Module: Statsample::SPSS

Defined in:
lib/statsample/converter/spss.rb

Class Method Summary collapse

Class Method Details

.tetrachoric_correlation_matrix(ds) ⇒ Object

Export a SPSS Matrix with tetrachoric correlations .

Use: 

ds=Daru::DataFrame.from_excel("my_data.xls")
puts Statsample::SPSS.tetrachoric_correlation_matrix(ds)



9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
 
# File 'lib/statsample/converter/spss.rb', line 9

def tetrachoric_correlation_matrix(ds)
  dsv=ds.reject_values(*Daru::MISSING_VALUES)
  # Delete all vectors doesn't have variation
  dsv.vectors.each { |f|
    if dsv[f].factors.size==1
      dsv.delete_vector(f) 
    else
      dsv[f]=dsv[f].dichotomize
    end
  }

  tcm=Statsample::Bivariate.tetrachoric_correlation_matrix(dsv)
  n=dsv.vectors.to_a.collect {|f|
    sprintf("%d",dsv[f].size)
  }
  meanlist=dsv.vectors.to_a.collect{|f|
    sprintf("%0.3f", dsv[f].mean)
  }
  stddevlist=dsv.vectors.to_a.collect{|f|
    sprintf("%0.3f", dsv[f].sd)
  }
  out=<<-HEREDOC
MATRIX DATA VARIABLES=ROWTYPE_ #{dsv.fields.join(",")}.
BEGIN DATA
N #{n.join(" ")}
MEAN	#{meanlist.join(" ")}
STDDEV #{stddevlist.join(" ")}
HEREDOC
tcm.row_size.times {|i|
  out +="CORR "
  (i+1).times {|j|
    out+=sprintf("%0.3f",tcm[i,j])+" "
  }
  out +="\n"
}
out+="END DATA.\nEXECUTE.\n"
end