To Whom It May Concern,<br><br>I&#39;m having a problem performing the 
causal inference portion of CEM with my data. Right now I have data with
 no missing values that categorizes citizen responses to political 
questions on voting behavior (which party bloc voted for, measured on an
 ordinal discrete scale), and political attitudes (two barometer 
questions, also measured on an ordinal discrete scale), as well as a 
number of background covariates (age, education, political interest, 
knowledge, religion, gender, etc.). My treatment variable is a 1 or 0 
depending on whether a respondent comes from an ethnically diverse 
district or not .<br>
<br>In running my CEM model, everything compiled just fine, however when trying to estimate the SATT, I get the following error:<br><br style="color: rgb(51, 51, 255);"><span style="color: rgb(51, 51, 255);">Error in att(mat1, as.factor(ONEPAR) ~ ELF + MUSLIM + CHRISTIAN + AGE +  : </span><br style="color: rgb(51, 51, 255);">

<span style="color: rgb(51, 51, 255);">  please, only use `lm&#39; or `glm&#39;</span><br><br>I
 suppose I&#39;m getting this because I chose a forest model for my 
estimation, but I don&#39;t see why this should be a problem. Just for 
reference here is my matching code and my att code. <br>
<br><span style="color: rgb(255, 0, 0);">AGECUT &lt;- c(0,29.5, 39.5, 49.5, 59.5, 69.5, 79.5)</span><br style="color: rgb(255, 0, 0);"><br style="color: rgb(255, 0, 0);"><span style="color: rgb(255, 0, 0);">mat1
 &lt;- cem(treatment=&quot;TREAT1&quot;, data=data2, drop=c(&quot;RESPNO&quot;, &quot;BACKCHK&quot;, 
&quot;URBRUR&quot;, &quot;PROVINCE&quot;, &quot;DISTRICT&quot;, &quot;ELF&quot;, &quot;DIVISION&quot;, &quot;LOCATION&quot;, 
&quot;DISCUSS&quot;, &quot;AUTH&quot;, &quot;PATR&quot;, &quot;ONEPAR&quot;,&quot;MULTPAR&quot;, &quot;FREEVOTE&quot;, &quot;FREEEXP&quot;, 
&quot;SINGLEAD&quot;, &quot;ELECT&quot;, &quot;REPRESENT&quot;, &quot;SALIENCE&quot;, &quot;TRUST1&quot;, &quot;TRUST2&quot;, 
&quot;TRUST3&quot;, &quot;REFORM1&quot;, &quot;REFORM2&quot;, &quot;Q88C_KEN&quot;, &quot;VOTE&quot;, &quot;RATIONALE&quot;, 
&quot;PATRON&quot;, &quot;FRVOTE&quot;, &quot;FREEXP&quot;, &quot;ELEC&quot;, &quot;MULTIPAR&quot;, &quot;REFORM&quot;, &quot;OTHERREL&quot;, 
&quot;TREAT&quot;, &quot;TREATMED2&quot;), cutpoints=list(AGE=AGECUT))</span><br style="color: rgb(255, 0, 0);">
<br style="color: rgb(255, 0, 0);"><span style="color: rgb(255, 0, 0);">mat1</span><br style="color: rgb(255, 0, 0);"><br style="color: rgb(255, 0, 0);"><span style="color: rgb(255, 0, 0);">est1 &lt;- att(mat1, ONEPAR~ELF+MUSLIM+CHRISTIAN+AGE+KNOW+INTEREST+EDUC+ETHMAJ+MALE, data=data2, model=&quot;forest&quot;)</span><br style="color: rgb(255, 0, 0);">

<br style="color: rgb(255, 0, 0);"><span style="color: rgb(255, 0, 0);">est1</span><br><br>If
 you have any idea of what I&#39;m doing incorrectly I&#39;d appreciate the 
help. My model runs fine using automated CEM via MatchIt, so I&#39;m not 
sure what the problem is here. Finally, I&#39;m getting some weird results 
with MatchIt -- namely, almost all the covariates on which I matched are
 turning up as significant. Any ideas as to what could be motivating 
this troubling anomaly? Note it is my understanding (possibly incorrect)
 that if treatment and control units are matched exactly, there should 
be no difference between treatment and control on matched covariates, 
and thus these measures should not significantly affect the outcome in 
the analysis.<br>
<br>Sincerely,<br>Ashley Anderson<br><font color="#888888">-- <br>Ph.D. Candidate<br>Harvard University Government Dept<br></font><br clear="all"><br>-- <br>Ph.D. Candidate<br>Harvard University Government Dept<br><br>