I have the following code for a multivariate GMM. When I run it, it gives an error. Any advice or guidance would be appreciated. proc iml;
NOTE: IML Ready
80 use WORK.IMPORT4;
81 read all var {X1 X2} into x;
81 ! /* Read multiple variables x1 and x2 */
82
83 mu = {120 150};
83 ! /* Mean vector */
84 si = {20 20};
84 ! /* Standard deviation vector */
85 pi = {0.5 0.5};
85 ! /* Mixing weights */
86
87 nVars = ncol(x);
87 ! /* Number of variables */
88 nClusters = nrow(mu);
88 ! /* Number of clusters */
89
90 /* Estep */
91 stop = 0;
92 results = j(1, 1 + nClusters + nClusters*nVars + nClusters*nVars, .);
93 idx = 1;
94 do i = 1 to 200 while (stop = 0);
95 print "Iteration" i;
96
97 /* Compute gamma */
98 gamma = pi[1] * pdf('normal', x, mu[1], si[1]) +
99 pi[2] * pdf('normal', x, mu[2], si[2]);
100 gamma = gamma / (gamma[,1] + gamma[,2]);
100 ! /* Normalize gamma */
101
102 /* Check for convergence */
103 if i = 1 then print gamma;
104
105 nk = gamma[,1] + gamma[,2];
105 ! /* Calculate nk */
106
107 npi = nk / sum(nk);
107 ! /* Calculate npi */
108
109 nmu = j(1, nVars, 0);
110 do k = 1 to nClusters;
111 nmu = nmu + (gamma[,k] # x[,1:nVars]);
112 end;
113 nmu = nmu / nk;
113 ! /* Calculate nmu */
114
115 nsi2 = j(nVars, nVars, 0);
116
116 ! do k = 1 to nClusters;
117
117 ! diff = x[,1:nVars] - nmu;
118
118 ! nsi2 = nsi2 + (gamma[,k] * (diff` * diff));
119
119 ! end;
120
121 nsi = sqrt(nsi2);
121 ! /* Calculate nsi */
122
123 diff = max(abs(mu - nmu));
123 ! /* Calculate diff */
124
125 if diff < 0.005 then stop = 1;
126
127 mu = nmu;
127 ! /* Update mu */
128 si = nsi;
128 ! /* Update si */
129 pi = npi;
129 ! /* Update pi */
130
131 results[idx, 1] = i;
132 results[idx, 2:(1+nClusters)] = npi;
133 results[idx, (2+nClusters):(1+nClusters+nVars)] = nmu;
134 results[idx, (2+nClusters+nVars):(1+nClusters+2*nVars)] = nsi;
135 idx = idx + 1;
136 end;
ERROR: (execution) Matrices do not conform to the operation.
operation : * at line 118 column 31
operands : _TEM1001, _TEM1003
_TEM1001 1500 rows 1 col (numeric)
_TEM1003 2 rows 2 cols (numeric)
5054876.6 5443147.7
5443147.7 6657773.5
statement : ASSIGN at line 118 column 6
137
138 create results from results;
139 append from results;
140 close results;
NOTE: The data set WORK.RESULTS has 1 observations and 6 variables.
141
142 quit;
... View more
