learn_pooled_vs_fixed_effects

source

learn_pooled_vs_fixed_effects(
    n_units=50,
    n_periods=10,
    beta=1.0,
    unit_effect_corr=0.8,
    seed=0,
)

Show how pooled OLS is biased by unit effects, and fixed effects fix it.

Simulates a panel where the regressor x is correlated with each unit’s fixed effect. Pooled OLS confounds within- and between-unit variation (biased); the within (fixed- effects) estimator recovers the true slope.

Parameters

Name	Type	Description	Default
n_units	int	Panel dimensions.	`50`
n_periods	int	Panel dimensions.	`50`
beta	float	True within-unit slope.	`1.0`
unit_effect_corr	float	Correlation between `x` and the unit effect (drives the pooled bias).	`0.8`
seed	int	Random seed.	`0`

Returns

Name	Type	Description
	SandboxResult	`df` (pooled vs FE vs true slope), `fig`, `summary` and `topic`.

Examples

This sandbox simulates its own panel, so the call needs no DataFrame:

import expdpy as ex

res = ex.learn_pooled_vs_fixed_effects()
res.fig