Regression with complex causal structure - MathOverflow most recent 30 from http://mathoverflow.net2013-05-21T15:55:35Zhttp://mathoverflow.net/feeds/question/88239http://www.creativecommons.org/licenses/by-nc/2.5/rdfhttp://mathoverflow.net/questions/88239/regression-with-complex-causal-structureRegression with complex causal structureZwingli2012-02-11T22:53:00Z2012-02-13T20:10:46Z
<p>Hi , I have already run a whole bunch of OLS and found the following</p>
<p>Regress P= B1*L+e_1, found b1<0</p>
<p>Regress X= B2*L+e_2, found b2>0</p>
<p>Regress X= B3*P+e_3, found b3<0</p>
<p>I want to build a case with complex causal structure, in which there are two channels that L positively affects X.</p>
<p>1.Reducing P increases X</p>
<p>2.L positively affects X on its own</p>
<p>3.In addition, L positively affects X through the effect that increasing L reduces P, and we know reducing P increases X, thus this is the second channel that L positively affects X.</p>
<p>Two questions.</p>
<p>A. What OLS or other type of regression equations[I guess it takes more than 1 equation] should I run to prove my case, ie, to prove (if not possible to prove, strongly suggest) this whole system of causal strucuture? </p>
<p>B. What regression diagnostics should I use in SAS to show my logic behind the causal strcuture (L increases X through 2 channels )are ok?</p>
<p>Thanks.</p>
http://mathoverflow.net/questions/88239/regression-with-complex-causal-structure/88370#88370Answer by magnetohydrodynamic for Regression with complex causal structuremagnetohydrodynamic2012-02-13T20:10:46Z2012-02-13T20:10:46Z<p>You want to make a <a href="http://www.ssicentral.com/lisrel/techdocs/compsem.pdf" rel="nofollow">structural equation model</a>.</p>