<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: How to calculate Cronbach's alpha using data from a correlation matrix in SAS? in New SAS User</title>
    <link>https://communities.sas.com/t5/New-SAS-User/How-to-calculate-Cronbach-s-alpha-using-data-from-a-correlation/m-p/565734#M11235</link>
    <description>&lt;P&gt;If I'm reading this correctly, it's the following, for at least the standardized Cronbach Alpha. I don't think you can calculate the non-standardized without full information.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The &lt;I&gt;standardized Cronbach's alpha&lt;/I&gt; can be defined as&lt;/P&gt;
&lt;DL&gt;
&lt;DD&gt;&lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/482efe306a23556da4bb197f024e075918027110" border="0" alt="\alpha _{{\text{standardized}}}={K{\bar  r} \over (1+(K-1){\bar  r})}" aria-hidden="true" /&gt;&lt;/SPAN&gt;&lt;/DD&gt;
&lt;/DL&gt;
&lt;P&gt;where &lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/2b76fce82a62ed5461908f0dc8f037de4e3686b0" border="0" alt="K" aria-hidden="true" /&gt;&lt;/SPAN&gt; is as above and &lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/3068f25537e70241a9a83d733c46fe052a905358" border="0" alt="{\bar  r}" aria-hidden="true" /&gt;&lt;/SPAN&gt; the mean of the &lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/b6b6edd9bbfad21f522f2145bb949630a4b341cf" border="0" alt="K(K-1)/2" aria-hidden="true" /&gt;&lt;/SPAN&gt; non-redundant &lt;A title="Correlation and dependence" href="https://en.wikipedia.org/wiki/Correlation_and_dependence#Pearson.27s_product-moment_coefficient" target="_blank"&gt;correlation coefficients&lt;/A&gt; (i.e., the mean of an &lt;A title="Triangular matrix" href="https://en.wikipedia.org/wiki/Triangular_matrix" target="_blank"&gt;upper triangular&lt;/A&gt;, or lower triangular, correlation matrix).&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;You have K, the number of elements and the r's to calculate the mean, so proc means, a data step or SQL should get you there though it is somewhat of a manual calculation.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&lt;A href="https://en.wikipedia.org/wiki/Cronbach's_alpha" target="_blank"&gt;https://en.wikipedia.org/wiki/Cronbach's_alpha&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;BLOCKQUOTE&gt;&lt;HR /&gt;&lt;a href="https://communities.sas.com/t5/user/viewprofilepage/user-id/277741"&gt;@daltonbc&lt;/a&gt;&amp;nbsp;wrote:&lt;BR /&gt;
&lt;P&gt;I have a correlation matrix, how can I calculate Cronbach's alpha of my factors using SAS? I don't have the original data set, just the correlation matrix, N, mean and std.&lt;/P&gt;
&lt;P&gt;I have a correlation matrix like this:&lt;/P&gt;
&lt;PRE&gt;DATA sol (TYPE=CORR);
INPUT _TYPE_ $ _NAME_ $ idealism relativism misanthropy gender attitude;
CARDS;
N        .        153     153     153     153      153
mean     .        3.64926 3.35810 2.32157 1.18954 2.37276
std      .        0.53439 0.57596 0.67560 0.39323 0.52979
corr idealism     1.0000   .       .       .       .
corr relativism  -0.0870  1.0000   .       .       .
corr misanthropy -0.1395  0.0525  1.0000   .       .
corr gender      -0.1011  0.0731  0.1504  1.0000   . 
corr attitude     0.0501  0.1581  0.2259 -0.1158  1.0000
;
proc factor;
    var  idealism relativism misanthropy gender attitude;
run;&lt;/PRE&gt;
&lt;DIV class="post-text"&gt;
&lt;P&gt;I was able to perform factorial analysis with my correlation matrix.&lt;/P&gt;
&lt;/DIV&gt;
&lt;DIV class="post-taglist grid gs4 gsy fd-column"&gt;&amp;nbsp;&lt;/DIV&gt;
&lt;HR /&gt;&lt;/BLOCKQUOTE&gt;
&lt;P&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;</description>
    <pubDate>Thu, 13 Jun 2019 03:09:34 GMT</pubDate>
    <dc:creator>Reeza</dc:creator>
    <dc:date>2019-06-13T03:09:34Z</dc:date>
    <item>
      <title>How to calculate Cronbach's alpha using data from a correlation matrix in SAS?</title>
      <link>https://communities.sas.com/t5/New-SAS-User/How-to-calculate-Cronbach-s-alpha-using-data-from-a-correlation/m-p/565728#M11234</link>
      <description>&lt;P&gt;I have a correlation matrix, how can I calculate Cronbach's alpha of my factors using SAS? I don't have the original data set, just the correlation matrix, N, mean and std.&lt;/P&gt;&lt;P&gt;I have a correlation matrix like this:&lt;/P&gt;&lt;PRE&gt;DATA sol (TYPE=CORR);
INPUT _TYPE_ $ _NAME_ $ idealism relativism misanthropy gender attitude;
CARDS;
N        .        153     153     153     153      153
mean     .        3.64926 3.35810 2.32157 1.18954 2.37276
std      .        0.53439 0.57596 0.67560 0.39323 0.52979
corr idealism     1.0000   .       .       .       .
corr relativism  -0.0870  1.0000   .       .       .
corr misanthropy -0.1395  0.0525  1.0000   .       .
corr gender      -0.1011  0.0731  0.1504  1.0000   . 
corr attitude     0.0501  0.1581  0.2259 -0.1158  1.0000
;
proc factor;
    var  idealism relativism misanthropy gender attitude;
run;&lt;/PRE&gt;&lt;DIV class="post-text"&gt;&lt;P&gt;I was able to perform factorial analysis with my correlation matrix.&lt;/P&gt;&lt;/DIV&gt;&lt;DIV class="post-taglist grid gs4 gsy fd-column"&gt;&amp;nbsp;&lt;/DIV&gt;</description>
      <pubDate>Thu, 13 Jun 2019 02:20:34 GMT</pubDate>
      <guid>https://communities.sas.com/t5/New-SAS-User/How-to-calculate-Cronbach-s-alpha-using-data-from-a-correlation/m-p/565728#M11234</guid>
      <dc:creator>daltonbc</dc:creator>
      <dc:date>2019-06-13T02:20:34Z</dc:date>
    </item>
    <item>
      <title>Re: How to calculate Cronbach's alpha using data from a correlation matrix in SAS?</title>
      <link>https://communities.sas.com/t5/New-SAS-User/How-to-calculate-Cronbach-s-alpha-using-data-from-a-correlation/m-p/565734#M11235</link>
      <description>&lt;P&gt;If I'm reading this correctly, it's the following, for at least the standardized Cronbach Alpha. I don't think you can calculate the non-standardized without full information.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The &lt;I&gt;standardized Cronbach's alpha&lt;/I&gt; can be defined as&lt;/P&gt;
&lt;DL&gt;
&lt;DD&gt;&lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/482efe306a23556da4bb197f024e075918027110" border="0" alt="\alpha _{{\text{standardized}}}={K{\bar  r} \over (1+(K-1){\bar  r})}" aria-hidden="true" /&gt;&lt;/SPAN&gt;&lt;/DD&gt;
&lt;/DL&gt;
&lt;P&gt;where &lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/2b76fce82a62ed5461908f0dc8f037de4e3686b0" border="0" alt="K" aria-hidden="true" /&gt;&lt;/SPAN&gt; is as above and &lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/3068f25537e70241a9a83d733c46fe052a905358" border="0" alt="{\bar  r}" aria-hidden="true" /&gt;&lt;/SPAN&gt; the mean of the &lt;SPAN class="mwe-math-element"&gt;&lt;IMG class="mwe-math-fallback-image-inline" src="https://wikimedia.org/api/rest_v1/media/math/render/svg/b6b6edd9bbfad21f522f2145bb949630a4b341cf" border="0" alt="K(K-1)/2" aria-hidden="true" /&gt;&lt;/SPAN&gt; non-redundant &lt;A title="Correlation and dependence" href="https://en.wikipedia.org/wiki/Correlation_and_dependence#Pearson.27s_product-moment_coefficient" target="_blank"&gt;correlation coefficients&lt;/A&gt; (i.e., the mean of an &lt;A title="Triangular matrix" href="https://en.wikipedia.org/wiki/Triangular_matrix" target="_blank"&gt;upper triangular&lt;/A&gt;, or lower triangular, correlation matrix).&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;You have K, the number of elements and the r's to calculate the mean, so proc means, a data step or SQL should get you there though it is somewhat of a manual calculation.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&lt;A href="https://en.wikipedia.org/wiki/Cronbach's_alpha" target="_blank"&gt;https://en.wikipedia.org/wiki/Cronbach's_alpha&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;BLOCKQUOTE&gt;&lt;HR /&gt;&lt;a href="https://communities.sas.com/t5/user/viewprofilepage/user-id/277741"&gt;@daltonbc&lt;/a&gt;&amp;nbsp;wrote:&lt;BR /&gt;
&lt;P&gt;I have a correlation matrix, how can I calculate Cronbach's alpha of my factors using SAS? I don't have the original data set, just the correlation matrix, N, mean and std.&lt;/P&gt;
&lt;P&gt;I have a correlation matrix like this:&lt;/P&gt;
&lt;PRE&gt;DATA sol (TYPE=CORR);
INPUT _TYPE_ $ _NAME_ $ idealism relativism misanthropy gender attitude;
CARDS;
N        .        153     153     153     153      153
mean     .        3.64926 3.35810 2.32157 1.18954 2.37276
std      .        0.53439 0.57596 0.67560 0.39323 0.52979
corr idealism     1.0000   .       .       .       .
corr relativism  -0.0870  1.0000   .       .       .
corr misanthropy -0.1395  0.0525  1.0000   .       .
corr gender      -0.1011  0.0731  0.1504  1.0000   . 
corr attitude     0.0501  0.1581  0.2259 -0.1158  1.0000
;
proc factor;
    var  idealism relativism misanthropy gender attitude;
run;&lt;/PRE&gt;
&lt;DIV class="post-text"&gt;
&lt;P&gt;I was able to perform factorial analysis with my correlation matrix.&lt;/P&gt;
&lt;/DIV&gt;
&lt;DIV class="post-taglist grid gs4 gsy fd-column"&gt;&amp;nbsp;&lt;/DIV&gt;
&lt;HR /&gt;&lt;/BLOCKQUOTE&gt;
&lt;P&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 13 Jun 2019 03:09:34 GMT</pubDate>
      <guid>https://communities.sas.com/t5/New-SAS-User/How-to-calculate-Cronbach-s-alpha-using-data-from-a-correlation/m-p/565734#M11235</guid>
      <dc:creator>Reeza</dc:creator>
      <dc:date>2019-06-13T03:09:34Z</dc:date>
    </item>
  </channel>
</rss>

