<div dir="ltr">
<div><span style="color:rgb(0,0,0);word-spacing:1px"><font face="arial, sans-serif">Prezados,</font></span></div><div><font face="arial, sans-serif"><br></font><div><div><font face="arial, sans-serif"><span style="word-spacing:1px;color:rgb(0,0,0)">A Comissão do Programa de Pós-Graduação em Estatística do IMECC-UNICAMP gostaria de convidá-los para assistir a</span><span style="word-spacing:1px;color:rgb(0,0,0)"> palestra</span> do Professor <span style="color:rgb(0,0,0);background-color:transparent"><b>Hedibert Lopes</b></span> nesta<b style="word-spacing:1px;color:rgb(0,0,0)"> sexta-feira,</b> dia <b>27/10/2023, </b><b style="word-spacing:1px;color:rgb(0,0,0)">às 11:00, sala 221 do IMECC</b>. Segue as informações da palestra e uma short Bio logo abaixo.</font></div></div></div><div><font face="arial, sans-serif"><br></font></div><font face="arial, sans-serif"><b>Palestrante:</b> Hedibert Lopes, Insper</font><div><font face="arial, sans-serif"><br></font></div><div><font face="arial, sans-serif"><b>Título:</b>
<span style="text-align:-webkit-center">Cutoff-aware BART for Estimating Heterogeneous Treatment Effects in Regression Discontinuity Designs</span></font></div><div><span style="background-color:transparent;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal"><font color="#222222"><font style="" face="arial, sans-serif"><span lang="en-US"><b><br></b></span></font></font></span></div><div><font face="arial, sans-serif"><span style="background-color:transparent;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal"><font color="#222222"><font style=""><span lang="en-US"><b>Autores:</b></span></font></font></span><span style="background-color:transparent;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal"><font color="#222222"><font style=""><span lang="en-US">
Rafael Alcantara, MeijiaWang, P. Richard Hahn and Hedibert Lopes</span></font></font></span></font></div><div><table width="851" cellpadding="0" cellspacing="0">
<colgroup><col width="851">
</colgroup><tbody><tr>
<td width="851" style="border:none;padding:0cm"><p class="gmail-western" align="center" style="font-family:"Liberation Serif","Times New Roman",serif;font-size:12pt;color:rgb(0,0,0);direction:ltr;background:transparent;line-height:115%;margin-bottom:0.25cm"></p></td></tr><tr><td width="851" style="border:none;padding:0cm"><p class="gmail-western" align="justify" style="font-family:"Liberation Serif","Times New Roman",serif;font-size:12pt;color:rgb(0,0,0);direction:ltr;background:transparent;line-height:115%;margin-bottom:0.25cm"><font size="2" face="arial, sans-serif"><span lang="en-US"><b>Resumo:
</b></span><span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal"><font color="#222222"><font style=""><span lang="en-US">This
paper proposes a modification of the Bayesian Causal Forest
algorithm (Hahn et al., 2020) - itself an extension of the BART
algorithm (Chipman et al., 2010) — which uses a novel regression
tree prior that incorporates the unique structure of regression
discontinuity designs. Specifically, we add constraints to the
tree splitting process that assure overlap within a narrow band
surrounding the running variable cutoff value (where the treatment
effect is identified). We show that unmodified BART and BCF models
estimate RDD treatment effects poorly, while our modified model
accurately recovers treatment effects at the cutoff. At the same
time, our modified model retains the inherent flexibility of all
BART-based models, allowing it to effectively explore
heterogeneous treatment effects. Simulation studies indicate that
the new approach improves upon traditional local polynomial
regression on both </span></font></font></span><span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal"><font color="#222222"><font style=""><span lang="en-US">simple
and complex data generating processes in terms of estimation
error, coverage, and interval length for both average and
conditional average treatment effects. We illustrate the new
method by analyzing data studied originally by Lindo et al. (2010)
to estimate the effect of academic probation </span></font></font></span><span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal"><font color="#222222"><font style=""><span lang="en-US">on
university students’ GPA; we find an average increase of 0.15 in
GPA for students whose previous semester GPA lied just below the
probation cutoff.</span></font></font></span><span lang="en-US"><b><br>
</b></span>
</font></p><p class="gmail-western" align="left" style="font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;line-height:100%;margin-bottom:0cm;font-family:"Liberation Serif","Times New Roman",serif;font-size:12pt;color:rgb(0,0,0);direction:ltr;background:transparent">
<span style="display:inline-block;border:none;padding:0cm"><font style=""><font color="#222222" size="2" face="arial, sans-serif"><b>Bio:</b> </font></font></span><span style="background-color:transparent;font-family:Arial,Helvetica,sans-serif;font-size:small;color:rgb(34,34,34)">Possui graduação e mestrado em Estatística pela UFRJ e doutorado
em Estatística e Teoria da Decisão pela Duke University. Foi
Professor de Estatística das Universidades Federal Fluminense e
Federal do Rio de Janeiro e de Estatística e Econometria da
University of Chicago Booth School of Business. Atualmente é
Professor de Estatística e Econometria do Insper - Instituto de
Ensino e Pesquisa. Tem atuado em várias áreas da Estatística e da
Econometria, com particular ênfase em métodos computacionais (MCMC,
algoritmos de saltos reversíveis e filtros de partículas) e na
abordagem Bayesiana em modelos dinâmicos, modelos fatoriais, modelos
espaço-temporal, teoria do valor extremo, cópula dinâmica, modelos
de mistura, modelos de volatilidade estocástica univariada e
multivariada, econometria financeira e séries temporais e variáveis
instrumentais.</span></p>
</td>
</tr>
</tbody></table></div></div>