Pere A. Taberner

Understanding matching estimators in causal inference and policy evaluation

Sat, 08 Mar 2025 00:00:00 +0000

Drawing accurate causal inference estimates from observational data is a central challenge in impact evaluation studies of public policies and social programs. Matching estimators are one of the techniques which allow investigators to compare treated and untreated groups that are similar in all relevant characteristics except for the treatment itself. Their simplicity and relatively easy implementation make them especially popular in policy evaluation, where conducting randomized controlled trials is often impractical. This blog post explores the concept of matching estimators, discussing their key limitations, the critical steps before and after matching, and the most widely used algorithms, providing a comprehensive...

How to estimate and interpret marginal effects from the logit model with STATA?

Mon, 06 Dec 2021 00:00:00 +0000

Logistic regression, also known as logit regression, logit model, or just logit, is one of the most regression analyses taught at universities and used in data analysis. It is a non-linear model which predicts the outcome of a categorical dependent variable with respect to a vector of independent variables. When performing a logit regression with a statistical package, such as Stata, R or Python, the coefficients are usually provided by log-odds scale. In short, this means that point estimates are complicated to interpret, however the sign and the confidence interval of estimates can be interpreted. For that reason, it is...

First steps with pandas (Python): importing datasets and how they look

Sat, 06 Nov 2021 00:00:00 +0000

Recently I started to learn Python and, especially, how to manage datasets with it. pandas is one of the well-known libraries for data management in Python. So, I would like to share my notes and my first steps with pandas. 0) Importing pandas First, I import the library with the name pd: import pandas as pd One of the first things I learned in Python is that libraries can be labeled/named as one wants. This is useful to be more efficient when writng code. Since I have labeled pandas as pd, now it is enough to write pd to call...

Tips for managing large-scale datasets efficiently in Stata

Sun, 25 Jul 2021 00:00:00 +0000

Occasionally we manage enormous datasets with a lot of variables and observations. Depending on the power of our machine, computations in Stata might take more or less time. However, these computations usually take more time than we would like, which is frustrating and inefficient. For this reason, I would like to share some tips that I have learned over many hours in front of Stata. compress command. I would say that it is one of the most valuable commands in Stata. It reduces the size of your dataset by converting the storage type of your variables into the most efficient typology. For instance, we...

List of open source books about R

Mon, 01 Feb 2021 00:00:00 +0000

I would like to share this list of free/open source books about R. These books teach different topics: tha basics of R, how to do graphs, statistics, econometrics… Most of these books are web-based, but some books are in pdf format. Just as a note: I have not used or checked of all them. As a final comment: I will be updating this list. Start with R R for Beginners by Emmanuel Paradis R para principiantes (in Spanish) by Juan Bosco Mendoza Vega Hands-On Programming with R by Garrett Grolemund The Epidemiologist R Handbook by Applied Epi More advanced level:...

How to compute distances between geolocations with QGIS?

Sun, 17 Jan 2021 00:00:00 +0000

Managing geodata has become more common over last decades. QGIS is an open source Geographic Information System (GIS) application which allows to manage geospatial data and perform spatial analysis. It is a project of the Open Source Geospatial Foundation (OSGeo) and it is available for Unix, Linux, Windows, MacOS and Android. The two main features of QGIS are (i) free of charge and (ii) user-friendly. Precisely, in the present post I explain how to compute distances between given geolocations in few steps for these who have never used QGIS. Concretely, geolocations stored in two csv files. So, let’s start! 1....

Merging and appending datasets with dplyr (R)

Sun, 10 Jan 2021 00:00:00 +0000

Introduction This brief post aims at explaining how to merge and append datasets with R, concretely with the package dplyr. First of all, it is important to have installed and loaded the library, i.e. install.packages("dplyr") and library(dplyr). library(dplyr) Before starting, the following illustration visually describes the definition of merge and append in the present post: Merge functions In this post I explain six useful functions in dplyr to merge datasets and one useful function to append datasets. First, I describe briefly the six merging functions (each function joins two indicated datasets): inner_join(): the output dataset only contains matched observations from...

The influence of the Bilingual Program on school segregation by socioeconomic origin in Madrid

Tue, 06 Oct 2020 00:00:00 +0000

Published in REICE – Revista Iberoamericana sobre Calidad, Eficacia y Cambio en Educación On September 21, 2020, our paper titled “The Influence of the Bilingual Program on the School Segregation by Socioeconomic Origin in the Autonomous Community of Madrid: Evidence from PISA” was published in the Spanish educational journal REICE. Co-authored with Lucas Gortazar, the paper examines how the bilingual program introduced in Madrid may have contributed to increasing school segregation by socioeconomic background. Since the paper was written in Spanish, I’m summarizing the key points here for a broader audience. Background and Motivation According to the PISA 2018 microdata...

Why students perform worse when stakes are high?

Fri, 11 Sep 2020 00:00:00 +0000

We all have been students some time ago. We remember the stress we used to feel some minutes before starting an exam and the increasing pressure when the examinations were important for our final grade or to achieve a specific goal such as university entrance exams or finish some educational stage. Then, after the exam or the grade publication, the most listened sentence among classmates were: “I don’t understand why I’ve made those mistakes; I had solved those exercises at home successfully!”. Does it sound familiar to you? So, psychologists called that choke under pressure (Baumeister, 1984; Beilock, 2004). Choke...

New KSNET Working Paper: Experimental evidence on the impact of cultural activities on health and well-being among the elderly

Thu, 01 Jan 1970 00:33:46 +0000

New KSNET Working Paper: Experimental evidence on the impact of cultural activities on health and well-being among the elderly

Award for the best communication on the Sustainability of Public Policies axis at the 4th Congress of Economy and Business of Catalonia