statsample 0.7.0 → 0.8.0

data/test/test_mle.rb

@@ -1,140 +1,139 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
-class StatsampleMLETestCase < Test::Unit::TestCase
-    def setup
-        @file_binomial=File.dirname(__FILE__)+'/../data/test_binomial.csv'
-        @crime=File.dirname(__FILE__)+'/../data/crime.txt'
-        @cases=100
-        a=Array.new()
-        b=Array.new()
-        c=Array.new()
-        y=Array.new()
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-        @cases.times{|i|
-            a.push(2*rand()-i)
-            b.push(2*rand()-5+i)
-            c.push(2*rand()+i)
-            y_val=i+(rand()*@cases.quo(2) - @cases.quo(4))
-            y.push(y_val<(@cases/2.0) ? 0.0 : 1.0)
-        }
-        a=a.to_vector(:scale)
-        b=b.to_vector(:scale)
-        c=c.to_vector(:scale)
-        y=y.to_vector(:scale)
-        
-        @ds_indep={'a'=>a,'b'=>b,'c'=>c}.to_dataset
-        constant=([1.0]*@cases).to_vector(:scale)
-        @ds_indep_2={'constant'=>constant,'a'=>a,'b'=>b,'c'=>c}.to_dataset
-        @ds_indep_2.fields=%w{constant a b c}
-        @mat_x=@ds_indep_2.to_matrix
-        @mat_y=y.to_matrix(:vertical)
-        @ds=@ds_indep.dup
-        @ds.add_vector('y',y)
-    end
-    def test_normal
-        y=Array.new()
-        y=@ds_indep.collect{|row|
-            row['a']*5+row['b']+row['c']+rand()*3
-        }
-        constant=([1]*@cases).to_vector(:scale)
-        ds_indep_2=@ds_indep.dup
-        ds_indep_2['constant']=constant
-        ds_indep_2.fields=%w{constant a b c}
-        mat_x=ds_indep_2.to_matrix
-        mat_y=y.to_matrix(:vertical)
-        mle=Statsample::MLE::Normal.new()
-        mle.verbose=false
-        coeffs_nr=mle.newton_raphson(mat_x,mat_y)
-        #p coeffs_nr
-        ds=@ds_indep.dup
-        ds.add_vector('y',y)
-        lr=Statsample::Regression.multiple(ds,'y')
-        lr_constant = lr.constant
-        lr_coeffs   = lr.coeffs
-        assert_in_delta(coeffs_nr[0,0], lr_constant,0.0000001)
-        assert_in_delta(coeffs_nr[1,0], lr_coeffs["a"],0.0000001)
-        assert_in_delta(coeffs_nr[2,0], lr_coeffs["b"],0.0000001)
-        assert_in_delta(coeffs_nr[3,0], lr_coeffs["c"],0.0000001)
-    end
-    
-    def test_probit
-        ds=Statsample::CSV.read(@file_binomial)
-        constant=([1.0]*ds.cases).to_vector(:scale)
-        ds_indep={'constant'=>constant, 'a'=>ds['a'],'b'=>ds['b'], 'c'=>ds['c']}.to_dataset(%w{constant a b c})
-        mat_x=ds_indep.to_matrix
-        mat_y=ds['y'].to_matrix(:vertical)
-        mle=Statsample::MLE::Probit.new
-        b_probit=mle.newton_raphson(mat_x,mat_y)
-        ll=mle.log_likehood(mat_x,mat_y,b_probit)
-        
-        b_exp=[-3.0670,0.1763,0.4483,-0.2240]
-        b_exp.each_index{|i|
-            assert_in_delta(b_exp[i], b_probit[i,0], 0.001)
-        }
-        assert_in_delta(-38.31559,ll,0.0001)
-    end
-    def test_logit_crime
-        ds=Statsample::PlainText.read(@crime, %w{crimerat maleteen south educ police60 police59 labor  males pop nonwhite unemp1  unemp2 median belowmed})
-        constant=([1.0]*ds.cases).to_vector(:scale)
-        ds2=ds.dup(%w{maleteen south educ police59})
-        ds2['constant']=constant
-        ds2.fields=%w{constant maleteen south educ police59}
-        mat_x=ds2.to_matrix
-        mat_y=(ds.compute "(crimerat>=110) ? 1:0").to_matrix(:vertical)
-        mle=Statsample::MLE::Logit.new
-        b=mle.newton_raphson(mat_x,mat_y)
-        ll=mle.log_likehood(mat_x,mat_y,b)
-        assert_in_delta(-18.606959,ll,0.001)
-        exp=[-17.701, 0.0833,-1.117, 0.0229, 0.0581]
-        exp.each_index{|i|
-            assert_in_delta(exp[i],b[i,0],0.001)
-        }
-        assert_equal(5,mle.iterations)        
-    end
-    def atest_logit_alglib
-        if(HAS_ALGIB)
-            ds=Statsample::CSV.read(@file_binomial)
-            constant=([1.0]*ds.cases).to_vector(:scale)
-            
-            ds_indep={'constant'=>constant, 'a'=>ds['a'],'b'=>ds['b'], 'c'=>ds['c']}.to_dataset(%w{constant a b c} )
-            
-            mat_x=ds_indep.to_matrix
-            mat_y=ds['y'].to_matrix(:vertical)
-            log=Alglib::Logit.build_from_matrix(ds.to_matrix)
-            coeffs=log.unpack[0]
-            b_alglib=Matrix.columns([[-coeffs[3], -coeffs[0], -coeffs[1], -coeffs[2]]])
-            mle=Statsample::MLE::Logit.new
-            ll_alglib=mle.log_likehood(mat_x,mat_y,b_alglib)
-            b_newton=mle.newton_raphson(mat_x,mat_y)
-            ll_pure_ruby=mle.log_likehood(mat_x,mat_y,b_newton)
-            #p b_alglib
-            #p b_newton
-            
-            assert_in_delta(ll_alglib,ll_pure_ruby,1)
-        end
+class StatsampleMLETestCase < MiniTest::Unit::TestCase
+  def setup
+    @file_binomial=File.dirname(__FILE__)+'/../data/test_binomial.csv'
+    @crime=File.dirname(__FILE__)+'/../data/crime.txt'
+    @cases=100
+    a=Array.new()
+    b=Array.new()
+    c=Array.new()
+    y=Array.new()
 
-    end
-    def atest_logit1
-        log=Alglib::Logit.build_from_matrix(@ds.to_matrix)
-        coeffs=log.unpack[0]
-        b=Matrix.columns([[-coeffs[3],-coeffs[0],-coeffs[1],-coeffs[2]]])
-#        puts "Coeficientes beta alglib:"
-        #p b
-        mle_alglib=Statsample::MLE::ln_mle(Statsample::MLE::Logit, @mat_x,@mat_y,b)
-#       puts "MLE Alglib:"
-        #p mle_alglib
-#        Statsample::CSV.write(ds,"test_binomial.csv")
+    @cases.times{|i|
+      a.push(2*rand()-i)
+      b.push(2*rand()-5+i)
+      c.push(2*rand()+i)
+      y_val=i+(rand()*@cases.quo(2) - @cases.quo(4))
+      y.push(y_val<(@cases/2.0) ? 0.0 : 1.0)
+    }
+    a=a.to_vector(:scale)
+    b=b.to_vector(:scale)
+    c=c.to_vector(:scale)
+    y=y.to_vector(:scale)
+
+    @ds_indep={'a'=>a,'b'=>b,'c'=>c}.to_dataset
+    constant=([1.0]*@cases).to_vector(:scale)
+    @ds_indep_2={'constant'=>constant,'a'=>a,'b'=>b,'c'=>c}.to_dataset
+    @ds_indep_2.fields=%w{constant a b c}
+    @mat_x=@ds_indep_2.to_matrix
+    @mat_y=y.to_matrix(:vertical)
+    @ds=@ds_indep.dup
+    @ds.add_vector('y',y)
+  end
+  def test_normal
+    y=Array.new()
+    y=@ds_indep.collect{|row|
+      row['a']*5+row['b']+row['c']+rand()*3
+    }
+    constant=([1]*@cases).to_vector(:scale)
+    ds_indep_2=@ds_indep.dup
+    ds_indep_2['constant']=constant
+    ds_indep_2.fields=%w{constant a b c}
+    mat_x=ds_indep_2.to_matrix
+    mat_y=y.to_matrix(:vertical)
+    mle=Statsample::MLE::Normal.new()
+    mle.verbose=false
+    coeffs_nr=mle.newton_raphson(mat_x,mat_y)
+    #p coeffs_nr
+    ds=@ds_indep.dup
+    ds.add_vector('y',y)
+    lr=Statsample::Regression.multiple(ds,'y')
+    lr_constant = lr.constant
+    lr_coeffs   = lr.coeffs
+    assert_in_delta(coeffs_nr[0,0], lr_constant,0.0000001)
+    assert_in_delta(coeffs_nr[1,0], lr_coeffs["a"],0.0000001)
+    assert_in_delta(coeffs_nr[2,0], lr_coeffs["b"],0.0000001)
+    assert_in_delta(coeffs_nr[3,0], lr_coeffs["c"],0.0000001)
+  end
 
+  def test_probit
+    ds=Statsample::CSV.read(@file_binomial)
+    constant=([1.0]*ds.cases).to_vector(:scale)
+    ds_indep={'constant'=>constant, 'a'=>ds['a'],'b'=>ds['b'], 'c'=>ds['c']}.to_dataset(%w{constant a b c})
+    mat_x=ds_indep.to_matrix
+    mat_y=ds['y'].to_matrix(:vertical)
+    mle=Statsample::MLE::Probit.new
+    b_probit=mle.newton_raphson(mat_x,mat_y)
+    ll=mle.log_likehood(mat_x,mat_y,b_probit)
 
+    b_exp=[-3.0670,0.1763,0.4483,-0.2240]
+    b_exp.each_index{|i|
+      assert_in_delta(b_exp[i], b_probit[i,0], 0.001)
+    }
+    assert_in_delta(-38.31559,ll,0.0001)
+  end
+  def test_logit_crime
+    ds=Statsample::PlainText.read(@crime, %w{crimerat maleteen south educ police60 police59 labor  males pop nonwhite unemp1  unemp2 median belowmed})
+    constant=([1.0]*ds.cases).to_vector(:scale)
+    ds2=ds.dup(%w{maleteen south educ police59})
+    ds2['constant']=constant
+    ds2.fields=%w{constant maleteen south educ police59}
+    mat_x=ds2.to_matrix
+    mat_y=(ds.compute "(crimerat>=110) ? 1:0").to_matrix(:vertical)
+    mle=Statsample::MLE::Logit.new
+    b=mle.newton_raphson(mat_x,mat_y)
+    ll=mle.log_likehood(mat_x,mat_y,b)
+    assert_in_delta(-18.606959,ll,0.001)
+    exp=[-17.701, 0.0833,-1.117, 0.0229, 0.0581]
+    exp.each_index{|i|
+      assert_in_delta(exp[i],b[i,0],0.001)
+    }
+    assert_equal(5,mle.iterations)
+  end
+  def atest_logit_alglib
+    if(HAS_ALGIB)
+      ds=Statsample::CSV.read(@file_binomial)
+      constant=([1.0]*ds.cases).to_vector(:scale)
 
-#        puts "iniciando newton"
-        coeffs_nr=Statsample::MLE.newton_raphson(@mat_x,@mat_y, Statsample::MLE::Logit)
-        #p coeffs_nr
-        mle_pure_ruby=Statsample::MLE::ln_mle(Statsample::MLE::Logit, @mat_x,@mat_y,coeffs_nr)
-        #p mle_pure_ruby
+      ds_indep={'constant'=>constant, 'a'=>ds['a'],'b'=>ds['b'], 'c'=>ds['c']}.to_dataset(%w{constant a b c} )
 
-        #puts "Malo: #{mle_malo} Bueno: #{mle_bueno} : #{mle_malo-mle_bueno}"
+      mat_x=ds_indep.to_matrix
+      mat_y=ds['y'].to_matrix(:vertical)
+      log=Alglib::Logit.build_from_matrix(ds.to_matrix)
+      coeffs=log.unpack[0]
+      b_alglib=Matrix.columns([[-coeffs[3], -coeffs[0], -coeffs[1], -coeffs[2]]])
+      mle=Statsample::MLE::Logit.new
+      ll_alglib=mle.log_likehood(mat_x,mat_y,b_alglib)
+      b_newton=mle.newton_raphson(mat_x,mat_y)
+      ll_pure_ruby=mle.log_likehood(mat_x,mat_y,b_newton)
+      #p b_alglib
+      #p b_newton
+
+      assert_in_delta(ll_alglib,ll_pure_ruby,1)
     end
+
+  end
+  def atest_logit1
+    log=Alglib::Logit.build_from_matrix(@ds.to_matrix)
+    coeffs=log.unpack[0]
+    b=Matrix.columns([[-coeffs[3],-coeffs[0],-coeffs[1],-coeffs[2]]])
+    #        puts "Coeficientes beta alglib:"
+    #p b
+    mle_alglib=Statsample::MLE::ln_mle(Statsample::MLE::Logit, @mat_x,@mat_y,b)
+    #       puts "MLE Alglib:"
+    #p mle_alglib
+    #        Statsample::CSV.write(ds,"test_binomial.csv")
+
+
+
+    #        puts "iniciando newton"
+    coeffs_nr=Statsample::MLE.newton_raphson(@mat_x,@mat_y, Statsample::MLE::Logit)
+    #p coeffs_nr
+    mle_pure_ruby=Statsample::MLE::ln_mle(Statsample::MLE::Logit, @mat_x,@mat_y,coeffs_nr)
+    #p mle_pure_ruby
+
+    #puts "Malo: #{mle_malo} Bueno: #{mle_bueno} : #{mle_malo-mle_bueno}"
+  end
 end
 

data/test/test_multiset.rb

@@ -1,98 +1,97 @@
-$:.unshift(File.dirname(__FILE__)+'/../lib/')
-require 'statsample'
-require 'test/unit'
+require(File.dirname(__FILE__)+'/test_helpers.rb')
 
-class StatsampleMultisetTestCase < Test::Unit::TestCase
-	def initialize(*args)
-		super
-	end
-    def test_creation
-        v1a=[1,2,3,4,5].to_vector
-        v2b=[11,21,31,41,51].to_vector
-        v3c=[21,23,34,45,56].to_vector
-        ds1={'v1'=>v1a,'v2'=>v2b,'v3'=>v3c}.to_dataset
-        v1b=[15,25,35,45,55].to_vector
-        v2b=[11,21,31,41,51].to_vector
-        v3b=[21,23,34,45,56].to_vector
-        ds2={'v1'=>v1b,'v2'=>v2b,'v3'=>v3b}.to_dataset
-        ms=Statsample::Multiset.new(['v1','v2','v3'])
-        ms.add_dataset('ds1',ds1)
-        ms.add_dataset('ds2',ds2)
-        assert_equal(ds1,ms['ds1'])
-        assert_equal(ds2,ms['ds2'])
-        assert_equal(v1a,ms['ds1']['v1'])
-        assert_not_equal(v1b,ms['ds1']['v1'])
-        ds3={'v1'=>v1b,'v2'=>v2b}.to_dataset
-        assert_raise ArgumentError do
-			ms.add_dataset(ds3)
-		end
-    end
-    def test_creation_empty
-        ms=Statsample::Multiset.new_empty_vectors(%w{id age name},%w{male female})
-        ds_male={'id'=>[].to_vector,'age'=>[].to_vector, 'name'=>[].to_vector}.to_dataset(%w{id age name})
-        ds_female={'id'=>[].to_vector,'age'=>[].to_vector, 'name'=>[].to_vector}.to_dataset(%w{id age name})
-        ms2=Statsample::Multiset.new(%w{id age name})
-        ms2.add_dataset('male',ds_male)
-        ms2.add_dataset('female',ds_female)
-        assert_equal(ms2.fields,ms.fields)
-        assert_equal(ms2['male'],ms['male'])
-        assert_equal(ms2['female'],ms['female'])        
-    end
-    def test_to_multiset_by_split_one
-        sex=%w{m m m m m f f f f m}.to_vector(:nominal)
-        city=%w{London Paris NY London Paris NY London Paris NY Tome}.to_vector(:nominal)
-        age=[10,10,20,30,34,34,33,35,36,40].to_vector(:scale)
-        ds={'sex'=>sex,'city'=>city,'age'=>age}.to_dataset
-        ms=ds.to_multiset_by_split('sex')
-        assert_equal(2,ms.n_datasets)
-        assert_equal(%w{f m},ms.datasets.keys.sort)
-        assert_equal(6,ms['m'].cases)
-        assert_equal(4,ms['f'].cases)
-        assert_equal(%w{London Paris NY London Paris Tome},ms['m']['city'].to_a)
-        assert_equal([34,33,35,36],ms['f']['age'].to_a)        
-    end
-    def test_to_multiset_by_split_multiple
-        sex=%w{m m m m m m m m m m f f f f f f f f f f}.to_vector(:nominal)
-        city=%w{London London London Paris Paris London London London Paris Paris London London London Paris Paris London London London Paris Paris}.to_vector(:nominal)
-		hair=%w{blonde blonde black black blonde blonde black black blonde blonde black black blonde blonde black black blonde blonde black black}.to_vector(:nominal)
-        age=[10,10,20,30,34,34,33,35,36,40, 10,10,20,30,34,34,33,35,36,40].to_vector(:scale)
-        ds={'sex'=>sex,'city'=>city,'hair'=>hair,'age'=>age}.to_dataset(%w{sex city hair age})
-        ms=ds.to_multiset_by_split('sex','city','hair')
-        assert_equal(8,ms.n_datasets)
-		assert_equal(3,ms[%w{m London blonde}].cases)
-		assert_equal(3,ms[%w{m London blonde}].cases)
-		assert_equal(1,ms[%w{m Paris black}].cases)		
-    end
-	
-    def test_stratum_proportion
-        ds1={'q1'=>[1,1,1,1,1,0,0,0,0,0,0,0].to_vector}.to_dataset
-        ds2={'q1'=>[1,1,1,1,1,1,1,0,0].to_vector}.to_dataset
-        assert_equal(5.0/12, ds1['q1'].proportion )
-        assert_equal(7.0/9, ds2['q1'].proportion )
-        ms=Statsample::Multiset.new(['q1'])
-        ms.add_dataset('d1',ds1)
-        ms.add_dataset('d2',ds2)
-        ss=Statsample::StratifiedSample.new(ms,{'d1'=>50,'d2'=>100})
-        assert_in_delta(0.655, ss.proportion('q1'),0.01)
-        assert_in_delta(0.345, ss.proportion('q1',0),0.01)        
-        
-    end
-    def test_stratum_scale
-        boys={'test'=>[50, 55, 60, 62, 62, 65, 67, 67, 70, 70, 73, 73, 75, 78, 78, 80, 85, 90].to_vector(:scale)}.to_dataset
-        girls={'test'=>[70, 70, 72, 72, 75, 75, 78, 78, 80, 80, 82, 82, 85, 85, 88, 88, 90, 90].to_vector(:scale)}.to_dataset
-        ms=Statsample::Multiset.new(['test'])
-        ms.add_dataset('boys',boys)
-        ms.add_dataset('girls',girls)
-        ss=Statsample::StratifiedSample.new(ms,{'boys'=>10000,'girls'=>10000})
-        assert_equal(2,ss.strata_number)
-        assert_equal(20000,ss.population_size)
-        assert_equal(10000,ss.stratum_size('boys'))
-        assert_equal(10000,ss.stratum_size('girls'))
-        assert_equal(36,ss.sample_size)
-        assert_equal(75,ss.mean('test'))
-        assert_in_delta(1.45,ss.standard_error_wor('test'),0.01)
-        assert_in_delta(ss.standard_error_wor('test'), ss.standard_error_wor_2('test'),0.00001)
-        
-        
+
+class StatsampleMultisetTestCase < MiniTest::Unit::TestCase
+  def initialize(*args)
+    super
+  end
+  def test_creation
+    v1a=[1,2,3,4,5].to_vector
+    v2b=[11,21,31,41,51].to_vector
+    v3c=[21,23,34,45,56].to_vector
+    ds1={'v1'=>v1a,'v2'=>v2b,'v3'=>v3c}.to_dataset
+    v1b=[15,25,35,45,55].to_vector
+    v2b=[11,21,31,41,51].to_vector
+    v3b=[21,23,34,45,56].to_vector
+    ds2={'v1'=>v1b,'v2'=>v2b,'v3'=>v3b}.to_dataset
+    ms=Statsample::Multiset.new(['v1','v2','v3'])
+    ms.add_dataset('ds1',ds1)
+    ms.add_dataset('ds2',ds2)
+    assert_equal(ds1,ms['ds1'])
+    assert_equal(ds2,ms['ds2'])
+    assert_equal(v1a,ms['ds1']['v1'])
+    assert_not_equal(v1b,ms['ds1']['v1'])
+    ds3={'v1'=>v1b,'v2'=>v2b}.to_dataset
+    assert_raise ArgumentError do
+      ms.add_dataset(ds3)
     end
-end
+  end
+  def test_creation_empty
+    ms=Statsample::Multiset.new_empty_vectors(%w{id age name},%w{male female})
+    ds_male={'id'=>[].to_vector,'age'=>[].to_vector, 'name'=>[].to_vector}.to_dataset(%w{id age name})
+    ds_female={'id'=>[].to_vector,'age'=>[].to_vector, 'name'=>[].to_vector}.to_dataset(%w{id age name})
+    ms2=Statsample::Multiset.new(%w{id age name})
+    ms2.add_dataset('male',ds_male)
+    ms2.add_dataset('female',ds_female)
+    assert_equal(ms2.fields,ms.fields)
+    assert_equal(ms2['male'],ms['male'])
+    assert_equal(ms2['female'],ms['female'])
+  end
+  def test_to_multiset_by_split_one
+    sex=%w{m m m m m f f f f m}.to_vector(:nominal)
+    city=%w{London Paris NY London Paris NY London Paris NY Tome}.to_vector(:nominal)
+    age=[10,10,20,30,34,34,33,35,36,40].to_vector(:scale)
+    ds={'sex'=>sex,'city'=>city,'age'=>age}.to_dataset
+    ms=ds.to_multiset_by_split('sex')
+    assert_equal(2,ms.n_datasets)
+    assert_equal(%w{f m},ms.datasets.keys.sort)
+    assert_equal(6,ms['m'].cases)
+    assert_equal(4,ms['f'].cases)
+    assert_equal(%w{London Paris NY London Paris Tome},ms['m']['city'].to_a)
+    assert_equal([34,33,35,36],ms['f']['age'].to_a)
+  end
+  def test_to_multiset_by_split_multiple
+    sex=%w{m m m m m m m m m m f f f f f f f f f f}.to_vector(:nominal)
+    city=%w{London London London Paris Paris London London London Paris Paris London London London Paris Paris London London London Paris Paris}.to_vector(:nominal)
+    hair=%w{blonde blonde black black blonde blonde black black blonde blonde black black blonde blonde black black blonde blonde black black}.to_vector(:nominal)
+    age=[10,10,20,30,34,34,33,35,36,40, 10,10,20,30,34,34,33,35,36,40].to_vector(:scale)
+    ds={'sex'=>sex,'city'=>city,'hair'=>hair,'age'=>age}.to_dataset(%w{sex city hair age})
+    ms=ds.to_multiset_by_split('sex','city','hair')
+    assert_equal(8,ms.n_datasets)
+    assert_equal(3,ms[%w{m London blonde}].cases)
+    assert_equal(3,ms[%w{m London blonde}].cases)
+    assert_equal(1,ms[%w{m Paris black}].cases)
+  end
+
+  def test_stratum_proportion
+    ds1={'q1'=>[1,1,1,1,1,0,0,0,0,0,0,0].to_vector}.to_dataset
+    ds2={'q1'=>[1,1,1,1,1,1,1,0,0].to_vector}.to_dataset
+    assert_equal(5.0/12, ds1['q1'].proportion )
+    assert_equal(7.0/9, ds2['q1'].proportion )
+    ms=Statsample::Multiset.new(['q1'])
+    ms.add_dataset('d1',ds1)
+    ms.add_dataset('d2',ds2)
+    ss=Statsample::StratifiedSample.new(ms,{'d1'=>50,'d2'=>100})
+    assert_in_delta(0.655, ss.proportion('q1'),0.01)
+    assert_in_delta(0.345, ss.proportion('q1',0),0.01)
+
+  end
+  def test_stratum_scale
+    boys={'test'=>[50, 55, 60, 62, 62, 65, 67, 67, 70, 70, 73, 73, 75, 78, 78, 80, 85, 90].to_vector(:scale)}.to_dataset
+    girls={'test'=>[70, 70, 72, 72, 75, 75, 78, 78, 80, 80, 82, 82, 85, 85, 88, 88, 90, 90].to_vector(:scale)}.to_dataset
+    ms=Statsample::Multiset.new(['test'])
+    ms.add_dataset('boys',boys)
+    ms.add_dataset('girls',girls)
+    ss=Statsample::StratifiedSample.new(ms,{'boys'=>10000,'girls'=>10000})
+    assert_equal(2,ss.strata_number)
+    assert_equal(20000,ss.population_size)
+    assert_equal(10000,ss.stratum_size('boys'))
+    assert_equal(10000,ss.stratum_size('girls'))
+    assert_equal(36,ss.sample_size)
+    assert_equal(75,ss.mean('test'))
+    assert_in_delta(1.45,ss.standard_error_wor('test'),0.01)
+    assert_in_delta(ss.standard_error_wor('test'), ss.standard_error_wor_2('test'),0.00001)
+
+
+  end
+end