and thank you in advance for any suggestions. I have 20 binary symptoms (for example, anxiety yes/no, depression yes/no), and i have to do a cluster analysis for my research project in order to see which symptoms cluster together. However, i find this quite challenging, as i don't know which method of hierarchical cluster analysis i should use and what distance measure. Any help would be highly appreciated. Thank you!!
Any help would be highly appreciated Ok, I did a quick search on CrossValidated and found that there are several similar questions with excellent answers. This one shows hierarchical clustering is very well suited to binary data. Two step clustering is also mentioned . There are many similarity measures for binary data. See A Survey of Binary Similarity and Distance Measures for example. Both the answers linked to above contain plenty of additional links for further reading.
Kudos to the authors for providing much better answers than I could.
Best thing is to read around the topic and then start playing with various hierarchical clustering models and simialrity measures. There is a simple introduction to R's hclust algorithm here and another cross validated question here with R code included to get you going. I hope this helps