topic Re: proc spatialreg optimization failure in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/proc-spatialreg-optimization-failure/m-p/691211#M33327 <P>Try to use &lt;/&gt; to load the output, rather than cutting and pasting.&nbsp; The former will preserve column id's, etc.&nbsp; Then please also include your code and some information about the dataset (response variable, number of records, etc.).&nbsp; All I can say is that it might (stressing might) be that your model is over-parameterized for the amount of data.&nbsp; Another possibility is multi-collinearity.</P> <P>&nbsp;</P> <P>SteveDenham</P> Tue, 13 Oct 2020 11:47:27 GMT SteveDenham 2020-10-13T11:47:27Z proc spatialreg optimization failure https://communities.sas.com/t5/Statistical-Procedures/proc-spatialreg-optimization-failure/m-p/691197#M33325 <P>I used proc spatialreg to analyze spatial econometrics model.</P><P>However, error messages kept showing up depending on model or data. "Opimization failed. Interpret the estimates with care" or&nbsp;</P><P>"Optimization cannot improve the function value". In addition, although the message 'Algorithm converged' comes out, standard error, t value, and p value don`t appear.&nbsp;</P><P>I specified quasi-Newton method and I specified maximum number of iterations as 1000.</P><P>&nbsp;</P><DIV class="branch"><DIV><DIV align="center"><TABLE cellspacing="0" cellpadding="5"><TBODY><TR><TD>Algorithm converged.</TD></TR></TBODY></TABLE></DIV></DIV><DIV><DIV align="center">Parameter EstimatesParameter DF Estimate StandardError t&nbsp;Value ApproxPr &gt; |t|Interceptpopf_rateacadoldfemalecollegemighouse_1ataxtrain_lambda_sigma2Restrict1 <TABLE cellspacing="0" cellpadding="5"><TBODY><TR><TD>1</TD><TD>12675</TD><TD>148.614569</TD><TD>85.29</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>32.448024</TD><TD>0.170667</TD><TD>190.12</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>505.773196</TD><TD>139.973396</TD><TD>3.61</TD><TD>0.0003</TD></TR><TR><TD>1</TD><TD>-585.435224</TD><TD>12.982785</TD><TD>-45.09</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>214.707052</TD><TD>12.250951</TD><TD>17.53</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>-499.383547</TD><TD>12.682656</TD><TD>-39.38</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>214.837050</TD><TD>1.364687</TD><TD>157.43</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>-240.843630</TD><TD>0.983443</TD><TD>-244.90</TD><TD>&lt;.0001</TD></TR><TR><TD>0</TD><TD>-199.938586</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>176.465831</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>1</TD><TD>98.594504</TD><TD>3.551837</TD><TD>27.76</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>1629.535839</TD><TD>152.198891</TD><TD>10.71</TD><TD>&lt;.0001</TD></TR><TR><TD>0</TD><TD>1.000000</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>1</TD><TD>11625708</TD><TD>0.255397</TD><TD>4.552E7</TD><TD>&lt;.0001</TD></TR><TR><TD>-1</TD><TD>94905077</TD><TD>.</TD><TD>.</TD><TD>. *</TD></TR></TBODY></TABLE><P>&nbsp;</P><DIV class="branch"><DIV><DIV align="center"><TABLE cellspacing="0" cellpadding="5"><TBODY><TR><TD>ERROR: Optimization failed. Interpret the estimates with care.</TD></TR></TBODY></TABLE></DIV></DIV><BR /><DIV><DIV align="center">Parameter EstimatesParameter DF Estimate StandardError t&nbsp;Value ApproxPr &gt; |t|Interceptpopf_rateacadoldfemalecollegemighouse_1ataxtrain_rho_lambda_sigma2 <TABLE cellspacing="0" cellpadding="5"><TBODY><TR><TD>1</TD><TD>4877.620429</TD><TD>5802.227026</TD><TD>0.84</TD><TD>0.4005</TD></TR><TR><TD>1</TD><TD>27.446622</TD><TD>1.054131</TD><TD>26.04</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>-738.228100</TD><TD>161.714703</TD><TD>-4.57</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>-460.278202</TD><TD>49.892925</TD><TD>-9.23</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>317.332993</TD><TD>23.506006</TD><TD>13.50</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>-514.798669</TD><TD>37.320073</TD><TD>-13.79</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>134.349259</TD><TD>93.345199</TD><TD>1.44</TD><TD>0.1501</TD></TR><TR><TD>1</TD><TD>-192.431771</TD><TD>19.548520</TD><TD>-9.84</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>-172.167729</TD><TD>18.373370</TD><TD>-9.37</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>221.460165</TD><TD>26.588296</TD><TD>8.33</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>383.475678</TD><TD>26.552452</TD><TD>14.44</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>1420.679084</TD><TD>299.021935</TD><TD>4.75</TD><TD>&lt;.0001</TD></TR><TR><TD>0</TD><TD>0.377923</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>-3.805885</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>1</TD><TD>660740</TD><TD>74.384999</TD><TD>8882.71</TD><TD>&lt;.0001</TD></TR></TBODY></TABLE><P>&nbsp;</P><DIV class="branch"><DIV><DIV align="center"><TABLE cellspacing="0" cellpadding="5"><TBODY><TR><TD>WARNING: Optimization cannot improve the function value.</TD></TR></TBODY></TABLE></DIV></DIV><DIV><DIV align="center">Parameter EstimatesParameter DF Estimate StandardError t&nbsp;Value ApproxPr &gt; |t|Interceptpopf_rateacadoldfemalecollegemighouse_1ataxtrain_lambda_sigma2Restrict1 <TABLE cellspacing="0" cellpadding="5"><TBODY><TR><TD>0</TD><TD>5033.903709</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>1</TD><TD>31.303281</TD><TD>0.028436</TD><TD>1100.83</TD><TD>&lt;.0001</TD></TR><TR><TD>1</TD><TD>569.039293</TD><TD>43.805973</TD><TD>12.99</TD><TD>&lt;.0001</TD></TR><TR><TD>0</TD><TD>-527.967647</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>438.671229</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>-363.941741</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>84.402772</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>-110.553241</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>-86.368103</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>1</TD><TD>223.582940</TD><TD>2.153441</TD><TD>103.83</TD><TD>&lt;.0001</TD></TR><TR><TD>0</TD><TD>381.665965</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>790.001959</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>1.000000</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>0</TD><TD>3031879</TD><TD>.</TD><TD>.</TD><TD>.</TD></TR><TR><TD>-1</TD><TD>81288778</TD><TD>.</TD><TD>.</TD><TD>. *</TD></TR></TBODY></TABLE></DIV></DIV></DIV></DIV></DIV></DIV></DIV></DIV></DIV> Tue, 13 Oct 2020 10:42:25 GMT https://communities.sas.com/t5/Statistical-Procedures/proc-spatialreg-optimization-failure/m-p/691197#M33325 Kyungjae 2020-10-13T10:42:25Z Re: proc spatialreg optimization failure https://communities.sas.com/t5/Statistical-Procedures/proc-spatialreg-optimization-failure/m-p/691211#M33327 <P>Try to use &lt;/&gt; to load the output, rather than cutting and pasting.&nbsp; The former will preserve column id's, etc.&nbsp; Then please also include your code and some information about the dataset (response variable, number of records, etc.).&nbsp; All I can say is that it might (stressing might) be that your model is over-parameterized for the amount of data.&nbsp; Another possibility is multi-collinearity.</P> <P>&nbsp;</P> <P>SteveDenham</P> Tue, 13 Oct 2020 11:47:27 GMT https://communities.sas.com/t5/Statistical-Procedures/proc-spatialreg-optimization-failure/m-p/691211#M33327 SteveDenham 2020-10-13T11:47:27Z