<div dir="ltr"><p class="MsoNormal" align="center" style="text-align:center"><b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">Ciclo
de Palestras online do Departamento de Estatística da UFBA<span></span></span></b></p>

<p class="MsoNormal" align="center" style="text-align:center"><b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><span> </span></span></b></p>

<p class="MsoNormal"><b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">Palestrante</span></b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">:
Francisco Cribari-Neto, do DE/UFPE<span></span></span></p><p class="MsoNormal"><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><br></span></p>

<p class="MsoNormal"><b><span lang="EN-US" style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">Título</span></b><span lang="EN-US" style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">: Inference in a bimodal Birnbaum-Saunders model, DE/UFPE.<span></span></span></p><p class="MsoNormal"><span lang="EN-US" style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><br></span></p>

<p class="MsoNormal"><b><span lang="EN-US" style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">Resumo</span></b><span lang="EN-US" style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">: We address the issue of performing inference on the parameters that
index a bimodal extension of the Birnbaum-Saunders distribution (BS). We show
that maximum likelihood point estimation can be problematic since the standard
nonlinear optimization algorithms may fail to converge. To deal with this
problem, we penalize the log-likelihood function. The numerical evidence we
present show that maximum likelihood estimation based on such penalized
function is made considerably more reliable. We also consider hypothesis
testing inference based on the penalized log-likelihood function. In
particular, we consider likelihood ratio, signed likelihood ratio, score and
Wald tests. Bootstrap-based testing inference is also considered. We use a
nonnested hypothesis test to distinguish between two bimodal BS laws. We derive
analytical corrections to some tests. Monte Carlo simulation results and
empirical applications are presented and discussed. </span><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">O
pesquisador Rodney Fonseca é co-autor deste trabalho.<span></span></span></p><p class="MsoNormal"><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><br></span></p>

<p class="MsoNormal"><b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">Data:
30/06/2017                                                         <span></span></span></b></p>

<p class="MsoNormal"><b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"> Hora: 11hs <span></span></span></b></p><p class="MsoNormal"><b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><br></span></b></p>

<p class="MsoNormal"><b><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">O
link para acompanhar a palestra é<span></span></span></b></p>

<p class="MsoNormal"><a href="https://www.youtube.com/channel/UCC96Rmc3qKEYkKk187IcLdA/live"><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">https://www.youtube.com/channel/UCC96Rmc3qKEYkKk187IcLdA/live</span></a><u><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><span></span></span></u></p>

<span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif">E todos que estiverem
acompanhando de forma online poderão enviar dúvidas pelo chat da transmissão,
pois as perguntas serão repassadas para o Prof. Francisco Cribari-Neto.</span><br><div><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><br></span></div><div><span style="font-size:12pt;line-height:115%;font-family:"Times New Roman",serif"><p class="MsoNormal" style="margin-bottom:0.0001pt;font-family:arial,sans-serif;font-size:12.8px;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="font-size:12pt;font-family:"Times New Roman",serif">Atenciosamente,</span></p><p class="MsoNormal" style="margin-bottom:0.0001pt;font-family:arial,sans-serif;font-size:12.8px;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="font-size:12pt;font-family:"Times New Roman",serif"><span class="gmail-m_-1622829971794810687gmail-m_3220021166648906282gmail-il">Lizandra</span> Fabio e Bruno Santos</span></p><span style="font-size:12pt;line-height:18.4px">Coordenadores do Ciclo de Palestras DEST-UFB<wbr>A</span><br></span></div></div>