<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>EconStor Collection:</title>
    <link>https://hdl.handle.net/10419/220089</link>
    <description />
    <pubDate>Tue, 28 Apr 2026 11:39:24 GMT</pubDate>
    <dc:date>2026-04-28T11:39:24Z</dc:date>
    <item>
      <title>Machine learning simulates agent-based model towards optimal policy: A surrogate model for public policy assessment</title>
      <link>https://hdl.handle.net/10419/298106</link>
      <description>Title: Machine learning simulates agent-based model towards optimal policy: A surrogate model for public policy assessment
Authors: Furtado, Bernardo Alves; Andreão, Gustavo Onofore
Abstract: Public policies are not intrinsically positive or negative. Rather, policies provide varying levels of effects across different recipients. Methodologically, computational modeling enables the application of a combination of multiple influences on empirical data, thus allowing for heterogeneous response to policies. We use a random forest machine learning algorithm to emulate an agentbased model (ABM) and evaluate competing policies across 46 Metropolitan Regions (MRs) in Brazil. In doing so, we use input parameters and output indicators of 11,076 actual simulation runs and one million emulated runs. As a result, we obtain the optimal (and non-optimal) performance of each region over the policies. Optimum is defined as a combination of production and inequality indicators for the full ensemble of MRs. Results suggest that MRs already have embedded structures that favor optimal or non-optimal results, but they also illustrate which policy is more beneficial to each place. In addition to providing MR-specific policies' results, the use of machine learning to simulate an ABM reduces the computational burden, whereas allowing for a much larger variation among model parameters. The coherence of results within the context of larger uncertainty - vis-à-vis those of the original ABM - suggests an additional test of robustness of the model. At the same time the exercise indicates which parameters should policymakers intervene, in order to work towards precise policy optimal instruments.</description>
      <pubDate>Sun, 01 Jan 2023 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://hdl.handle.net/10419/298106</guid>
      <dc:date>2023-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Features and determinants of the firm size distribution: An enpirical analysis with Brazilian data</title>
      <link>https://hdl.handle.net/10419/298110</link>
      <description>Title: Features and determinants of the firm size distribution: An enpirical analysis with Brazilian data
Authors: Foguel, Miguel Nathan; Ribeiro, Eduardo Pontual
Abstract: The Pareto distribution has been used to describe firm sizes in many theoretical models for its convenience and empirical validity. We provide estimates of the Pareto parameters across industries and investigate the determinants of the shape of the firm size distribution in Brazil. The Pareto tail distribution is not rejected for about 70% of the industries, with the Zipf tail distribution (scale coefficient equal to 1) accepted for about 50% of the industries. The size distributions in manufacturing and all industries are affected by the human capital intensity and may be affected by industry uncertainty and instability, in line with the literature.</description>
      <pubDate>Sun, 01 Jan 2023 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://hdl.handle.net/10419/298110</guid>
      <dc:date>2023-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Optimal policy: Which, where, and why</title>
      <link>https://hdl.handle.net/10419/298109</link>
      <description>Title: Optimal policy: Which, where, and why
Authors: Furtado, Bernardo Alves; Andreão, Gustav Onofre
Abstract: The paper exploits a simulation environment and its output indicators to compare the performance of "ex-ante" policy instruments across housing and social welfare domains. We create a progressive score to contrast six single and mixed policy instruments against a no-policy baseline. The multiple simulation results include indicators for distinct instruments, cities, and policy goals. The exercise provides a counterfactual arena where we explore public investment trade-offs quantitatively and empirically - which constitutes a rare (usually impossible) policy practice. We demonstrate with data that policymakers may avoid incongruities by defining: i) which policy instrument; ii) to apply where; and iii) towards which goal (why). Results suggest that a mixed policy instrument evaluated by a comprehensive indicator performs better overall. However, optimal policy classification changes when considering different places or goals.</description>
      <pubDate>Sun, 01 Jan 2023 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://hdl.handle.net/10419/298109</guid>
      <dc:date>2023-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Measuring the natural rate of interest in Brazil</title>
      <link>https://hdl.handle.net/10419/298107</link>
      <description>Title: Measuring the natural rate of interest in Brazil
Authors: Maka, Alexis
Abstract: This paper applies the Holston-Laubach-Williams methodology to estimate the natural rate of interest for Brazil.</description>
      <pubDate>Sun, 01 Jan 2023 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://hdl.handle.net/10419/298107</guid>
      <dc:date>2023-01-01T00:00:00Z</dc:date>
    </item>
  </channel>
</rss>

