Question about hierarchical Cluster Analysis

I'm doing using hierarchical Cluster Analysis with SPSS, for an ordinal variable (likert scale). The variable contains several statements.
Those statements are in rows not in columns (so the columns are the respondents are in columns). some of the participants did not answer all of the statements, so when I am running the analysis I get an error message, it seems that I need that all the answers will be completed. Can I fill the missing answers with the average of the respondents' answers in each statement? Or should I do something else?


Less is more. Stay pure. Stay poor.
For clarification are you conducting hierarchical cluster analysis where you end up with a dendrogram looking figure or hierarchical multilevel modeling of clusters (regression)?

Thanks and welcome to the forum!