topic Re: running regression with condition on sample size in SAS Programming https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824322#M325534 <P><SPAN>This is about this part of ypour quwation.<BR />"the observations under any particular NIC code will be less than 10 also. i would like to exclude observations under such NIC codes in running the regression. "</SPAN></P> <P><SPAN>Identify the Year+NIC combination and remove such records, in the data preparation step and before you start performing the regression.&nbsp;<BR />Make sure that the data is sorted using the by variables before the regression is performed.<BR />Once done your code should give the desired results.</SPAN></P> Wed, 20 Jul 2022 10:42:24 GMT Sajid01 2022-07-20T10:42:24Z running regression with condition on sample size https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824280#M325517 <P>dear all,&nbsp;</P><P>i have my data in the following format&nbsp;</P><TABLE><TBODY><TR><TD>company_name</TD><TD>year</TD><TD>NIC</TD><TD>Y</TD><TD>X1</TD><TD>X2</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2011</TD><TD>8</TD><TD>0.332</TD><TD>1.484</TD><TD>0.367</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2012</TD><TD>8</TD><TD>0.306</TD><TD>1.324</TD><TD>0.139</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2013</TD><TD>8</TD><TD>0.289</TD><TD>1.081</TD><TD>0.050</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2014</TD><TD>8</TD><TD>0.303</TD><TD>1.030</TD><TD>0.048</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2015</TD><TD>8</TD><TD>0.283</TD><TD>0.972</TD><TD>0.071</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2016</TD><TD>8</TD><TD>0.280</TD><TD>1.015</TD><TD>0.067</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2017</TD><TD>8</TD><TD>0.287</TD><TD>1.068</TD><TD>0.069</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2018</TD><TD>8</TD><TD>0.249</TD><TD>1.050</TD><TD>0.075</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2019</TD><TD>8</TD><TD>0.251</TD><TD>1.145</TD><TD>0.135</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2020</TD><TD>8</TD><TD>0.251</TD><TD>1.233</TD><TD>0.142</TD></TR><TR><TD>20 Microns Ltd.</TD><TD>2021</TD><TD>8</TD><TD>0.223</TD><TD>1.057</TD><TD>-0.137</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2011</TD><TD>62</TD><TD>0.110</TD><TD>0.186</TD><TD>0.010</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2012</TD><TD>62</TD><TD>0.106</TD><TD>0.155</TD><TD>-0.011</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2013</TD><TD>62</TD><TD>0.075</TD><TD>0.103</TD><TD>-0.037</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2014</TD><TD>62</TD><TD>0.054</TD><TD>0.072</TD><TD>-0.012</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2015</TD><TD>62</TD><TD>0.052</TD><TD>0.089</TD><TD>0.017</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2016</TD><TD>62</TD><TD>0.034</TD><TD>0.092</TD><TD>-0.015</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2017</TD><TD>62</TD><TD>0.028</TD><TD>0.099</TD><TD>-0.024</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2018</TD><TD>62</TD><TD>0.028</TD><TD>0.085</TD><TD>-0.014</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2019</TD><TD>62</TD><TD>0.037</TD><TD>0.108</TD><TD>0.018</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2020</TD><TD>62</TD><TD>0.018</TD><TD>0.073</TD><TD>-0.032</TD></TR><TR><TD>3I Infotech Ltd.</TD><TD>2021</TD><TD>62</TD><TD>0.023</TD><TD>0.073</TD><TD>0.003</TD></TR><TR><TD>3M India Ltd.</TD><TD>2011</TD><TD>22</TD><TD>0.332</TD><TD>1.919</TD><TD>0.158</TD></TR><TR><TD>3M India Ltd.</TD><TD>2012</TD><TD>22</TD><TD>0.331</TD><TD>1.842</TD><TD>0.281</TD></TR><TR><TD>3M India Ltd.</TD><TD>2013</TD><TD>22</TD><TD>0.303</TD><TD>1.681</TD><TD>0.182</TD></TR><TR><TD>3M India Ltd.</TD><TD>2014</TD><TD>22</TD><TD>0.268</TD><TD>1.272</TD><TD>0.120</TD></TR><TR><TD>3M India Ltd.</TD><TD>2015</TD><TD>22</TD><TD>0.263</TD><TD>1.279</TD><TD>0.069</TD></TR><TR><TD>3M India Ltd.</TD><TD>2016</TD><TD>22</TD><TD>0.283</TD><TD>1.393</TD><TD>0.195</TD></TR><TR><TD>3M India Ltd.</TD><TD>2017</TD><TD>22</TD><TD>0.348</TD><TD>1.570</TD><TD>0.145</TD></TR><TR><TD>3M India Ltd.</TD><TD>2018</TD><TD>22</TD><TD>0.241</TD><TD>1.289</TD><TD>0.104</TD></TR></TBODY></TABLE><P>I have to regress Y on X1 and X2. the regression should be run for each year&nbsp; and in each year, each NIC code separately. I use the following code for running the regression and for saving the residual and predicted values.&nbsp;</P><P>&nbsp;</P><P>PROC REG DATA=have;<BR />MODEL Y=X1 X2;<BR />by YEAR NIC;<BR />output out=estimated<BR />p=predicted<BR />r=residual;<BR />run;&nbsp;</P><P>&nbsp;</P><P>in some cases, the observations under any particular NIC code will be less than 10 also. i would like to exclude observations under such NIC codes in running the regression.&nbsp;</P><P>&nbsp;</P><P>please let me how should i modify the above mentioned code to achieve this purpose.&nbsp;</P><P>&nbsp;</P><P>thanking you in advance&nbsp;&nbsp;</P> Wed, 20 Jul 2022 05:31:32 GMT https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824280#M325517 srikanthyadav44 2022-07-20T05:31:32Z Re: running regression with condition on sample size https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824317#M325532 <P>Did you mean to use Company_Name instead of Year on the BY statement?&nbsp;</P> <P>Also, the NIC is constant for each company, so I suspect you should simply use<BR />BY Company_Name;<BR />for this analysis.</P> <P>&nbsp;</P> <P>To exclude observations for which NIC &lt; 10, use a WHERE statement, as follows:</P> <PRE><CODE class=" language-sas">PROC REG DATA=have; where NIC &gt;= 10; by Company_Name; MODEL Y=X1 X2; output out=estimated p=predicted r=residual; run; </CODE></PRE> Wed, 20 Jul 2022 09:59:10 GMT https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824317#M325532 Rick_SAS 2022-07-20T09:59:10Z Re: running regression with condition on sample size https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824322#M325534 <P><SPAN>This is about this part of ypour quwation.<BR />"the observations under any particular NIC code will be less than 10 also. i would like to exclude observations under such NIC codes in running the regression. "</SPAN></P> <P><SPAN>Identify the Year+NIC combination and remove such records, in the data preparation step and before you start performing the regression.&nbsp;<BR />Make sure that the data is sorted using the by variables before the regression is performed.<BR />Once done your code should give the desired results.</SPAN></P> Wed, 20 Jul 2022 10:42:24 GMT https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824322#M325534 Sajid01 2022-07-20T10:42:24Z Re: running regression with condition on sample size https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824326#M325536 Hi Rick_SAS<BR />the code is not working.<BR />i want to include the observations where frequency with the NIC code is<BR />more than 10.<BR />NIC code is the classification of the companies. for example, NIC code 01<BR />has only 8 companies in a particular year, want to exclude all the<BR />companies with NIC code 01 for that particular year , in running the<BR />regression.<BR />please suggest me the SAS CODE with this condition<BR /><BR />thanking you in advance<BR /> Wed, 20 Jul 2022 11:31:45 GMT https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824326#M325536 srikanthyadav44 2022-07-20T11:31:45Z Re: running regression with condition on sample size https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824327#M325537 <BLOCKQUOTE><HR /><a href="https://communities.sas.com/t5/user/viewprofilepage/user-id/280123">@srikanthyadav44</a>&nbsp;wrote:<BR /><BR />NIC code is the classification of the companies. for example, NIC code 01<BR />has only 8 companies in a particular year, want to exclude all the<BR />companies with NIC code 01 for that particular year , in running the<BR />regression.<BR /><HR /></BLOCKQUOTE> <P>this is confusing, as this is not what is seen in your example data. Could you explain more and provide example data that illustrates the issue?</P> Wed, 20 Jul 2022 11:43:10 GMT https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824327#M325537 PaigeMiller 2022-07-20T11:43:10Z Re: running regression with condition on sample size https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824563#M325642 Dear Mr. Paige Miller<BR />i have updated my query with more clear illustration.<BR />please have a look and suggest a SAS code<BR />thank you in advance Thu, 21 Jul 2022 08:25:03 GMT https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824563#M325642 srikanthyadav44 2022-07-21T08:25:03Z Re: running regression with condition on sample size https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824564#M325643 <TABLE><TBODY><TR><TD>company_name</TD><TD>year</TD><TD>NIC</TD><TD>Y</TD><TD>X1</TD><TD>X2</TD></TR><TR><TD>A D F Foods Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.18</TD><TD>0.88</TD><TD>0.08</TD></TR><TR><TD>Adani Wilmar Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.29</TD><TD>4.08</TD><TD>1.16</TD></TR><TR><TD>Agro Tech Foods Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.44</TD><TD>2.50</TD><TD>0.24</TD></TR><TR><TD>Ajanta Soya Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.17</TD><TD>6.23</TD><TD>1.44</TD></TR><TR><TD>Ambar Protein Inds. Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.17</TD><TD>7.12</TD><TD>1.53</TD></TR><TR><TD>Andrew Yule &amp; Co. Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.14</TD><TD>0.54</TD><TD>0.12</TD></TR><TR><TD>Arcuttipore Tea Co. Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.05</TD><TD>0.22</TD><TD>0.00</TD></TR><TR><TD>Avanti Feeds Ltd.</TD><TD>2011</TD><TD>10</TD><TD>0.15</TD><TD>1.76</TD><TD>0.95</TD></TR><TR><TD>Associated Alcohols &amp; Breweries Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.13</TD><TD>0.95</TD><TD>0.11</TD></TR><TR><TD>Devyani International Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.37</TD><TD>1.44</TD><TD>-0.04</TD></TR><TR><TD>Eco Friendly Food Processing Park Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.01</TD><TD>0.11</TD><TD>0.02</TD></TR><TR><TD>Elegant Floriculture &amp; Agrotech (India) Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.02</TD><TD>0.04</TD><TD>0.00</TD></TR><TR><TD>Flex Foods Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.15</TD><TD>0.61</TD><TD>0.11</TD></TR><TR><TD>G M Breweries Ltd.</TD><TD>2011</TD><TD>11</TD><TD>3.89</TD><TD>2.01</TD><TD>0.10</TD></TR><TR><TD>G R M Overseas Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.13</TD><TD>1.61</TD><TD>-1.00</TD></TR><TR><TD>Naturite Agro Products Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.19</TD><TD>1.26</TD><TD>1.13</TD></TR><TR><TD>Orient Beverages Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.14</TD><TD>0.39</TD><TD>0.12</TD></TR><TR><TD>S I P Industries Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.11</TD><TD>0.21</TD><TD>-0.05</TD></TR><TR><TD>Sinnar Bidi Udyog Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.07</TD><TD>0.92</TD><TD>0.13</TD></TR><TR><TD>Tarai Foods Ltd.</TD><TD>2011</TD><TD>11</TD><TD>0.10</TD><TD>0.22</TD><TD>-0.22</TD></TR><TR><TD>A D F Foods Ltd.</TD><TD>2012</TD><TD>10</TD><TD>0.17</TD><TD>0.71</TD><TD>0.01</TD></TR><TR><TD>Adani Wilmar Ltd.</TD><TD>2012</TD><TD>10</TD><TD>0.19</TD><TD>3.70</TD><TD>1.08</TD></TR><TR><TD>Agro Tech Foods Ltd.</TD><TD>2012</TD><TD>10</TD><TD>0.40</TD><TD>2.47</TD><TD>-0.05</TD></TR><TR><TD>Ajanta Soya Ltd.</TD><TD>2012</TD><TD>10</TD><TD>0.17</TD><TD>6.87</TD><TD>1.26</TD></TR><TR><TD>Andrew Yule &amp; Co. Ltd.</TD><TD>2012</TD><TD>10</TD><TD>0.16</TD><TD>0.62</TD><TD>0.08</TD></TR><TR><TD>Arcuttipore Tea Co. Ltd.</TD><TD>2012</TD><TD>10</TD><TD>0.07</TD><TD>0.20</TD><TD>-0.03</TD></TR><TR><TD>Avanti Feeds Ltd.</TD><TD>2012</TD><TD>10</TD><TD>0.23</TD><TD>2.72</TD><TD>1.28</TD></TR><TR><TD>Associated Alcohols &amp; Breweries Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.13</TD><TD>1.24</TD><TD>0.43</TD></TR><TR><TD>Devyani International Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.42</TD><TD>1.50</TD><TD>0.36</TD></TR><TR><TD>Eco Friendly Food Processing Park Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.01</TD><TD>0.43</TD><TD>0.34</TD></TR><TR><TD>Elegant Floriculture &amp; Agrotech (India) Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.01</TD><TD>0.03</TD><TD>0.00</TD></TR><TR><TD>Flex Foods Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.20</TD><TD>0.67</TD><TD>0.06</TD></TR><TR><TD>G M Breweries Ltd.</TD><TD>2012</TD><TD>11</TD><TD>4.26</TD><TD>1.69</TD><TD>0.13</TD></TR><TR><TD>Naturite Agro Products Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.09</TD><TD>0.88</TD><TD>0.14</TD></TR><TR><TD>S D F Industries Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.32</TD><TD>0.69</TD><TD>-0.07</TD></TR><TR><TD>S I P Industries Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.17</TD><TD>0.14</TD><TD>-0.21</TD></TR><TR><TD>Saptarishi Agro Inds. Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.03</TD><TD>0.00</TD><TD>-0.41</TD></TR><TR><TD>Sinnar Bidi Udyog Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.08</TD><TD>0.35</TD><TD>-0.55</TD></TR><TR><TD>Tarai Foods Ltd.</TD><TD>2012</TD><TD>11</TD><TD>0.10</TD><TD>0.22</TD><TD>-0.05</TD></TR></TBODY></TABLE><P>i have updated the my data illustration to get more clarity on my query</P><P>in the above table, in the year 2011, the companies under "NIC 10" are only 8 . so, i would like to exclude in running the regression.&nbsp;</P><P>in the same year, companies "under NIC 11"&nbsp; are 12,, so i would like to include these companies in running the regression and so on .</P><P>&nbsp;</P><P>i have to run the regression for every year and for each NIC code separately(yearwise-NIC code wise)</P><P>&nbsp;</P><P>i am using this code presently, as requesting to suggest the change to this code to achieve my above discussed objective in running the regression&nbsp;</P><P>PROC REG DATA=have;<BR />MODEL Y=X1 X2 X3;<BR />by YEAR NIC;<BR />output out=estimated<BR />p=predicted<BR />r=residual;<BR />run;&nbsp;</P> Thu, 21 Jul 2022 08:33:30 GMT https://communities.sas.com/t5/SAS-Programming/running-regression-with-condition-on-sample-size/m-p/824564#M325643 srikanthyadav44 2022-07-21T08:33:30Z