statsample 0.5.0 → 0.5.1

data/lib/statsample/dominanceanalysis.rb

@@ -114,6 +114,11 @@ module Statsample
             }
             out
         end
+        def get_averages(averages)
+          out={}
+          averages.each{|key,val| out[key]=val.to_vector(:scale).mean }
+          out
+        end
         def average_k(k)
             return nil if k==@fields.size
             models=md_k(k)
@@ -123,11 +128,7 @@ module Statsample
                     averages[f].push(m.contributions[f]) unless m.contributions[f].nil?
                 }
             }
-            out={}
-            averages.each{|key,val|
-                out[key]=val.to_vector(:scale).mean
-            }
-            out
+            get_averages(averages)
         end
         def general_averages
             if @general_averages.nil?
@@ -138,11 +139,7 @@ module Statsample
                         averages[f].push(ak[f])
                     }
                 end
-                out={}
-                averages.each{|key,val|
-                    out[key]=val.to_vector(:scale).mean
-                }
-                @general_averages=out
+                @general_averages=get_averages(averages)
             end
             @general_averages
         end

data/lib/statsample/htmlreport.rb

@@ -27,6 +27,29 @@ module Statsample
         @uniq_file+=1
         "#{prepend}_#{@uniq_file}_#{Time.now.to_i}"
     end
+    
+    def add_tetrachoric_correlation_matrix(ds)
+      add_anchor("Tetrachoric correlation Matrix")
+      html="<h2>Tetrachoric Correlation Matrix</h2> <table><thead><th>-</th><th>"+ds.fields.join("</th><th>")+"</th> </thead> <tbody>"
+        matrix=Statsample::Bivariate.tetrachoric_correlation_matrix(ds)
+
+      
+        (0...(matrix.row_size)).each {|row|
+            html+="<tr><td>"+ds.fields[row]+"</td>"
+            (0...(matrix.column_size)).each {|col|
+                if matrix[row,col].nil?
+                    html+="<td>--</td>"
+                else
+                    html+="<td><strong>#{sprintf("%0.2f",matrix[row,col])}</td>"
+                end
+            }
+            html+="</tr>"
+        }
+        html+="</tbody></table>"
+        @partials.push(html)
+    end
+    
+    
     def add_correlation_matrix(ds)
         add_anchor("Correlation Matrix")
         html="<h2>Correlation Matrix</h2> <table><thead><th>-</th><th>"+ds.fields.join("</th><th>")+"</th> </thead> <tbody>"

data/lib/statsample/regression/multiple/baseengine.rb

@@ -8,7 +8,7 @@ module Statsample
         @y_var=y_var
         @r2=nil
         end
-        
+
         # Retrieves a vector with predicted values for y
         def predicted
         (0...@ds.cases).collect { |i|
@@ -52,13 +52,13 @@ module Statsample
         # Sum of squares (Error)
         def sse
         sst - ssr
-        end            
+        end
         # T values for coeffs
         def coeffs_t
         out={}
         se=coeffs_se
         coeffs.each{|k,v|
-        out[k]=v / se[k] 
+        out[k]=v / se[k]
         }
         out
         end
@@ -69,7 +69,7 @@ module Statsample
         # Mean Square Error
         def mse
         sse.quo(df_e)
-        end            
+        end
         # Degrees of freedom for regression
         def df_r
         @dep_columns.size
@@ -113,7 +113,7 @@ module Statsample
         out
         end
         # Estimated Variance-Covariance Matrix
-        # Used for calculation of se of constant 
+        # Used for calculation of se of constant
         def estimated_variance_covariance_matrix
         mse_p=mse
         columns=[]
@@ -129,7 +129,7 @@ module Statsample
         end
         # T for constant
         def constant_t
-        constant.to_f/constant_se 
+        constant.to_f/constant_se
         end
         # Standard error for constant
         def constant_se
@@ -140,27 +140,27 @@ module Statsample
         c=coeffs
         out=""
         out.extend report_type
-        out.add <<HEREDOC
-        Summary for regression of #{@fields.join(',')} over #{@y_var}
-        *************************************************************
-        Engine: #{self.class}
-        Cases(listwise)=#{@ds.cases}(#{@ds_valid.cases})
-        r=#{sprintf("%0.3f",r)}
-        r2=#{sprintf("%0.3f",r2)}
-        Equation=#{sprintf("%0.3f",constant)}+#{@fields.collect {|k| sprintf("%0.3f%s",c[k],k)}.join(' + ')}
+        out.add <<-HEREDOC
+Summary for regression of #{@fields.join(',')} over #{@y_var}
+*************************************************************
+Engine: #{self.class}
+Cases(listwise)=#{@ds.cases}(#{@ds_valid.cases})
+r=#{sprintf("%0.3f",r)}
+r2=#{sprintf("%0.3f",r2)}
+Equation=#{sprintf("%0.3f",constant)}+#{@fields.collect {|k| sprintf("%0.3f%s",c[k],k)}.join(' + ')}
 HEREDOC
-        
+
         out.add_line
         out.add "ANOVA TABLE"
-        
+
         t=Statsample::ReportTable.new(%w{source ss df ms f s})
         t.add_row(["Regression", sprintf("%0.3f",ssr), df_r, sprintf("%0.3f",msr), sprintf("%0.3f",f), sprintf("%0.3f", significance)])
         t.add_row(["Error", sprintf("%0.3f",sse), df_e, sprintf("%0.3f",mse)])
-        
+
         t.add_row(["Total", sprintf("%0.3f",sst), df_r+df_e])
-        
+
         out.parse_table(t)
-        
+
         begin
         out.add "Beta coefficientes"
         sc=standarized_coeffs
@@ -171,63 +171,63 @@ HEREDOC
         t.add_row([f, sprintf("%0.3f", c[f]), sprintf("%0.3f", sc[f]), sprintf("%0.3f", cse[f]), sprintf("%0.3f", c[f].quo(cse[f]))])
         }
         out.parse_table(t)
-        
+
         rescue
         end
         out
         end
         def assign_names(c)
-        a={}
-        @fields.each_index {|i|
-        a[@fields[i]]=c[i]
-        }
-        a
-        end
-        
-        
+          a={}
+          @fields.each_index {|i|
+          a[@fields[i]]=c[i]
+          }
+          a
+        end
+
+
         # Deprecated
         # Sum of squares of error (manual calculation)
         # using the predicted value minus the y_i value
         def sse_manual
-        pr=predicted
-        cases=0
-        sse=(0...@ds.cases).inject(0) {|a,i|
-        if !@dy.data_with_nils[i].nil? and !pr[i].nil?
-        cases+=1
-        a+((pr[i]-@dy[i])**2)
-        else
-        a
-        end
-        }
-        sse*(min_n_valid-1.0).quo(cases-1)
+          pr=predicted
+          cases=0
+          sse=(0...@ds.cases).inject(0) {|a,i|
+          if !@dy.data_with_nils[i].nil? and !pr[i].nil?
+          cases+=1
+          a+((pr[i]-@dy[i])**2)
+          else
+          a
+          end
+          }
+          sse*(min_n_valid-1.0).quo(cases-1)
         end
         # Sum of squares of regression
         # using the predicted value minus y mean
         def ssr_direct
-        mean=@dy.mean
-        cases=0
-        ssr=(0...@ds.cases).inject(0) {|a,i|
-        invalid=false
-        v=@dep_columns.collect{|c| invalid=true if c[i].nil?; c[i]}
-        if !invalid
-        cases+=1
-        a+((process(v)-mean)**2)
-        else
-        a
-        end
-        }
-        ssr
+          mean=@dy.mean
+          cases=0
+          ssr=(0...@ds.cases).inject(0) {|a,i|
+            invalid=false
+            v=@dep_columns.collect{|c| invalid=true if c[i].nil?; c[i]}
+            if !invalid
+              cases+=1
+              a+((process(v)-mean)**2)
+            else
+              a
+            end
+          }
+          ssr
         end
         def sse_direct
-        sst-ssr
+          sst-ssr
         end
         def process(v)
-        c=coeffs
-        total=constant
-        @fields.each_index{|i|
-        total+=c[@fields[i]]*v[i]
-        }
-        total
+          c=coeffs
+          total=constant
+          @fields.each_index{|i|
+            total+=c[@fields[i]]*v[i]
+          }
+          total
         end
       end
     end

data/lib/statsample/regression/multiple/gslengine.rb

@@ -1,4 +1,4 @@
-if HAS_ALGIB
+if HAS_GSL
 module Statsample
 module Regression
 module Multiple

data/lib/statsample/reliability.rb

@@ -1,160 +1,158 @@
 module Statsample
-	module Reliability
-		class << self
-            # Calculate Chonbach's alpha for a given dataset.
-            # only uses tuples without missing data
+  module Reliability
+	  class << self
+      # Calculate Chonbach's alpha for a given dataset.
+      # only uses tuples without missing data
 			def cronbach_alpha(ods)
 				ds=ods.dup_only_valid
 				n_items=ds.fields.size
 				sum_var_items=ds.vectors.inject(0) {|ac,v|
-					ac+v[1].variance_sample
-				}
+          ac+v[1].variance_sample }
 				total=ds.vector_sum
 				(n_items / (n_items-1).to_f) * (1-(sum_var_items/ total.variance_sample))
 			end
-            # Calculate Chonbach's alpha for a given dataset
-            # using standarized values for every vector.
-            # Only uses tuples without missing data
-
-            def cronbach_alpha_standarized(ods)
-                ds=ods.fields.inject({}){|a,f|
-                    a[f]=ods[f].vector_standarized
-                    a
-                }.to_dataset
-                cronbach_alpha(ds)
-            end
-		end
-        
+      # Calculate Chonbach's alpha for a given dataset
+      # using standarized values for every vector.
+      # Only uses tuples without missing data
+      
+      def cronbach_alpha_standarized(ods)
+        ds=ods.dup_only_valid.fields.inject({}){|a,f|
+          a[f]=ods[f].vector_standarized; a
+        }.to_dataset
+        cronbach_alpha(ds)
+      end
+		end   
 		class ItemCharacteristicCurve
-            attr_reader :totals, :counts,:vector_total
-            def initialize (ds, vector_total=nil)
-                vector_total||=ds.vector_sum
-                raise "Total size != Dataset size" if vector_total.size!=ds.cases
-                @vector_total=vector_total
-                @ds=ds
-                @totals={}
-                @counts=@ds.fields.inject({}) {|a,v| a[v]={};a}
-                process
-            end
-            def process
-                i=0
-                @ds.each{|row|
-					tot=@vector_total[i]
-                   @totals[tot]||=0
-                   @totals[tot]+=1
-					@ds.fields.each {|f|
-                        item=row[f].to_s
-                       @counts[f][tot]||={}
-                       @counts[f][tot][item]||=0
-                       @counts[f][tot][item] += 1 
-					}
+      attr_reader :totals, :counts,:vector_total
+      def initialize (ds, vector_total=nil)
+        vector_total||=ds.vector_sum
+        raise "Total size != Dataset size" if vector_total.size!=ds.cases
+        @vector_total=vector_total
+        @ds=ds
+        @totals={}
+        @counts=@ds.fields.inject({}) {|a,v| a[v]={};a}
+        process
+      end
+      def process
+        i=0
+        @ds.each do |row|
+          tot=@vector_total[i]
+          @totals[tot]||=0
+          @totals[tot]+=1
+					@ds.fields.each  do |f|
+            item=row[f].to_s
+            @counts[f][tot]||={}
+            @counts[f][tot][item]||=0
+            @counts[f][tot][item] += 1 
+          end
 					i+=1
-				}
-            end
-            def curve_field(field, item)
-                out={}
-                item=item.to_s
-                @totals.each{|value,n|
-                    count_value= @counts[field][value][item].nil? ? 0 : @counts[field][value][item] 
-                    out[value]=count_value.to_f/n.to_f
-                }
-                out
-            end
         end
+      end
+      def curve_field(field, item)
+        out={}
+        item=item.to_s
+        @totals.each{|value,n|
+            count_value= @counts[field][value][item].nil? ? 0 : @counts[field][value][item] 
+            out[value]=count_value.to_f/n.to_f
+        }
+        out
+      end
+    end
 		class ItemAnalysis
-            attr_reader :mean, :sd,:valid_n, :alpha , :alpha_standarized
+      attr_reader :mean, :sd,:valid_n, :alpha , :alpha_standarized
 			def initialize(ds)
-				@ds=ds.dup_only_valid
-				@total=@ds.vector_sum
-				@mean=@total.mean
-                @median=@total.median
-                @skew=@total.skew
-                @kurtosis=@total.kurtosis
-				@sd=@total.sdp
-				@valid_n=@total.size
-                begin
-				@alpha=Statsample::Reliability.cronbach_alpha(ds)
-				@alpha_standarized=Statsample::Reliability.cronbach_alpha_standarized(ds)
-                rescue => e
-                    raise DatasetException.new(@ds,e), "Problem on calculate alpha" 
-                end
+        @ds=ds.dup_only_valid
+        @total=@ds.vector_sum
+        @item_mean=@ds.vector_mean.mean
+        @mean=@total.mean
+        @median=@total.median
+        @skew=@total.skew
+        @kurtosis=@total.kurtosis
+        @sd = @total.sd
+        @valid_n = @total.size
+        begin
+          @alpha = Statsample::Reliability.cronbach_alpha(ds)
+          @alpha_standarized = Statsample::Reliability.cronbach_alpha_standarized(ds)
+        rescue => e
+          raise DatasetException.new(@ds,e), "Problem on calculate alpha" 
+        end
 			end
             # Returns a hash with structure
 			def item_characteristic_curve
-				i=0
-				out={}
-                total={}
-				@ds.each{|row|
-					tot=@total[i]
-					@ds.fields.each {|f|
-						out[f]||= {}
-                        total[f]||={}
-						out[f][tot]||= 0
-                        total[f][tot]||=0
-						out[f][tot]+= row[f] 
-                        total[f][tot]+=1
-					}
-					i+=1
-				}
-                total.each{|f,var|
-                    var.each{|tot,v|
-                        out[f][tot]=out[f][tot].to_f / total[f][tot]
-                    }
-                }
-                out
+        i=0
+        out={}
+        total={}
+        @ds.each do |row|
+          tot=@total[i]
+          @ds.fields.each do |f|
+            out[f]||= {}
+            total[f]||={}
+            out[f][tot]||= 0
+            total[f][tot]||=0
+            out[f][tot]+= row[f] 
+            total[f][tot]+=1
+          end
+          i+=1
+        end
+        total.each do |f,var|
+          var.each do |tot,v|
+            out[f][tot]=out[f][tot].to_f / total[f][tot]
+          end
+        end
+        out
 			end
-            def gnuplot_item_characteristic_curve(directory, base="crd",options={})
-                require 'gnuplot'
-
-                crd=item_characteristic_curve
-                @ds.fields.each {|f|
-                    x=[]
-                    y=[]
-                Gnuplot.open do |gp|
-                Gnuplot::Plot.new( gp ) do |plot|
-                    crd[f].sort.each{|tot,prop|
-                       x.push(tot)
-                       y.push((prop*100).to_i.to_f/100)
-                   }
-                plot.data << Gnuplot::DataSet.new( [x, y] ) do |ds|
-                ds.with = "linespoints"
-                ds.notitle
-                end
-
-                end
-                end
-            }
-            
-            end
-            def svggraph_item_characteristic_curve(directory, base="icc",options={})
-                require 'statsample/graph/svggraph'
-                crd=ItemCharacteristicCurve.new(@ds)
-               @ds.fields.each {|f|
-                   factors=@ds[f].factors.sort
-                   options={
-                           :height=>500,
-                           :width=>800,
-                           :key=>true
-                   }.update(options)
-                   graph = ::SVG::Graph::Plot.new(options)
-                   factors.each{|factor|
-                       factor=factor.to_s
-                       dataset=[]
-                           crd.curve_field(f, factor).each{|tot,prop|
-                               dataset.push(tot)
-                               dataset.push((prop*100).to_i.to_f/100)
-                            }
-                        graph.add_data({
-                                :title=>"#{factor}",
-                               :data=>dataset
-                        })
-                   }
-                   File.open(directory+"/"+base+"_#{f}.svg","w") {|fp|
-                       fp.puts(graph.burn())
-                   }
-               }
-               
-           end
+      def gnuplot_item_characteristic_curve(directory, base="crd",options={})
+        require 'gnuplot'
+        
+        crd=item_characteristic_curve
+        @ds.fields.each {|f|
+            x=[]
+            y=[]
+        Gnuplot.open do |gp|
+        Gnuplot::Plot.new( gp ) do |plot|
+            crd[f].sort.each{|tot,prop|
+               x.push(tot)
+               y.push((prop*100).to_i.to_f/100)
+           }
+        plot.data << Gnuplot::DataSet.new( [x, y] ) do |ds|
+        ds.with = "linespoints"
+        ds.notitle
+        end
+        
+        end
+        end
+        }
+        
+      end
+      def svggraph_item_characteristic_curve(directory, base="icc",options={})
+        require 'statsample/graph/svggraph'
+        crd=ItemCharacteristicCurve.new(@ds)
+        @ds.fields.each {|f|
+         factors=@ds[f].factors.sort
+         options={
+                 :height=>500,
+                 :width=>800,
+                 :key=>true
+         }.update(options)
+         graph = ::SVG::Graph::Plot.new(options)
+         factors.each{|factor|
+             factor=factor.to_s
+             dataset=[]
+                 crd.curve_field(f, factor).each{|tot,prop|
+                     dataset.push(tot)
+                     dataset.push((prop*100).to_i.to_f/100)
+                  }
+              graph.add_data({
+                      :title=>"#{factor}",
+                     :data=>dataset
+              })
+         }
+         File.open(directory+"/"+base+"_#{f}.svg","w") {|fp|
+             fp.puts(graph.burn())
+         }
+        }
+         
+      end
 			def item_total_correlation
 				@ds.fields.inject({}) do |a,v|
 					vector=@ds[v].dup
@@ -163,7 +161,7 @@ module Statsample
 					total=ds2.vector_sum
 					a[v]=Statsample::Bivariate.pearson(vector,total)
 					a
-				end
+        end
 			end
 			def item_statistics
 				@ds.fields.inject({}) do |a,v|
@@ -171,9 +169,29 @@ module Statsample
 					a
 				end
 			end
-			
+      # Returns a dataset with cases ordered by score
+      # and variables ordered by difficulty
+      
+			def item_difficulty_analysis
+        dif={}
+        @ds.fields.each{|f| dif[f]=@ds[f].mean }
+        dif_sort=dif.sort{|a,b| -(a[1]<=>b[1])}
+        scores_sort={}
+        scores=@ds.vector_mean
+        scores.each_index{|i| scores_sort[i]=scores[i] }
+        scores_sort=scores_sort.sort{|a,b| a[1]<=>b[1]}
+        ds_new=Statsample::Dataset.new(['case','score'] + dif_sort.collect{|a,b| a})
+        scores_sort.each do |i,score|
+          row=[i, score]
+          case_row=@ds.case_as_hash(i)
+          dif_sort.each{|variable,dif_value| row.push(case_row[variable]) }
+          ds_new.add_case_array(row)
+        end
+        ds_new.update_valid_data
+        ds_new
+      end
 			def stats_if_deleted
-				@ds.fields.inject({}){|a,v|
+				@ds.fields.inject({}) do |a,v|
 					ds2=@ds.dup
 					ds2.delete_vector(v)
 					total=ds2.vector_sum
@@ -183,13 +201,15 @@ module Statsample
 					a[v][:variance_sample]=total.variance_sample
 					a[v][:alpha]=Statsample::Reliability.cronbach_alpha(ds2)
 					a
-				}
+        end
 			end
 			def html_summary
 				html = <<EOF
 <p><strong>Summary for scale:</strong></p>
 <ul>
-<li>Mean=#{@mean}</li>
+<li>Items=#{@ds.fields.size}</li>
+<li>Total Mean=#{@mean}</li>
+<li>Item Mean=#{@item_mean}</li>
 <li>Std.Dv.=#{@sd}</li>
 <li>Median=#{@median}</li>
 <li>Skewness=#{sprintf("%0.3f",@skew)}</li>