<html>
  <head>

    <meta http-equiv="content-type" content="text/html; charset=iso-2022-jp">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    <div class="moz-text-html" lang="ja">
      <div class="moz-text-html" lang="ja">
        <div class="moz-text-html" lang="ja">
          <div class="moz-text-html" lang="ja">
            <pre><font size="3">$BGR7<!!;~2<$^$9$^$9$4@61I$N$3$H$H$*7D$S?=$7>e$2$^$9!#(B

$B$5$F!$Bh(B146$B2sCO0h2J3X%o!<%/%7%g%C%W$r!$2<5-$NDL$j3+:E$9$k1?$S$H$J$j$^$7(B
$B$?$N$G$40FFb?=$7>e$2$^$9!#$4B?K;Cf$H$OB8$8$^$9$,!$@'Hs$4=P@J$/$@$5$$!#(B

                              $B5-(B

$BF|(B  $B;~!'(B2016$BG/(B3$B7n(B11$BF|!J6b!K(B16$B!'(B00$B!A(B18$B!'(B00

$B>l(B  $B=j!'ElKLBg3X(B $B>pJs2J3X8&5f2J?7Eo(B412$B9f<<(B

</font><font size="3">$BJs!!(B  $B9p(B  $B!!<T!'(B<font face="Times New Roman">$B@%C+!!AO(B $B!!!J9-EgBg3X!K(B</font></font><font face="Times New Roman"><b><span style="font-size: 12pt;"><span lang="EN-US"><o:p></o:p></span></span></b></font><pre><font face="Times New Roman">$B%?!!%$!!%H!!%k!'(B</font><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,serif;
mso-fareast-font-family:&quot;$B#M#S(B $B%4%7%C%/(B&quot;;mso-font-kerning:0pt" lang="EN-US">A new approach to investigate spatially varying relationships</span>
<span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,serif;
mso-fareast-font-family:&quot;$B#M#S(B $B%4%7%C%/(B&quot;;mso-font-kerning:0pt;mso-ansi-language:EN-US;
mso-fareast-language:JA;mso-bidi-language:AR-SA" lang="EN-US">- Application to the hedonic analysis of flood risk - </span><span style="font-size:12.0pt;font-family:
&quot;$B#M#S(B $B#P%4%7%C%/(B&quot;;mso-bidi-font-family:&quot;$B#M#S(B $B#P%4%7%C%/(B&quot;;mso-font-kerning:0pt;mso-ansi-language:
EN-US;mso-fareast-language:JA;mso-bidi-language:AR-SA" lang="EN-US"></span></pre></pre>
            <pre><pre>$B%"%V%9%H%i%/%H!'(B<span style="font-size:12.0pt;font-family:&quot;$B#M#S(B $B#P%4%7%C%/(B&quot;;mso-bidi-font-family:&quot;$B#M#S(B $B#P%4%7%C%/(B&quot;;
mso-font-kerning:0pt" lang="EN-US"></span><span style="font-size:12.0pt;font-family:&quot;Times New Roman&quot;,serif;
mso-fareast-font-family:&quot;$B#M#S(B $B%4%7%C%/(B&quot;;mso-font-kerning:0pt" lang="EN-US">This study developed a spatially varying coefficient model by 
extending the random effects eigenvector spatial filtering model (Murakami and 
Griffith, 2015). The developed model has the following properties: the coefficients
are interpretable in terms of the Moran coefficient; unlike standard spatially varying
coefficient models, our model estimates different spatial smoothness for each coefficient.
A Monte Carlo simulation revealed that our model outperforms geographically weighted
regression models with regard to the accuracy of the coefficient estimates and the
computational time. We then empirically applied our model to a land price
analysis of flood risk for Ibaraki prefecture. The obtained empirical result
showed that flood risk was not capitalized into land prices around the
inundated area by a river flood on September, 2015 in Joso municipality.<o:p></o:p></span><pre>$B")(B980-8579 $B@gBf;T@DMU6h9S4,;z@DMU(B6-3-09
        $B!!ElKLBg3XBg3X1!>pJs2J3X8&5f2JEo!J@DMU;3!K(B
        $B!!(B
$B!!!!!!!!!!@$OC?M!'0BF#D+IW!"A>F;CR!"2OLnC#?N!"0KF#N<!"D%M[!"2#0f>D1{(B
$B!!!!!!!!!!(BTEL$B!'!!(B 022-795-4503
$B!!!!!!!!!!(B<a moz-do-not-send="true" class="moz-txt-link-abbreviated" href="mailto:zhang@se.si.tohoku.ac.jp">zhang@se.is.tohoku.ac.jp</a></pre></pre></pre>
          </div>
        </div>
      </div>
    </div>
  </body>
</html>