This presentation introduces a Stata command that implements an efficient variant of the peer-effects regression model of Arcidiacono (2012). The command augments linear regressions with peer effects defined as the average of individual fixed effects within peer groups and allows for flexible specifications, including heterogeneous peer effects by individual type, subgroup-specific peer effects, and weighted peer contributions. Additional fixed effects can be absorbed directly in the regression. Compared with existing implementations, the proposed algorithm is computationally more efficient and delivers correct estimation of clustered standard errors. The command is designed for scalable and flexible empirical analysis of peer effects in large datasets.

The use of the Bayesian approach for regression analysis is spreading more across different disciplines. The possibility to incorporate a priori information in the form of probability distributions for the parameters of the model makes this approach highly appealing when the researcher has that knowledge. Bayesian vector autoregressive models (BVAR) are particularly attractive because the overparameterization present in many VAR models can be handled by using prior probability distributions that allow shrinking the parameter space. In this presentation, I will briefly highlight the general elements associated with Bayesian VAR models, and I will use a couple of examples to illustrate the way Stata implements the estimation for the parameters of a VAR model using the Bayesian approach and how we can get probabilities for events that combine levels for the different endogenous variables of the model.

As economies pursue environmental transitions, the labor market effects of green jobs are of growing interest to both researchers and policymakers. This presentation investigates the green wage premium in Portugal using detailed longitudinal-linked employer-employee data from 2010 to 2019. We quantify the wage differentials between green and nongreen jobs and disentangle the roles of both observable characteristics (for example, education, tenure, firm size) and unobservable factors (for example, individual abilities, firm-specific effects). Our results show that workers in green jobs earn, on average, between 20% and 50% more than those in nongreen jobs; however, this gap narrows to 3%–7% when controlling for covariates. Using fixed effects and structural wage decompositions, we find that green jobs offer lower returns to unobservable abilities, suggesting that they rely more on formal qualifications and structured task content. These patterns persist in a robustness check using a sample of displaced workers, mitigating concerns about endogenous matching. Our findings underscore the importance of skill-based wage structures in green labor markets and provide policy-relevant insights for managing the reallocation of labor during environmental transitions.

Using firm-level data for Portugal, 2006–2021, we investigate linkages between private financing—private equity (including venture capital) and private debt—and firms' exporting and innovation. Combining matching and regression procedures, we find that private financing is associated with exporting and R&D activity. Firms financed by private equity are more likely to export and to export a larger share of their sales. They also exhibit higher propensity to allocate employees and funds to R&D and to channel a larger share of investment into it. Private debt is likewise positively related to innovation inputs and exports, but both effects are limited to the extensive margin.

metaxl is a Stata package developed by BPLIM for managing dataset metadata. The package enables users to extract metadata from Stata datasets and store them in structured Excel files. metaxl can also read metadata from these spreadsheets and apply them to datasets, thereby promoting consistency and standardization across multiple data extractions. In addition, metaxl provides tools for checking, comparing, and harmonizing metadata files, which are particularly useful for managing large and complex datasets. By decoupling metadata from the data themselves metaxl enhances overall data management practices and is especially suited to working with confidential data. This presentation will highlight the package’s key features, common uses, and practical considerations for integrating metaxl into existing data-handling pipelines.

bpstat is a Stata package provided by BPLIM that enables users to import thousands (over 70,000) of statistical series from the Banco de Portugal BPstat database directly into Stata. It supports both a command-line interface and a dialog-driven mode, streamlining the retrieval of time-series data and associated metadata. The package leverages embedded Python code (available since Stata 16), facilitating access to the BPstat API—the open data API provided by Banco de Portugal. Thanks to bpstat, researchers can efficiently access a wide array of Portuguese and Euro-area economic and financial statistics published by Banco de Portugal, facilitating empirical analysis and economic research.

As datasets continue to grow and “big data” become a practical reality, Stata users increasingly face challenges related to storage and performance. A modern solution to these issues is Parquet—an open-source, columnar file format designed for efficient storage and capable of improving performance when used correctly. Some tools for handling Parquet files in Stata have emerged, but this presentation will focus on the community-contributed stata_parquet_io package by Jon Rothbaum. I will discuss the advantages of Parquet and demonstrate how to read, write, merge, and append Parquet files in Stata, drawing on practical experience to highlight efficient workflows and common pitfalls. The goal is to show how Parquet can offer substantial benefits over native Stata files when working with large datasets—and how to use it effectively.

We find that labor market concentration can be an important driver of employee childbearing. First, we present two parsimonious models to illustrate how childbearing decisions are related to employer concentration, highlighting job security and wages as relevant channels of labor market power. We then conduct empirical analyses based on comprehensive matched employer-employee panel data from Portugal from 2010 to 2023, including a novel variable on worker absences for childbearing reasons and an instrumental-variables approach. At both the extensive and intensive margins of childbearing, leave of absence is negatively impacted by concentration levels. For instance, an increase in labor concentration from the 25th to the 75th percentile can reduce childbearing by up to 94% for women up to 40 years of age. By extending the canonical child penalty model to consider labor market concentration, we also find that employees in more concentrated markets in their childbirth year are more penalized in terms of subsequent wages. Our results indicate that reducing employer concentration can increase fertility rates.

Touristification has emerged as a transformative yet contentious force in urban economies, creating both economic opportunities and displacement pressures. We estimate the impact of a rapid touristification boom on residential mobility and income trajectories of incumbent households in two of Europe’s most affected cities. Using administrative tax records from 2016–2019 and an instrumental-variables strategy based on proximity to tourist amenities, we show that short-term rental expansion significantly increased outmigration rates. We further document heterogeneous income effects across sources and demographic groups, identifying the populations most vulnerable to tourism-driven housing market shocks.

We exploit the assignment mechanism of the APOIAR program, a targeted initiative aimed at supporting the firms most affected during the COVID-19 pandemic, to provide causal evidence on the impact of grants on firm survival and performance in times of crisis. Using sharp and fuzzy regression discontinuity designs and drawing on a combination of administrative datasets, we find that eligible firms experienced a short-term increase in profitability in 2021, with €1 of support increasing net income by €0.658. However, these effects did not persist into 2022, and we found no significant changes in turnover or cost reduction, indicating that the increase in profitability was mechanically due to the subsidy. Firms allocated part of the grant to rental payments and purchases of office supplies, including modest investments in digitalization. Our findings suggest that these funds were particularly important for exante less productive, with less cash on hand, and more indebted firms.