PSPP: Cluster Analysis

[@neffetsg]

Works perfect, thanks.

[@johnclayton8000]

GNU pspp 1.4.1 now has the ability to append the cluster index and the Euclidean distance to the dataset. The syntax now has a /Save option QUICK CLUSTER var_list [/CRITERIA=CLUSTERS(k) [MXITER(max_iter)] CONVERGE(epsilon) [NOINITIAL]] [/MISSING={EXCLUDE,INCLUDE} {LISTWISE, PAIRWISE}] [/PRINT={INITIAL} {CLUSTER}] [/SAVE[=[CLUSTER[(membership_var)]] [DISTANCE[(distance_var)]]] This adds 2 columns to your dataset: QUICK CLUSTER per1 per2 per3 per4 per5 /CRITERIA=CLUSTERS(4) /PRINT=CLUSTER /SAVE=CLUSTER DISTANCE. QCL_0 and QCL_1 The QCL_0 column contains the cluster index for the record. The QCL_1 column contains the Euclidean Distance from the cluster centre for the record.