or run

npx @tessl/cli init

Version

Tile

Overview

Evals

Files

docs

diagnostics.md index.md ml-models.md ols-models.md panel-models.md probit-models.md regime-models.md spatial-error-models.md sur-models.md tsls-models.md utilities.md

tile.json

tessl/pypi-spreg

Spatial econometric regression models for analyzing geographically-related data interactions.

Workspace: tessl
Visibility: Public
Created: 3 months ago
Last updated: 3 months ago
Describes: pkg:pypi/spreg@1.8.x

To install, run

npx @tessl/cli install tessl/pypi-spreg@1.8.0

spreg

A comprehensive Python library for spatial econometric regression analysis. spreg provides methods for analyzing processes where observations interact with one another across geographic space, offering simultaneous autoregressive spatial regression models, diagnostic tools, and regime-based analysis capabilities.

Package Information

Package Name: spreg
Language: Python
Installation: pip install spreg

Core Imports

import spreg

Common specific imports:

from spreg import OLS, TSLS, GM_Error_Het, GM_Error_Hom
from spreg import GM_Combo_Het, GM_Combo_Hom
from spreg import ML_Error, ML_Lag

Basic Usage

import numpy as np
import spreg
from libpysal import weights

# Prepare data
n = 100
y = np.random.randn(n, 1)
x = np.random.randn(n, 2)
w = weights.lat2W(10, 10)  # 10x10 spatial weights

# Basic OLS with spatial diagnostics
ols_model = spreg.OLS(y, x, w=w, spat_diag=True, name_y='y', name_x=['x1', 'x2'])
print(ols_model.summary)

# Spatial error model with heteroskedasticity
spatial_model = spreg.GM_Error_Het(y, x, w=w.sparse, name_y='y', name_x=['x1', 'x2'])  
print(spatial_model.summary)

# Two-stage least squares for endogenous variables
yend = np.random.randn(n, 1)  # endogenous variable
q = np.random.randn(n, 1)     # instrument
tsls_model = spreg.TSLS(y, x, yend, q, name_y='y', name_x=['x1', 'x2'], 
                        name_yend=['yend'], name_q=['instrument'])
print(tsls_model.summary)

Architecture

spreg follows a consistent class-based architecture for regression models:

Base Classes: Provide core estimation without diagnostics (e.g., BaseOLS, BaseTSLS)
Full Classes: Extend base classes with comprehensive diagnostics and output formatting
Spatial Models: Handle spatial dependence through error correlation (*_Error) or lag structures (*_Lag)
Regime Models: Allow parameters to vary across spatial or categorical regimes
Diagnostic Functions: Standalone functions for testing spatial autocorrelation, heteroskedasticity, and model specification

The library integrates seamlessly with the PySAL ecosystem, using libpysal.weights objects for spatial relationships and supporting common NumPy/SciPy data structures.

Capabilities

OLS Regression Models

Ordinary least squares with extensive spatial and non-spatial diagnostic capabilities, supporting robust standard errors and spatial lag of X (SLX) specifications.

class OLS:
    def __init__(self, y, x, w=None, robust=None, gwk=None, sig2n_k=False,
                 nonspat_diag=True, spat_diag=False, moran=False, 
                 white_test=False, vif=False, slx_lags=0, slx_vars='All',
                 regimes=None, vm=False, constant_regi='one', cols2regi='all',
                 regime_err_sep=False, cores=False, name_y=None, name_x=None,
                 name_w=None, name_ds=None, latex=False): ...

OLS Models

Two-Stage Least Squares

Two-stage least squares estimation for handling endogenous variables, with spatial diagnostic capabilities and regime-based analysis.

class TSLS:
    def __init__(self, y, x, yend, q, h=None, robust=None, gwk=None, sig2n_k=False,
                 nonspat_diag=True, spat_diag=False, slx_lags=0, slx_vars='All',
                 regimes=None, vm=False, name_y=None, name_x=None, name_yend=None,
                 name_q=None, name_h=None, name_w=None, name_ds=None, latex=False): ...

Two-Stage Least Squares

Spatial Error Models

GMM estimation of spatial error models with options for heteroskedasticity, homoskedasticity, and combined spatial lag-error specifications (SARAR models).

class GM_Error_Het:
    def __init__(self, y, x, w, max_iter=1, epsilon=0.0000001, step1c=False, 
                 inv_method='power_exp', hard_bound=False, vm=False, name_y=None,
                 name_x=None, name_w=None, name_ds=None, latex=False): ...

class GM_Error_Hom:
    def __init__(self, y, x, w, hard_bound=False, vm=False, name_y=None,
                 name_x=None, name_w=None, name_ds=None, latex=False): ...

class GM_Combo_Het:
    def __init__(self, y, x, yend, q, w, w_lags=1, lag_q=True, max_iter=1,
                 epsilon=0.0000001, step1c=False, inv_method='power_exp',
                 hard_bound=False, vm=False, name_y=None, name_x=None, 
                 name_yend=None, name_q=None, name_w=None, name_ds=None, 
                 latex=False): ...

Spatial Error Models

Maximum Likelihood Models

Full information maximum likelihood estimation for spatial lag and error models with analytical derivatives and concentrated log-likelihood functions.

class ML_Error:
    def __init__(self, y, x, w, epsilon=0.0000001, hard_bound=False, vm=False,
                 name_y=None, name_x=None, name_w=None, name_ds=None, latex=False): ...

class ML_Lag:
    def __init__(self, y, x, w, epsilon=0.0000001, hard_bound=False, vm=False,
                 name_y=None, name_x=None, name_w=None, name_ds=None, latex=False): ...

Maximum Likelihood Models

Regime-Based Models

Spatial regression models allowing parameters to vary across regimes, with options for separate or joint estimation and extensive regime-specific diagnostics.

class GM_Error_Het_Regimes:
    def __init__(self, y, x, regimes, w, constant_regi='many', cols2regi='all',
                 regime_err_sep=False, regime_lag_sep=False, cores=False,
                 max_iter=1, epsilon=0.0000001, step1c=False, 
                 inv_method='power_exp', hard_bound=False, vm=False, 
                 name_y=None, name_x=None, name_regimes=None, name_w=None,
                 name_ds=None, latex=False): ...

Regime Models

Panel Data Models

Fixed effects and random effects panel data models with spatial error and lag specifications for analyzing spatially-correlated panel datasets.

class Panel_FE_Error:
    def __init__(self, y, x, w, epsilon=0.0000001, hard_bound=False, vm=False,
                 name_y=None, name_x=None, name_w=None, name_ds=None, 
                 latex=False): ...

class Panel_RE_Error:
    def __init__(self, y, x, w, epsilon=0.0000001, hard_bound=False, vm=False,
                 name_y=None, name_x=None, name_w=None, name_ds=None,
                 latex=False): ...

Panel Models

SUR Models

Seemingly unrelated regressions with spatial error and lag structures for simultaneous equation systems with cross-equation correlation.

class SUR:
    def __init__(self, bigy, bigX, df_name=None, sur_constant=True, name_bigy=None, 
                 name_bigX=None, name_ds=None, vm=False, latex=False): ...

SUR Models

Probit Models

Spatial probit regression for binary choice models with spatial dependence, supporting various spatial structures and diagnostic tests.

class Probit:
    def __init__(self, y, x, w=None, optim='newton', scalem='phimean', maxiter=100,
                 vm=False, name_y=None, name_x=None, name_w=None, name_ds=None,
                 latex=False, hard_bound=False): ...

Probit Models

Diagnostic Functions

Comprehensive diagnostic testing for spatial autocorrelation, heteroskedasticity, normality, multicollinearity, and model specification in spatial regression contexts.

class LMtests:
    def __init__(self, ols, w, tests=["all"]): ...

class MoranRes:
    def __init__(self, ols, w, z=False): ...

class AKtest:
    def __init__(self, iv, w, case='nosp'): ...

def jarque_bera(reg): ...
def breusch_pagan(reg): ...
def white(reg): ...

Diagnostic Functions

Utility Functions

Core utilities for spatial operations, matrix computations, GMM optimization, and data generation for simulation studies.

def get_lags(w, x, w_lags): ...
def get_spFilter(w, lamb, sf): ...
def optim_moments(moments_in, vcX, all_par, start, hard_bound): ...
def set_endog(y, x, w, yend, q, w_lags, lag_q, slx_lags, slx_vars): ...

class RegressionPropsY: ...
class RegressionPropsVM: ...

Utilities

Common Parameters

Most spreg models share these common parameters:

y (array): nx1 dependent variable
x (array): nxk independent variables (constant added automatically unless suppressed)
w (pysal W object or sparse matrix): Spatial weights matrix
regimes (list/Series): Regime identifier for observations
vm (boolean): Include variance-covariance matrix in output
name_y, name_x, name_w, name_ds (strings): Variable and dataset names for output
latex (boolean): Format output for LaTeX
hard_bound (boolean): Raise exception if spatial parameters outside [-1,1]

Common Attributes

All spreg regression models provide these standard attributes:

betas (array): Estimated coefficients
u (array): Residuals
predy (array): Predicted values
vm (array): Variance-covariance matrix (if requested)
n (int): Number of observations
k (int): Number of parameters
output (DataFrame): Formatted results table
summary (string): Comprehensive summary with diagnostics

Spatial models additionally provide:

e_filtered (array): Spatially filtered residuals
pr2 (float): Pseudo R-squared
Spatial parameters (rho for lag, lambda for error)

Version

Tile

Files

tessl/pypi-spreg

To install, run

index.md.css-3qkkll{font-size:var(--chakra-font-sizes-sm);font-weight:var(--chakra-font-weights-normal);color:var(--chakra-colors-gray-300);}docs/

spreg

Package Information

Core Imports

Basic Usage

Architecture

Capabilities

OLS Regression Models

Two-Stage Least Squares

Spatial Error Models

Maximum Likelihood Models

Regime-Based Models

Panel Data Models

SUR Models

Probit Models

Diagnostic Functions

Utility Functions

Common Parameters

Common Attributes

index.mddocs/