cluster

  1. S

    PhD - which statistical analysis to use? MLM, t tests, ANOVA?

    Hi, my research question is "do large cognitive changes precede a period of mood stability?" (N = 30), I have 20 therapy sessions data for each participant, which includes scores on a cognitive style questionnaire and scores on a mood questionnaire of each session. My supervisor has suggested...
  2. C

    Clusters building from series of financial data

    Hi everyone, First of all I need to tell you that I don't know many things about statistics - I work in finance. Currently I need to "reverse-engineering" one of our projects. To put it clear, I have a series of data (26 members, products we sell, percentage) that represent the share in total...
  3. J

    Help Hierarchial Cluster Analysis & Categorical data

    :confused: Hi, I am trying to cluster my variables which are all the letters of the alphabet by the observations of many participants in a lipreading experiment. I used cosine method as it detects patterns, and I transformed the reponses from letters to numbers to input in SPSS (A=1, B=2 ect)...
  4. C

    Help! should I use svy: logit or xtlogit random effect for stratified cluster RCT?!

    Hi, I'm analysing some secondary outcome data from a cluster RCT and I don't know whether to do it using svyset and then svy: logistic or whether to do xtlogit , or i(cluster) re ...they give very different odds ratios and so i do need to know which is correct! The trial design is as...
  5. V

    Dendrogram Not Working for Method: Wards, Measure: Cosine?

    I'm running an Hierarchical Cluster Analysis. When I run with Method: Wards, Measure: Euclidean, I get a beautiful dendrogram: The clusters with Method: Wards, Measure: Euclidean, are not nearly as useful as the clusters I get on this data using Method: Wards, Measure: Cosine. However...
  6. E

    Linear test for trend adjusted for cluster group?

    Hi, any help appreciated with this question. I have 8 time periods over which I wish to see if usage of a service changes using several demographics (age group, sex, HIV status, etc). There are about 2000 attendances in each time period from about 50 clusters. I can get proportions with 95%...