Sum of responses per category for preference questions.

I would prefer to learn about sustainability as:

In my residence hall, I would prefer to learn about sustainability as:

compare 2 recycling questions

##  [1] "Year"                 "Campus"               "und.sust"            
##  [4] "Learn.sust."          "Course"               "Cert.program"        
##  [7] "In.class"             "Club"                 "Campus.life"         
## [10] "Other.1"              "Programs"             "Bulletin.board"      
## [13] "Poster"               "CA"                   "Email.Newsletter"    
## [16] "Other.2"              "Not.apply"            "Conserve.energy"     
## [19] "Recycle"              "Shower.time"          "Teeth"               
## [22] "Leaks"                "Walk"                 "Public.transp"       
## [25] "Bike"                 "Fair.trade"           "organic"             
## [28] "low.env.effect"       "Family.friends"       "Recycle.knowledge"   
## [31] "Recycle.properly"     "Sust.school"          "Reasons.why"         
## [34] "Confident"            "Pract.sust.behaviors" "Friend"              
## [37] "Yes.but.Dont.Know"    "Havent.Heard"         "Media"               
## [40] "NA."                  "College.Quest"        "ResLife"             
## [43] "Family"               "High.School"          "und.def"

Within each of the columns, the shaded areas correspond to the proportions of the corresponding “recycle” categories. There is a proportion scale on the right of the plot. So, roughly 25% of those that answered 1 for “recycle knowledge” also answered 1 for “recycle.” The widths of the columns correspond to the number of samples in each of the categories. We see that the smallest category in “recycle knowledge” is 1. Areas within the columns reflects the distribution of “recycle” responses within each of the “recycle knowledge” categories.

I ran a chi-square test to see if the distribution of responses was what you’d expect just by pure chance or if there is a pattern.

chisq.test(rk.f, recycle.f)
## 
##  Pearson's Chi-squared test
## 
## data:  rk.f and recycle.f
## X-squared = 8.7359, df = 4, p-value = 0.06805

Compare ‘confident’ and ‘und.sust’ responses

## 
##  Pearson's Chi-squared test
## 
## data:  conf.f and und.sust.f
## X-squared = 42.0542, df = 6, p-value = 1.794e-07

Does living on campus affect response?