https://communities.sas.com/t5/Statistical-Procedures/Predictive-modeling/m-p/355662#M18644 <P>Hi,</P><P>&nbsp;</P><P>I have the following sample dataset</P><P>&nbsp;</P><TABLE><TBODY><TR><TD>ID</TD><TD>Purchase Date</TD><TD>Age</TD><TD>Sales</TD></TR><TR><TD>3621901</TD><TD>04/01/2010</TD><TD>21</TD><TD>990</TD></TR><TR><TD>6271017</TD><TD>04/01/2010</TD><TD>29</TD><TD>642</TD></TR><TR><TD>3914676</TD><TD>02/01/2010</TD><TD>26</TD><TD>955</TD></TR><TR><TD>3888167</TD><TD>04/01/2010</TD><TD>32</TD><TD>834</TD></TR><TR><TD>3888167</TD><TD>04/01/2010</TD><TD>30</TD><TD>616</TD></TR><TR><TD>3888167</TD><TD>04/01/2010</TD><TD>38</TD><TD>657</TD></TR><TR><TD>3289156</TD><TD>04/01/2010</TD><TD>33</TD><TD>322</TD></TR><TR><TD>3621901</TD><TD>30/11/2011</TD><TD>27</TD><TD>855</TD></TR><TR><TD>6271017</TD><TD>31/05/2012</TD><TD>40</TD><TD>381</TD></TR><TR><TD>3914676</TD><TD>11/06/2012</TD><TD>29</TD><TD>915</TD></TR><TR><TD>3888167</TD><TD>11/06/2012</TD><TD>40</TD><TD>972</TD></TR><TR><TD>3015141</TD><TD>28/05/2012</TD><TD>26</TD><TD>755</TD></TR><TR><TD>4518247</TD><TD>28/05/2012</TD><TD>31</TD><TD>415</TD></TR><TR><TD>4518247</TD><TD>13/06/2012</TD><TD>30</TD><TD>652</TD></TR></TBODY></TABLE><P>&nbsp;</P><P>having 3 years of data for different customers &amp; as seen the customers ids may repeat over 2 different point in time.How is it best possible to run a predictive model given there are different point of time involved with same customer ids?</P><P>&nbsp;</P><P>Would be great if you can advice.</P> Wed, 03 May 2017 16:15:21 GMT Lopa2016 2017-05-03T16:15:21Z https://communities.sas.com/t5/Statistical-Procedures/Predictive-modeling/m-p/355662#M18644 <P>Hi,</P><P>&nbsp;</P><P>I have the following sample dataset</P><P>&nbsp;</P><TABLE><TBODY><TR><TD>ID</TD><TD>Purchase Date</TD><TD>Age</TD><TD>Sales</TD></TR><TR><TD>3621901</TD><TD>04/01/2010</TD><TD>21</TD><TD>990</TD></TR><TR><TD>6271017</TD><TD>04/01/2010</TD><TD>29</TD><TD>642</TD></TR><TR><TD>3914676</TD><TD>02/01/2010</TD><TD>26</TD><TD>955</TD></TR><TR><TD>3888167</TD><TD>04/01/2010</TD><TD>32</TD><TD>834</TD></TR><TR><TD>3888167</TD><TD>04/01/2010</TD><TD>30</TD><TD>616</TD></TR><TR><TD>3888167</TD><TD>04/01/2010</TD><TD>38</TD><TD>657</TD></TR><TR><TD>3289156</TD><TD>04/01/2010</TD><TD>33</TD><TD>322</TD></TR><TR><TD>3621901</TD><TD>30/11/2011</TD><TD>27</TD><TD>855</TD></TR><TR><TD>6271017</TD><TD>31/05/2012</TD><TD>40</TD><TD>381</TD></TR><TR><TD>3914676</TD><TD>11/06/2012</TD><TD>29</TD><TD>915</TD></TR><TR><TD>3888167</TD><TD>11/06/2012</TD><TD>40</TD><TD>972</TD></TR><TR><TD>3015141</TD><TD>28/05/2012</TD><TD>26</TD><TD>755</TD></TR><TR><TD>4518247</TD><TD>28/05/2012</TD><TD>31</TD><TD>415</TD></TR><TR><TD>4518247</TD><TD>13/06/2012</TD><TD>30</TD><TD>652</TD></TR></TBODY></TABLE><P>&nbsp;</P><P>having 3 years of data for different customers &amp; as seen the customers ids may repeat over 2 different point in time.How is it best possible to run a predictive model given there are different point of time involved with same customer ids?</P><P>&nbsp;</P><P>Would be great if you can advice.</P> Wed, 03 May 2017 16:15:21 GMT https://communities.sas.com/t5/Statistical-Procedures/Predictive-modeling/m-p/355662#M18644 Lopa2016 2017-05-03T16:15:21Z https://communities.sas.com/t5/Statistical-Procedures/Predictive-modeling/m-p/355971#M18660 <P>It seems it is REPEATED measure model.</P> <P>Check Generalize Linear Mixed Model.</P> <P>PROC GLIMMIX + RANDOM year/subject=id residual ;</P> Thu, 04 May 2017 13:48:36 GMT https://communities.sas.com/t5/Statistical-Procedures/Predictive-modeling/m-p/355971#M18660 Ksharp 2017-05-04T13:48:36Z