LISTSERV mailing list manager LISTSERV 16.0

Help for STAT_875 Archives


STAT_875 Archives

STAT_875 Archives


STAT_875@LISTSERV.UNL.EDU


View:

Message:

[

First

|

Previous

|

Next

|

Last

]

By Topic:

[

First

|

Previous

|

Next

|

Last

]

By Author:

[

First

|

Previous

|

Next

|

Last

]

Font:

Proportional Font

LISTSERV Archives

LISTSERV Archives

STAT_875 Home

STAT_875 Home

STAT_875  April 2009, Week 2

STAT_875 April 2009, Week 2

Subject:

Re: proj4

From:

Chris Bilder <[log in to unmask]>

Reply-To:

STAT 875 Listserv <[log in to unmask]>

Date:

Thu, 9 Apr 2009 09:04:52 -0500

Content-Type:

text/plain

Parts/Attachments:

Parts/Attachments

text/plain (57 lines)

Chris,

Are you sure that the conversion to EVP form worked?  Take a look at the EVP 
form to make sure it makes sense.  I have noticed the gummary() function will 
not work correctly at times if all (or most) of the n_j's  are equal to 1.  For 
example, another student in the class recently had this problem and their EVP 
form contained some 0 values for the n_j's.  If this is happening to you, I 
recommend that you replace the n_j created by gsummary() with your own 
that is simply a column of 1's.  Re-estimate the model in the EVP form with 
this new n_j and verify the estimates match what was given for the non-EVP 
form.  

Chaorong: There is still a saturated model with logistic regression.  One would 
have a separate parameter for every observation in the data set. :)


Chris


On Thu, 9 Apr 2009 13:36:02 +0000, [log in to unmask] 
<[log in to unmask]> wrote:

>Sorry. forget about the previous email. This is not log-linear model and there 
is no saturated model.
>
>Chaorong
>
>----
>Chaorong Wu, MA
>Statistical Consultant
>Nebraska Evaluation and Research (NEAR) Center
>College of Education and Human Sciences
>University of Nebraska-Lincoln
>248 Teachers College Hall
>Lincoln, NE 68588-0345
>Office Number: (402) 472-2580
>Email: [log in to unmask]
>Near Center Website: http://cehs.unl.edu/near
>________________________________________
>From: STAT 875 Listserv [[log in to unmask]] On Behalf Of Chris 
Wichman [[log in to unmask]]
>Sent: Wednesday, April 08, 2009 10:52 PM
>To: [log in to unmask]
>Subject: Re: proj4
>
>Just curious if anyone else is having a problem similar to mine:
>
>When I run my fitted model I get the original data set as my EVP, when I put 
this into examine.resid my G^2 = 0
>
>When I create adhoc categories and re run examine.resid I get a G^2 = 1
>
>If I use the weight = in glm() both my original data set EVP and my adhoc 
EVP result in exactly 0 for pearson and sd residuals, and I get a message 
stating that the Pearson Statistic cannot be calculated.
>
>Chris Wichman

Top of Message | Previous Page | Permalink

Advanced Options


Options

Log In

Log In

Get Password

Get Password


Search Archives

Search Archives


Subscribe or Unsubscribe

Subscribe or Unsubscribe


Archives

May 2017, Week 1
April 2017, Week 4
April 2017, Week 3
April 2017, Week 2
March 2017, Week 5
March 2017, Week 4
March 2017, Week 3
March 2017, Week 1
February 2017, Week 4
February 2017, Week 3
February 2017, Week 2
February 2017, Week 1
January 2017, Week 4
January 2017, Week 3
January 2017, Week 2
November 2016, Week 5
May 2016, Week 1
April 2016, Week 3
April 2016, Week 1
March 2016, Week 4
March 2016, Week 1
February 2016, Week 4
February 2016, Week 3
February 2016, Week 2
February 2016, Week 1
January 2016, Week 4
January 2016, Week 3
January 2016, Week 2
January 2016, Week 1
December 2015, Week 2
May 2015, Week 1
April 2015, Week 5
April 2015, Week 4
April 2015, Week 3
April 2015, Week 2
April 2015, Week 1
March 2015, Week 4
March 2015, Week 3
March 2015, Week 1
February 2015, Week 4
February 2015, Week 3
February 2015, Week 2
February 2015, Week 1
January 2015, Week 5
January 2015, Week 4
January 2015, Week 3
January 2015, Week 2
December 2014, Week 5
May 2014, Week 1
April 2014, Week 4
April 2014, Week 3
April 2014, Week 2
April 2014, Week 1
March 2014, Week 3
March 2014, Week 2
February 2014, Week 4
February 2014, Week 3
February 2014, Week 1
January 2014, Week 5
January 2014, Week 3
January 2014, Week 2
January 2014, Week 1
December 2013, Week 5
May 2013, Week 1
April 2013, Week 3
April 2013, Week 2
April 2013, Week 1
March 2013, Week 4
March 2013, Week 1
February 2013, Week 4
February 2013, Week 2
February 2013, Week 1
January 2013, Week 4
January 2013, Week 3
January 2013, Week 2
January 2013, Week 1
May 2012, Week 1
April 2012, Week 4
April 2012, Week 3
April 2012, Week 2
April 2012, Week 1
March 2012, Week 5
March 2012, Week 4
March 2012, Week 3
March 2012, Week 2
March 2012, Week 1
February 2012, Week 4
February 2012, Week 3
February 2012, Week 2
February 2012, Week 1
January 2012, Week 5
January 2012, Week 4
January 2012, Week 3
January 2012, Week 2
May 2010, Week 1
April 2010, Week 5
April 2010, Week 3
April 2010, Week 2
April 2010, Week 1
March 2010, Week 5
March 2010, Week 4
March 2010, Week 3
March 2010, Week 2
March 2010, Week 1
February 2010, Week 4
February 2010, Week 3
February 2010, Week 2
February 2010, Week 1
January 2010, Week 4
January 2010, Week 3
January 2010, Week 2
May 2009, Week 3
May 2009, Week 1
April 2009, Week 3
April 2009, Week 2
April 2009, Week 1
March 2009, Week 3
March 2009, Week 2
March 2009, Week 1
February 2009, Week 4
February 2009, Week 3
February 2009, Week 2
February 2009, Week 1
January 2009, Week 5
January 2009, Week 4
January 2009, Week 3
January 2009, Week 2
January 2009, Week 1
May 2008, Week 5
May 2008, Week 1
April 2008, Week 4
April 2008, Week 3
April 2008, Week 2
April 2008, Week 1
March 2008, Week 5
March 2008, Week 4
March 2008, Week 3
March 2008, Week 2
February 2008, Week 5
February 2008, Week 4
February 2008, Week 3
February 2008, Week 2
February 2008, Week 1
January 2008, Week 4
January 2008, Week 3
January 2008, Week 2
December 2007, Week 2
May 2007, Week 1
April 2007, Week 4
April 2007, Week 3
April 2007, Week 2
April 2007, Week 1
March 2007, Week 4
March 2007, Week 3
March 2007, Week 2
February 2007, Week 4
February 2007, Week 3
February 2007, Week 2
February 2007, Week 1
January 2007, Week 5
January 2007, Week 4
January 2007, Week 3
January 2007, Week 2
December 2006, Week 3
May 2006, Week 1
April 2006, Week 4
April 2006, Week 3
April 2006, Week 2
April 2006, Week 1
March 2006, Week 5
March 2006, Week 4
March 2006, Week 3
March 2006, Week 2
March 2006, Week 1
February 2006, Week 4
February 2006, Week 3
February 2006, Week 2
February 2006, Week 1
January 2006, Week 5
January 2006, Week 4
January 2006, Week 3
January 2006, Week 2
January 2006, Week 1
December 2005, Week 4
May 2005, Week 1
April 2005, Week 4
April 2005, Week 3
April 2005, Week 2
April 2005, Week 1
March 2005, Week 4
March 2005, Week 3
March 2005, Week 2
March 2005, Week 1
February 2005, Week 4
February 2005, Week 3
February 2005, Week 2
February 2005, Week 1
January 2005, Week 5
January 2005, Week 4
January 2005, Week 3
January 2005, Week 2
January 2005, Week 1
December 2004, Week 3

ATOM RSS1 RSS2



LISTSERV.UNL.EDU

CataList Email List Search Powered by the LISTSERV Email List Manager