{"id":67,"date":"2013-03-08T17:33:39","date_gmt":"2013-03-08T22:33:39","guid":{"rendered":"http:\/\/homepages.uc.edu\/~yaozo\/wordpress\/?p=67"},"modified":"2013-03-08T17:33:39","modified_gmt":"2013-03-08T22:33:39","slug":"spatial-panel-data-models-using-stata","status":"publish","type":"post","link":"https:\/\/zhuoyao.net\/index.php\/2013\/03\/08\/spatial-panel-data-models-using-stata\/","title":{"rendered":"Spatial panel data models using Stata"},"content":{"rendered":"

A new command for estimating and forecasting spatial panel data models using Stata is now available:\u00a0xsmle<\/a>.<\/p>\n

xsmle<\/a>\u00a0fits fixed or random effects spatial models for balanced panel data. See the\u00a0mi<\/a>\u00a0prefix command in order to use\u00a0xsmle<\/a>\u00a0in the unbalanced case. Consider the following general specification for the spatial panel data model:<\/p>\n

yit=\u03c4yit\u22121+\u03c1Wyit+Xit\u03b2+DZit\u03b8+ai+\u03b3t+vit
\nvit=\u03bbEvit+uit<\/p>\n

where\u00a0uit\u00a0is a normally distributed error term,\u00a0W\u00a0is the spatial matrix for the autoregressive component,\u00a0D\u00a0the\u00a0spatial matrix for the spatially lagged independent variables,\u00a0E\u00a0the spatial matrix for the idiosyncratic error\u00a0component.\u00a0ai\u00a0is the individual fixed or random effect and\u00a0\u03b3tis the time effect.\u00a0xsmle<\/a>\u00a0fits the following nested models:<\/p>\n

i) The SAR model with lagged dependent variable (\u00a0\u03b8=\u03bb=0\u00a0)<\/p>\n

yit=\u03c4yit\u22121+\u03c1Wyit+Xit\u03b2+ai+\u03b3t+uit\u00a0,<\/p>\n

where the standard SAR model is obtained by setting\u00a0\u03c4=0\u00a0.<\/p>\n

ii) The SDM model with lagged dependent variable (\u00a0\u03bb=0\u00a0)<\/p>\n

yit=\u03c4yit\u22121+\u03c1Wyit+Xit\u03b2+DZit\u03b8+ai+\u03b3t+uit\u00a0,<\/p>\n

where the standard SDM model is obtained by setting\u00a0\u03c4=0\u00a0.\u00a0xsmle<\/a>\u00a0allows to use a different weighting matrix for the spatially lagged dependent variable (\u00a0W\u00a0) and the\u00a0spatially lagged regressors (\u00a0D\u00a0) together with a different sets of explanatory (\u00a0Xit\u00a0) and spatially lagged\u00a0regressors (\u00a0Zit\u00a0). The default is to use\u00a0W=D\u00a0and\u00a0Xit=Zit\u00a0.<\/p>\n

iii) The SAC model (\u00a0\u03b8=\u03c4=0\u00a0)<\/p>\n

yit=\u03c1Wyit+Xit\u03b2+ai+\u03b3t+vit\u00a0,
\nvit=\u03bbEvit+uit\u00a0,<\/p>\n

for which\u00a0xsmle<\/a>\u00a0allows to use a different weighting matrix for the spatially lagged dependent variable (\u00a0W\u00a0) and the\u00a0error term (\u00a0E\u00a0).<\/p>\n

iv) The SEM model (\u00a0\u03c1=\u03b8=\u03c4=0\u00a0)<\/p>\n

yit=Xit\u03b2+ai+\u03b3t+vit\u00a0,
\nvit=\u03bbEvit+uit\u00a0.<\/p>\n

v) The GSPRE model (\u00a0\u03c1=\u03b8=\u03c4=0\u00a0)<\/p>\n

yit=Xit\u03b2+ai+vit\u00a0,
\nai=\u03d5Wai+\u03bci\u00a0,
\nvit=\u03bbEvit+uit\u00a0,<\/p>\n

where also the random effects have a spatial autoregressive form.<\/p>\n

The command was written together with\u00a0Andrea Piano Mortari<\/a>\u00a0and\u00a0Gordon Hughes<\/a>.<\/p>\n

You may install it by typing<\/p>\n

net install xsmle, all from(http:\/\/www.econometrics.it\/stata<\/a>)<\/code><\/p>\n

in your Stata command bar.<\/p>\n

HTH,
\nFederico<\/p>\n

 <\/p>\n

http:\/\/www.econometrics.it\/?p=312<\/p>\n","protected":false},"excerpt":{"rendered":"

A new command for estimating and forecasting spatial panel data models using Stata is now available:\u00a0xsmle. xsmle\u00a0fits fixed or random effects spatial models for balanced… <\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-67","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/posts\/67","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/comments?post=67"}],"version-history":[{"count":0,"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/posts\/67\/revisions"}],"wp:attachment":[{"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/media?parent=67"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/categories?post=67"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/zhuoyao.net\/index.php\/wp-json\/wp\/v2\/tags?post=67"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}