<BR><BR>  <BLOCKQUOTE class=replbq style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #1010ff 2px solid">Date: Mon, 6 Feb 2006 15:37:42 -0800 (PST)<BR>From: Julie Johnson &lt;aruba_2006@yahoo.com&gt;<BR>Subject: interpreting principal components of analysis<BR>To: rasch@acer.edu.au<BR><BR>  <DIV>I am a beginning Rasch user and am having difficulty interpreting the principal components of analysis print outs.&nbsp; I am hoping that my results are positive and would appreciate some assistance for experienced Rasch users.</DIV>  <DIV>&nbsp;</DIV>  <DIV>My results from Table 23.2 are below.</DIV>  <DIV>&nbsp;</DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'">STANDARDIZED RESIDUAL CONTRAST PLOT<?xml:namespace prefix = o ns = "urn:schemas-microsoft-com:office:office" /><o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
 style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'"><SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>Contrast 1 extracts 3.5 units out of 56 units of Item residual variance noise.<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'"><SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>Yardstick (variance explained by measures)-to-This Contrast ratio: 25.1:1<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'"><SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>Yardstick-to-Total Noise ratio (total variance of residuals): 1.6:1<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt;
 COLOR: black; FONT-FAMILY: 'Courier New'"><SPAN style="mso-spacerun: yes">&nbsp;</SPAN><o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'">Table of STANDARDIZED RESIDUAL variance (in Eigenvalue units)<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'"><SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>Empirical<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>Modeled<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt;
 mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'">Total variance in observations<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>=<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>143.6 100.0%<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>100.0%<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'">Variance explained by measures<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>=<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>87.6<SPAN style="mso-spacerun: yes">&nbsp; </SPAN>61.0%<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>61.1%<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align:
 none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'">Unexplained variance (total)<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>=<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>56.0<SPAN style="mso-spacerun: yes">&nbsp; </SPAN>39.0% 100.0%<SPAN style="mso-spacerun: yes">&nbsp;&nbsp; </SPAN>38.9%<o:p></o:p></SPAN></DIV>  <DIV class=MsoNormal style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN style="FONT-SIZE: 8pt; COLOR: black; FONT-FAMILY: 'Courier New'">Unexplned variance in 1st contrast =<SPAN style="mso-spacerun: yes">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </SPAN>3.5<SPAN style="mso-spacerun: yes">&nbsp;&nbsp; </SPAN>2.4%<SPAN style="mso-spacerun: yes">&nbsp;&nbsp; </SPAN>6.2%<o:p></o:p></SPAN></DIV>  <DIV>  <DIV>&nbsp;</DIV>  <DIV>Thanks for your input,</DIV>  <DIV>&nbsp;</DIV>  <DIV>Julie Johnson</DIV></DIV>  <div>  <HR SIZE=1>  Relax. Yahoo! Mail <A
 href="http://us.rd.yahoo.com/mail_us/taglines/viruscc/*http://communications.yahoo.com/features.php?page=221">virus scanning</A> helps detect nasty viruses!</BLOCKQUOTE><BR><p>__________________________________________________<br>Do You Yahoo!?<br>Tired of spam?  Yahoo! Mail has the best spam protection around <br>http://mail.yahoo.com