Random Effects

Fit a Random Effects estimator explaining a panel of dependent_tickers (the entities) by a regressor x, via Swamy-Arora feasible Generalized Least Squares.

Also known as: RE, GLS panel estimator, Swamy-Arora estimator.

See get_fixed_effects for how dependent_tickers/independent_tickers/ independent_column are shaped into a panel, and panel_data_model.get_random_effects for the full estimator formula, references, and how it compares to Fixed Effects. Unlike Fixed Effects, Random Effects retains and estimates a single, population-average intercept rather than one intercept per entity – more efficient than Fixed Effects if entity effects are indeed uncorrelated with the regressor(s) (see get_hausman_test to check that assumption).

Random Effects in Python

get_random_effects is part of the Econometrics module of the open-source Finance Toolkit. Install it with:

pip install financetoolkit -U

Then call get_random_effects as shown below.

from financetoolkit import Toolkit

toolkit = Toolkit(
    ["AAPL", "MSFT", "AMZN"], api_key="FINANCIAL_MODELING_PREP_KEY"
)

toolkit.econometrics.get_random_effects(
    independent_column="Volume", period="weekly"
)

Which returns:

Parameters

get_random_effects accepts the following parameters:

• independent_tickers (str | list[str] | None, optional): The factor ticker(s), whose column values are broadcast identically to every entity at each date. Mutually exclusive with independent_column. Note: since this Toolkit instance’s historical data is aligned onto a common calendar across tickers, a broadcast factor’s entity mean is identical for every entity, leaving no between-entity variation to identify Random Effects’ between-regression step – prefer independent_column here unless dependent_tickers genuinely differ in their date coverage (e.g. different listing histories).
• independent_column (str | None, optional): A different historical data column, taken per-entity from each of dependent_tickers’ own data, to use as the regressor. Mutually exclusive with independent_tickers.
• dependent_tickers (str | list[str] | None, optional): The panel of entity tickers to explain. Defaults to None, meaning every ticker in the Toolkit instance (other than independent_tickers, if given).
• period (str, optional): The data frequency (daily, weekly, monthly, quarterly, or yearly). Defaults to “daily”.
• column (str, optional): The dependent variable’s historical data column. Defaults to “Return”.
• rounding (int | None, optional): The number of decimals to round the results to. Defaults to None.

Related Panel Data