variance, and Covariance are also output. [Discuss] 💬

image

Sources