Projects | Carlos Mendez

Comparative Causal Metrics

Sun, 17 May 2026 00:00:00 +0000

Welcome to Comparative Causal Metrics! (Work in Progress)

An introduction to regional impact evaluation using modern causal-inference methods implemented in R and Quarto. The resource covers quasi-experimental techniques for evaluating policy effects and interventions on regional outcomes, with worked examples and publicly available data for full reproducibility.

This work in progress book features:

Quasi-experimental Methods — From interrupted time series to synthetic control and Bayesian structural time series, with a regional comparative focus.
R + Quarto Notebooks — Reproducible chapters with collapsible code, ready to render locally or extend with your own data.

Chapters

Introduction
Interrupted Time Series
Regression Discontinuity in Time
Basic Differences-in-Differences
Classical Synthetic Control
Structural Bayesian Time Series
References

Contribute and provide feedback at https://github.com/quarcs-lab/ccm.

Companion resource: Mastering Causal Metrics — an AI-powered Python study guide based on Angrist & Pischke’s Mastering ‘Metrics.

Mastering Causal Metrics

Wed, 22 Apr 2026 00:00:00 +0000

Welcome to Mastering Causal Metrics!

An AI-powered study guide to Mastering Causal Metrics. Learn the foundations of causal inference with interactive Python notebooks and AI tools, based on the foundational textbook Mastering ‘Metrics: The Path from Cause to Effect by Angrist & Pischke.

This platform features:

Foundational Methods – Based on Mastering ‘Metrics by Angrist & Pischke. Learn causal inference from randomized trials to differences-in-differences.
Python Notebooks – Zero-installation Google Colab notebooks. Real datasets, working code, and complete implementations of every method.
AI-Powered Learning – Multiple AI tutors with distinct pedagogical styles.

Interactive Google Colab Notebooks

Click any badge below to open and run immediately in your browser:

Part I: The Framework

Chapter	Title	Topics	Colab Notebook
1	Randomized Trials	Selection Bias, Potential Outcomes, RAND HIE

Part II: The Five Tools

Chapter	Title	Topics
2	Regression	OLS, Omitted Variable Bias, Bad Controls
3	Instrumental Variables	LATE, Compliers, Minneapolis DV Experiment
4	Regression Discontinuity	Sharp RD, Bandwidth, MLDA and Mortality
5	Differences-in-Differences	Parallel Trends, Two-Way FE, Great Depression Banking

Part III: Synthesis

Chapter	Title	Topics	Colab Notebook
6	The Wages of Schooling	Twins, Quarter of Birth, Sheepskin Effects

How to Use the Notebooks

Click any “Open in Colab” badge above
Sign in with your Google account (free)
Click “Run All” in the Runtime menu (or run cells individually)
Explore and modify – change parameters, try different models, experiment with the data
Save your work – File > Save a copy in Drive to keep your modifications

No installation, no downloads, no setup required!

Authors and Credits

Carlos Mendez – Python implementation and educational notebook development

Joshua D. Angrist & Jorn-Steffen Pischke – Original textbook, Mastering ‘Metrics

metricsAI

Wed, 21 Jan 2026 00:00:00 +0000

Welcome to metricsAI!

This data science platform offers a modern introduction to econometrics by combining cloud-based Python notebooks with AI learning tools from NotebookLM.

Designed as an interactive companion to Colin Cameron’s textbook, Analysis of Economics Data: An Introduction to Econometrics, metricsAI transforms static chapters into dynamic learning experiences. Students can access AI summaries, Python code, and practical examples directly in their browsers via Google Colab. There is zero setup or installation required, and the notebooks feature built-in AI tools for code generation, explanation, and transformation.

📓 Interactive Google Colab Notebooks

Click any badge below to open and run immediately in your browser:

Part I: Statistical Foundations

Chapter	Title	Colab Notebook
1	Analysis of Economics Data
2	Univariate Data Summary
3	The Sample Mean
4	Statistical Inference for the Mean

Part II: Bivariate Regression

Chapter	Title	Colab Notebook
5	Bivariate Data Summary
6	The Least Squares Estimator
7	Statistical Inference for Bivariate Regression
8	Case Studies for Bivariate Regression
9	Models with Natural Logarithms

Part III: Multiple Regression

Chapter	Title	Colab Notebook
10	Data Summary for Multiple Regression
11	Statistical Inference for Multiple Regression
12	Further Topics in Multiple Regression
13	Case Studies for Multiple Regression

Part IV: Advanced Topics

Chapter	Title	Colab Notebook
14	Regression with Indicator Variables
15	Regression with Transformed Variables
16	Checking the Model and Data
17	Panel Data, Time Series Data, Causation

How to Use the Notebooks

Click any “Open in Colab” badge above
Sign in with your Google account (free)
Click “Run All” in the Runtime menu (or run cells individually)
Explore and modify - change parameters, try different models, experiment with the data
Save your work - File → Save a copy in Drive to keep your modifications

No installation, no downloads, no setup required!

👥 Authors and Credits

Carlos Mendez - Python implementation and educational notebook development

A. Colin Cameron - Original textbook, data, Stata/R code, slides.

GeoDevelopment Dashboards

Sun, 18 Jan 2026 00:00:00 +0000

Mendez, C. (2026). Space-time dynamics of population, luminosity, land cover, and GDP in Cambodia (2013-2019). Google Earth Engine Application. Access App | Open in GEE

Kanyama, Y., & Mendez, C. (2026). Exploring regional disparities in Japan: Multi-scale comparison of GDP per capita (1990–2022). Google Earth Engine Application. Access App | Open in GEE

DS4Bolivia

Wed, 14 Jan 2026 00:00:00 +0000

DS4Bolivia: A Data Science Repository to Study GeoSpatial Development in Bolivia

Welcome to DS4Bolivia! This project aggregates spatial and socio-economic datasets, interactive dashboards, and computational workflows focused on 339 municipalities of Bolivia. It is designed to bridge the gap between spatial analysis and sustainable development goals (SDGs).

This repository is organized for researchers and data scientists interested in:

Spatial Econometrics: Understanding regional disparities, growth, and clustering.
Spatial Machine Learning: Utilizing satellite imagery (Earth Observation) for predictive modeling.
Sustainable Development: Tracking SDG indicators at a granular local level.

🖥️ Interactive Geospatial Dashboards

Explore the data without writing code. These applications visualize the space-time dynamics of key development indicators.

Space-time dynamics of population, luminosity, land cover and GDP (2013-2019): Visualize the evolution of population density, night-time lights, land cover changes, and GDP estimates across Bolivian municipalities in 2013 and 2019.

🐍 Cloud-based Computational Notebooks

Step-by-step tutorials to help you reproduce our analysis. These notebooks utilize Python libraries such as GeoPandas and PySAL.

Introduction to Exploratory Spatial Data Analysis (ESDA)
Focus: Learn how to detect spatial clusters and outliers using Global and Local Moran’s I.
Key Concepts: Spatial Autocorrelation, LISA Statistics, Choropleth Mapping.

💾 Spatially-Explicit Datasets

Curated datasets ready for analysis. These files are pre-processed to align with Bolivian municipal boundaries.

SDGs & Satellite Embeddings (2017)
Description: A merged dataset combining socio-economic indicators (SDGs) with high-dimensional feature vectors extracted from satellite imagery.
Use Case:　Training machine learning models to predict poverty or development indices based on visual patterns from space.

📜 Citation

If you use this repository in your research, please cite it using the following metadata.

APA Format

Mendez, C., Gonzales, E., Leoni, P., Andersen, L., Hendrix, P. (2024). DS4Bolivia: A Data Science Repository to Study GeoSpatial Development in Bolivia [Data set]. GitHub. https://github.com/quarcs-lab/ds4bolivia

BibTeX Format

@misc{ds4bolivia2026,
author = {Mendez, Carlos and Gonzales, Erick and Leoni, Pedro and Andersen, Lykke and Hendrix, Peralta},
title = {{DS4Bolivia}: A Data Science Repository to Study GeoSpatial Development in Bolivia},
year = {2026},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/quarcs-lab/ds4bolivia}}
}

🚀 Construct your own dataset

The datasets are organized into modules, all linked by a unique identifier (asdf_id).

Dataset Category	File Path	Description	Join Key
Region Names	`/regionNames/regionNames.csv`	Administrative metadata (Municipality names, Department names).	`asdf_id`
Socio-Economic	`/sdg/sdg.csv`	Sustainable Development Goal (SDG) indices and poverty metrics.	`asdf_id`
Satellite Features	`/satelliteEmbeddings/satelliteEmbeddings2017.csv`	Feature vectors (embeddings) extracted from daytime satellite imagery.	`asdf_id`
Spatial Vector	`/maps/bolivia339geoqueryOpt.geojson`	Geometric boundaries (Polygons) for all municipalities.	`asdf_id`

⚠️ Important Note on Identifiers: > The primary key for joining all datasets in this repository is asdf_id.
While mun_id (standard government code) is present in the administrative data, asdf_id ensures consistency across the satellite embeddings and optimized map files provided here. Always ensure this column is treated as an int or string consistently across both dataframes before merging.

You can run the examples below immediately in Google Colab.

Example 1: Integrating Attribute Data

This script demonstrates how to merge the administrative names, socio-economic indicators, and satellite machine learning features into a single analytical dataframe.

import pandas as pd
# -----------------------------------------------------------------------------
# 1. SETUP: Define Source URLs
# We use the raw GitHub URL to stream data directly into Colab/Pandas.
# -----------------------------------------------------------------------------
REPO_URL = "https://raw.githubusercontent.com/quarcs-lab/ds4bolivia/master"
url_names = f"{REPO_URL}/regionNames/regionNames.csv"
url_sdg = f"{REPO_URL}/sdg/sdg.csv"
url_emb = f"{REPO_URL}/satelliteEmbeddings/satelliteEmbeddings2017.csv"
# -----------------------------------------------------------------------------
# 2. LOAD: Read CSVs
# -----------------------------------------------------------------------------
print("Loading datasets...")
df_names = pd.read_csv(url_names)
df_sdg = pd.read_csv(url_sdg)
df_embeddings = pd.read_csv(url_emb)
# -----------------------------------------------------------------------------
# 3. MERGE: Combine Dataframes
# -----------------------------------------------------------------------------
# Step A: Attach SDG data to Names
df_merged_step1 = pd.merge(df_names, df_sdg, on='asdf_id', how='inner')
# Step B: Attach Satellite Embeddings to the result
df_final = pd.merge(df_merged_step1, df_embeddings, on='asdf_id', how='inner')
# -----------------------------------------------------------------------------
# 4. VERIFY
# -----------------------------------------------------------------------------
print(f"Merge Complete.")
print(f"Original Municipalities: {len(df_names)}")
print(f"Final Merged Rows: {len(df_final)}")
print(f"Total Columns: {len(df_final.columns)}")
# Display the first few rows (names + first few embedding columns)
display(df_final[['mun', 'dep', 'index_sdg1', 'A00', 'A01', 'A02']].head())

Example 2: Integrating Spatial and Attribute Data

This script takes the merged data from Example 1 and attaches it to the municipality geometries (GeoJSON) for spatial analysis and plotting.


import geopandas as gpd
import matplotlib.pyplot as plt
# -----------------------------------------------------------------------------
# 1. LOAD SPATIAL DATA
# We load the optimized GeoJSON file containing municipality boundaries.
# -----------------------------------------------------------------------------
geojson_url = f"{REPO_URL}/maps/bolivia339geoqueryOpt.geojson"
print("Loading GeoJSON map...")
gdf_boundaries = gpd.read_file(geojson_url)
# -----------------------------------------------------------------------------
# 2. SPATIAL DATA PREPARATION
# GeoJSON often loads IDs as objects/strings, while CSVs load as integers.
# -----------------------------------------------------------------------------
# Force 'asdf_id' to integer to match the pandas dataframe
gdf_boundaries['asdf_id'] = gdf_boundaries['asdf_id'].astype(int)
# -----------------------------------------------------------------------------
# 3. ATTRIBUTE JOIN
# Merge the spatial dataframe (gdf) with the attribute dataframe (df_final).
# This creates a 'GeoDataFrame' capable of spatial operations.
# -----------------------------------------------------------------------------
gdf_bolivia = gdf_boundaries.merge(df_final, on='asdf_id', how='inner')
# -----------------------------------------------------------------------------
# 4. VISUALIZATION (Choropleth Map)
# Plot the "No Poverty" SDG Index (SDG 1)
# -----------------------------------------------------------------------------
fig, ax = plt.subplots(1, 1, figsize=(12, 10))
gdf_bolivia.plot(
column='index_sdg1', # Variable to map
cmap='viridis', # Color palette (perceptually uniform)
linewidth=0.1, # Border width
edgecolor='white', # Border color
legend=True,
legend_kwds={'label': "SDG 1 Index (No Poverty)", 'orientation': "horizontal"},
ax=ax
)
ax.set_title("Bolivia: SDG 1 Index by Municipality", fontsize=15)
ax.set_axis_off() # Turn off lat/lon axis numbers for cleaner look
plt.show()

Data sources

SDG indicators are originally contructed by Andersen, L. E., Canelas, S., Gonzales, A., Peñaranda, L. (2020) Atlas municipal de los Objetivos de Desarrollo Sostenible en Bolivia 2020. La Paz: Universidad Privada Boliviana, SDSN Bolivia

🤝 Contributing

We welcome contributions! If you are fixing a Coordinate Reference System (CRS) issue, adding a new spatial model, or uploading fresh data, please submit a Pull Request.

GeoDevelopment Observatory of Cambodia

Mon, 15 Sep 2025 00:00:00 +0000

How to cite this project:

Mendez C., Khoun T., Poortinga A. (2025) GeoDevelopment Observatory of Cambodia.https://bit.ly/gdo-cambodia

The GeoDevelopment Observatory (GDO) of Cambodia provides a public access platform for the analysis, monitoring, and evaluation of sustainable regional development. The observatory integrates environmental, social, and economic indicators—designated as GeoDevelopment Indicators—collected from satellite imagery, ground-based surveys, and administrative records. These multi-dimensional datasets are analyzed using AI-enhanced computational notebooks and specialized web applications within the GeoDevelopment Tools framework. The technical analyses are then converted into GeoDevelopment Insights, which present the data in accessible formats for different user groups. Researchers utilize the platform for conducting empirical analyses, decision-makers access it for policy development and implementation, and citizens engage with it to understand development patterns in their regions. This systematic approach facilitates the transformation of complex sustainability data into usable information for monitoring progress, evaluating interventions, and informing sustainable regional development policies.

Slides by Carlos Mendez

Source: https://bit.ly/gdo-cambodia

Contribute and provide feedback at https://github.com/gdo-cambodia

Computational data science notebooks and apps for development studies

Tue, 08 Apr 2025 00:00:00 +0000

How to cite this project:

Mendez C. (2025) Computational Data Science Notebooks and Apps for Development Studies. Zenodo https://doi.org/10.5281/zenodo.15250204

Contribute and provide feedback at https://github.com/cmg777/ds4ds

Basic statistics and econometrics

Mendez C. (2024) Gapminder introduction to data science using Python
Mendez C. (2025) Introduction to statistical differences and relationships using Python
Mendez C. (2025) Statistics is about differences, relationships, and predictions
Mendez C. (2024) Descriptive statistics and multi-boundary mapping using Python
Mendez C. (2025) Use regressions to explore relationships using Python

Economic growth and development

Mendez C. (2025) Introduction to growth equations using Python
Mendez C. & Leiva F. (2023) The Solow growth model and its convergence prediction using Python
Mendez C. (2023) The Solow growth model and its convergence prediction using R
Mendez C. (2021) Convergence clubs in labor productivity and its proximate sources using R

Exploratory data analysis

Mendez C. (2024) Exploratory spatial data analysis of municipal development in Bolivia using Python

Causal inference

Mendez C. (2025) Introduction to directed acyclical graphs (DAGs) using R
Mendez C. (2024) Heterogeneous treatment effects via two-stage DID using R
Mendez C. (2025) Synthetic control explorer: Estimate counterfactuals with weighted combinations of control units

Machine learning

Mendez C. (2025) Introductory machine learning for econometrics: Exploring the Mincer equation in Python
Mendez C. (2025) An interactive app to learn SHAP plots with XGBoost predictions

Spatial econometrics

Bayesian econometrics

Feature engineering and geocomputation

Mendez C. (2025) Regional dynamics of luminosity-based GDP using Google Earth Engine
TBA

Projects | Carlos Mendez

Comparative Causal Metrics

Welcome to Comparative Causal Metrics! (Work in Progress)

Chapters

Related project

Mastering Causal Metrics

Welcome to Mastering Causal Metrics!

Interactive Google Colab Notebooks

Part I: The Framework

Part II: The Five Tools

Part III: Synthesis

How to Use the Notebooks

Authors and Credits

metricsAI

Welcome to metricsAI!

📓 Interactive Google Colab Notebooks

Part I: Statistical Foundations

Part II: Bivariate Regression

Part III: Multiple Regression

Part IV: Advanced Topics

How to Use the Notebooks

👥 Authors and Credits

GeoDevelopment Dashboards

DS4Bolivia

DS4Bolivia: A Data Science Repository to Study GeoSpatial Development in Bolivia

🖥️ Interactive Geospatial Dashboards

🐍 Cloud-based Computational Notebooks

💾 Spatially-Explicit Datasets

📜 Citation

APA Format

BibTeX Format

🚀 Construct your own dataset

Example 1: Integrating Attribute Data

Example 2: Integrating Spatial and Attribute Data

Data sources

🤝 Contributing

GeoDevelopment Observatory of Cambodia

Computational data science notebooks and apps for development studies

Basic statistics and econometrics

Economic growth and development

Exploratory data analysis

Causal inference

Machine learning

Spatial econometrics

Bayesian econometrics

Feature engineering and geocomputation