The accompanying table contains a portion of data from the National Longitudinal Survey (NLS), which follows over 12,000 individuals in the United States over time. Variables in this analysis include Urban (1 if lives in urban area, 0 otherwise), Siblings (number of siblings), White (1 if white, 0 otherwise), Christian (1 if Christian, 0 otherwise), FamilySize, Height, Weight (in pounds), and Income (in $).

a. Use hierarchical clustering to group the respondents. Use Gower’s coefficient for the distance between observations and Ward’s clustering method to cluster the individuals into four clusters. How many individuals are in the largest cluster? 

b. Describe the characteristics of the clusters.

Transcribed Image Text:

Urban 1 1 ⠀ 1 Siblings 8 1 ⠀ 2 White 1 1 ⠀ 1 ⠀ Income 0 40000 # 43000