<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <title>DSpace Collection: Project Reports</title>
  <link rel="alternate" href="http://117.239.156.194:8080/jspui/handle/123456789/30" />
  <subtitle>Project Reports</subtitle>
  <id>http://117.239.156.194:8080/jspui/handle/123456789/30</id>
  <updated>2025-12-24T22:59:04Z</updated>
  <dc:date>2025-12-24T22:59:04Z</dc:date>
  <entry>
    <title>THE LOG OF GRAVITY</title>
    <link rel="alternate" href="http://117.239.156.194:8080/jspui/handle/123456789/73" />
    <author>
      <name>Silva, Santos, Silvana Enreyro</name>
    </author>
    <id>http://117.239.156.194:8080/jspui/handle/123456789/73</id>
    <updated>2024-03-26T05:33:12Z</updated>
    <published>2006-01-01T00:00:00Z</published>
    <summary type="text">Title: THE LOG OF GRAVITY
Authors: Silva, Santos, Silvana Enreyro
Abstract: Although economists have long been aware of Jensen’s in-&#xD;
equality, many econometric applications have neglected an important&#xD;
implication of it: under heteroskedasticity, the parameters of log-&#xD;
linearized models estimated by OLS lead to biased estimates of the true&#xD;
elasticities. We explain why this problem arises and propose an appropri-&#xD;
ate estimator. Our criticism of conventional practices and the proposed&#xD;
solution extend to a broad range of applications where log-linearized&#xD;
equations are estimated. We develop the argument using one particular&#xD;
illustration, the gravity equation for trade. We find significant differences&#xD;
between estimates obtained with the proposed estimator and those ob-&#xD;
tained with the traditional method.</summary>
    <dc:date>2006-01-01T00:00:00Z</dc:date>
  </entry>
</feed>

