statsample-ekatena 2.0.2

data/benchmarks/factor_map.rb

@@ -0,0 +1,37 @@
+require(File.expand_path(File.dirname(__FILE__)+'/helpers_benchmark.rb'))
+
+extend BenchPress
+
+
+name "Statsample::Factor::Map with and without GSL"
+author 'Clbustos'
+date '2011-01-18'
+summary "Velicer's MAP uses a lot of Matrix algebra. How much we can improve the timing using GSL?
+"
+
+reps 20 #number of repetitions
+
+m=Matrix[ 
+        [ 1, 0.846, 0.805, 0.859, 0.473, 0.398, 0.301, 0.382],
+        [ 0.846, 1, 0.881, 0.826, 0.376, 0.326, 0.277, 0.415],
+        [ 0.805, 0.881, 1, 0.801, 0.38, 0.319, 0.237, 0.345],
+        [ 0.859, 0.826, 0.801, 1, 0.436, 0.329, 0.327, 0.365],
+        [ 0.473, 0.376, 0.38, 0.436, 1, 0.762, 0.73, 0.629],
+        [ 0.398, 0.326, 0.319, 0.329, 0.762, 1, 0.583, 0.577],
+        [ 0.301, 0.277, 0.237, 0.327, 0.73, 0.583, 1, 0.539],
+        [ 0.382, 0.415, 0.345, 0.365, 0.629, 0.577, 0.539, 1]
+  ]
+  
+map=Statsample::Factor::MAP.new(m)
+
+
+measure "Statsample::Factor::MAP without GSL" do
+  map.use_gsl=false
+  map.compute
+end
+
+measure "Statsample::Factor::MAP with GSL" do
+  map.use_gsl=true
+  map.compute
+end
+

data/benchmarks/helpers_benchmark.rb

@@ -0,0 +1,5 @@
+$:.unshift(File.expand_path(File.dirname(__FILE__)+'/../lib/'))
+$:.unshift(File.expand_path(File.dirname(__FILE__)+'/'))
+
+require 'statsample'
+require 'bench_press'

data/doc_latex/manual/equations.tex

@@ -0,0 +1,78 @@
+\part{Equations}
+\section{Convention}
+\begin{align*}
+n &= \text{sample size}\\
+N &= \text{population size}\\
+p &= \text{proportion inside a sample}\\
+P &= \text{proportion inside a population}
+\end{align*}
+\section{Ruby::Regression::Multiple}
+
+To compute the standard error of coefficients, you obtain the estimated variance-covariance matrix of error.
+
+Let \mathbf{X} be matrix of predictors data, including a constant column; \mathbf{MSE} as mean square error; SSE as Sum of squares of errors; n the number of cases; p as number of predictors
+
+\begin{equation}
+\mathbf{MSE}=\frac{SSE}{n-p-1}
+\end{equation}
+
+\begin{equation}
+\mathbf{E}=(\mathbf{X'}\mathbf{X})^-1\mathbf{MSE}
+\end{equation}
+
+The root squares of diagonal should be standard errors
+
+
+\section{Ruby::SRS}
+Finite Poblation correction is used on standard error calculation on poblation below 10.000. Function 
+\begin{verbatim}
+fpc_var(sam,pop)
+\end{verbatim}
+calculate FPC for variance with
+\begin{equation}
+fpc_{var} = \frac{N-n} {N-1}
+\end{equation}
+
+with n  as sam and N as pop
+
+Function 
+\begin{verbatim}
+fpc = fpc(sam,pop)
+\end{verbatim}
+
+calculate FPC for standard deviation with 
+\begin{equation}
+fpc_{sd} = \sqrt{\frac{N-n} {N-1}}
+\label{fpc}
+\end{equation}
+with n  as sample size and N as population size.
+
+\subsection{Sample Size estimation for proportions}
+
+On infinite poblations, you should use method
+\begin{verbatim}
+estimation_n0(d,prop,margin=0.95)
+\end{verbatim}
+which uses
+\begin{equation}
+n = \frac{t^2(pq)}{d^2}
+\label{n_i}
+\end{equation}
+where
+\begin{align*}
+t &= \text{t value for given level of confidence ( 1.96 for 95\% )}\\
+d &= \text{margin of error}
+\end{align*}
+
+On finite poblations, you should use
+\begin{verbatim}
+estimation_n(d,prop,n_pobl, margin=0.95)
+\end{verbatim}
+which uses
+\begin{equation}
+n = \frac{n_i}{1+(\frac{n_i-1}{N})}
+\end{equation}
+
+Where $n_i$ is n on \ref{n_i} and N is population size
+
+

data/examples/boxplot.rb

@@ -0,0 +1,28 @@
+#!/usr/bin/ruby
+# == Description
+# 
+# This example illustrates how daru, combined with Statsample::Graph::Boxplot
+# can be used for generating box plots of a normally distributed set of data.
+# 
+# The 'rnorm' function, defined in statsample/shorthands generates a Daru::Vector
+# object which contains the specified number of random variables in a normal distribution.
+# It uses the 'distribution' gem for this purpose.
+# 
+# Create a boxplot of the data by specifying the vectors a, b and c and providing 
+# necessary options to Statsample::Graph::Boxplot. The 'boxplot' function is shorthand
+# for calling Statsample::Graph::Boxplot.
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
+Statsample::Analysis.store(Statsample::Graph::Boxplot) do 
+  n = 30
+  a = rnorm(n-1,50,10)
+  b = rnorm(n, 30,5)
+  c = rnorm(n,5,1)
+  a.push(2)
+
+  boxplot(:vectors=>[a,b,c],:width=>300, :height=>300, :groups=>%w{first first second}, :minimum=>0)
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run
+end

data/examples/chisquare_test.rb

@@ -0,0 +1,23 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib')
+require 'statsample'
+
+Statsample::Analysis.store(Statsample::Test::ChiSquare) do
+  # Collect the two vectors with the categorical data (raw number of occurences) into one matrix. Here
+  #--------------------------------------------
+  #| category | observation 1 | observation 2 |
+  #|------------------------------------------|
+  #|    A     |      100      |      20       |
+  #|    B     |      50       |      70       |
+  #|    C     |      30       |      100      |
+  #|------------------------------------------|
+  #
+  m=Matrix[[100, 50, 30],[20, 70, 100]]
+  x_2=Statsample::Test.chi_square(m)
+  # after the test is done, look at the p-value.
+  puts x_2.probability
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end

data/examples/correlation_matrix.rb

@@ -0,0 +1,32 @@
+#!/usr/bin/ruby
+
+# == Description
+# 
+# Creating and summarizing a correlation matrix with daru and statsample
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+require 'statsample'
+Statsample::Analysis.store("Statsample::Bivariate.correlation_matrix") do
+  # Create a Daru::DataFrame containing 4 vectors a, b, c and d.
+  #
+  # Notice that the `clone` option has been set to *false*. This tells Daru
+  # to not clone the Daru::Vectors being supplied by `rnorm`, since it would
+  # be unnecessarily counter productive to clone the vectors once they have
+  # been assigned to the dataframe.
+  samples=1000
+  ds = Daru::DataFrame.new({
+    :a => rnorm(samples),
+    :b => rnorm(samples),
+    :c => rnorm(samples),
+    :d => rnorm(samples)
+  }, clone: false)
+
+  # Calculate correlation matrix by calling the `cor` shorthand.
+  cm = cor(ds)
+  summary(cm)
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end
+

data/examples/dataset.rb

@@ -0,0 +1,30 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+# == Description
+#
+# This example demonstrates creation of basic Vectors and DataFrames.
+require 'statsample'
+
+Statsample::Analysis.store(Daru::DataFrame) do
+  samples = 1000
+
+  # The 'new_with_size' function lets you specify the size of the 
+  # vector as the argument and the block specifies how each element
+  # of the vector will be created.
+  a = Daru::Vector.new_with_size(samples) {r=rand(5); r==4 ? nil: r}
+  b = Daru::Vector.new_with_size(samples) {r=rand(5); r==4 ? nil: r}
+
+  # Pass the Daru::Vector objects in a Hash to the DataFrame constructor
+  # to make a DataFrame.
+  # 
+  # The *order* option lets you specify the way the vectors in the Hash 
+  # will be ordered. Not specifyin this will order vectors in alphabetical
+  # order by default.
+  ds = Daru::DataFrame.new({:a=>a,:b=>b}, order: [:b, :a])
+  summary(ds)
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end
+

data/examples/dominance_analysis.rb

@@ -0,0 +1,33 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+# == Description
+#
+# Dominance Analysis with statsample
+require 'statsample'
+Statsample::Analysis.store(Statsample::DominanceAnalysis) do
+  sample=300
+  a=rnorm(sample)
+  b=rnorm(sample)
+  c=rnorm(sample)
+  d=rnorm(sample)
+  
+  ds = Daru::DataFrame.new({:a => a,:b => b,:cc => c,:d => d}, clone: false)
+  attach(ds)
+  ds[:y]=a*5 + b*3 + cc*2 + d + rnorm(300)
+  cm=cor(ds)
+  summary(cm)
+  lr=lr(ds,:y)
+  summary(lr)
+  da=dominance_analysis(ds,:y)
+  summary(da)
+  
+  da = dominance_analysis(ds,:y,:name=>"Dominance Analysis using group of predictors", :predictors=>[:a, :b, [:cc, :d]])
+  summary(da)
+end
+
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end
+

data/examples/dominance_analysis_bootstrap.rb

@@ -0,0 +1,32 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+require 'statsample'
+
+Statsample::Analysis.store(Statsample::DominanceAnalysis::Bootstrap) do
+  sample=300
+  a=rnorm(sample)
+  b=rnorm(sample)
+  c=rnorm(sample)
+  d=rnorm(sample)  
+  a.rename :a
+  b.rename :b
+  c.rename :c
+  d.rename :d
+  
+  ds = Daru::DataFrame.new({:a => a,:b => b,:cc => c,:d => d})
+  attach(ds)
+  ds[:y1] = a*5  + b*2 + cc*2 + d*2 + rnorm(sample,0,10)
+  ds[:y2] = a*10 + rnorm(sample)
+  
+  dab=dominance_analysis_bootstrap(ds, [:y1,:y2], :debug=>true)
+  dab.bootstrap(100,nil)
+  summary(dab)
+  ds2=ds[:a..:y1]
+  dab2=dominance_analysis_bootstrap(ds2, :y1, :debug=>true)
+  dab2.bootstrap(100,nil)
+  summary(dab2)
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end

data/examples/histogram.rb

@@ -0,0 +1,26 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+# == Description
+# 
+# This example demonstrates how a histogram can be created 
+# with statsample.
+# 
+# The 'histogram' function creates a histogram by using the 
+# Statsample::Graph::Histogram class. This class accepts data 
+# in a Daru::Vector (as created by `rnorm`).
+# 
+# A line showing normal distribution can be drawn by setting 
+# the `:line_normal_distribution` option to *true*.
+# 
+# See this notebook for an illustration: 
+# http://nbviewer.ipython.org/github/SciRuby/sciruby-notebooks/blob/master/statistics/Creating%20a%20Histogram.ipynb
+require 'statsample'
+
+Statsample::Analysis.store(Statsample::Graph::Histogram) do
+  histogram(rnorm(3000,0,20), :line_normal_distribution => true)
+end
+
+if __FILE__==$0
+   Statsample::Analysis.run
+end

data/examples/icc.rb

@@ -0,0 +1,24 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+require 'statsample'
+
+Statsample::Analysis.store(Statsample::Reliability::ICC) do
+
+  size=1000
+  a = Daru::Vector.new_with_size(size) {rand(10)}
+  b = a.recode{|i|i+rand(4)-2}
+  c = a.recode{|i|i+rand(4)-2}
+  d = a.recode{|i|i+rand(4)-2}
+  @ds = Daru::DataFrame.new({:a => a,:b => b,:c => c,:d => d})
+  @icc=Statsample::Reliability::ICC.new(@ds)
+  summary(@icc)
+  @icc.type=:icc_3_1
+  summary(@icc)
+  @icc.type=:icc_a_k
+  summary(@icc)
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end

data/examples/levene.rb

@@ -0,0 +1,29 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+# == Description
+# 
+# This example demonstrates how a levene test can be performed by
+# using Daru::Vector and the Statsample::Test::Levene class.
+# 
+# Levene's test is an inferential statistic used to assess the
+# equality of variances for a variable calculated for two or more groups.
+# 
+# == References
+# 
+# http://en.wikipedia.org/wiki/Levene%27s_test
+require 'statsample'
+
+Statsample::Analysis.store(Statsample::Test::Levene) do
+
+  a = Daru::Vector.new([1,2,3,4,5,6,7,8,100,10])
+  b = Daru::Vector.new([30,40,50,60,70,80,90,100,110,120])
+
+  # The 'levene' function is used as a shorthand 
+  # for creating a Statsample::Test::Levene object.
+  summary(levene([a,b]))
+end
+
+if __FILE__==$0
+  Statsample::Analysis.run_batch
+end

data/examples/multiple_regression.rb

@@ -0,0 +1,20 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+# == Description
+# 
+# This example shows how multiple regression can be performed using statsample and daru.
+require 'statsample'
+
+Statsample::Analysis.store(Statsample::Regression::Multiple) do
+
+  samples=2000
+  ds=dataset(:a => rnorm(samples),:b => rnorm(samples),:cc => rnorm(samples),:d => rnorm(samples))
+  attach(ds)
+  ds[:y] = a*5+b*3+cc*2+d+rnorm(samples)
+  summary lr(ds,:y)
+end
+
+if __FILE__==$0
+   Statsample::Analysis.run_batch
+end

data/examples/multivariate_correlation.rb

@@ -0,0 +1,33 @@
+#!/usr/bin/ruby
+$:.unshift(File.dirname(__FILE__)+'/../lib/')
+
+require 'statsample'
+require 'mathn'
+
+
+Statsample::Analysis.store(Statsample::Regression::Multiple::MultipleDependent) do
+  
+  complete=Matrix[
+  [1,0.53,0.62,0.19,-0.09,0.08,0.02,-0.12,0.08],
+  [0.53,1,0.61,0.23,0.1,0.18,0.02,-0.1,0.15],
+  [0.62,0.61,1,0.03,0.1,0.12,0.03,-0.06,0.12],
+  [0.19,0.23,0.03,1,-0.02,0.02,0,-0.02,-0.02],
+  [-0.09,0.1,0.1,-0.02,1,0.05,0.06,0.18,0.02],
+  [0.08,0.18,0.12,0.02,0.05,1,0.22,-0.07,0.36],
+  [0.02,0.02,0.03,0,0.06,0.22,1,-0.01,-0.05],
+  [-0.12,-0.1,-0.06,-0.02,0.18,-0.07,-0.01,1,-0.03],
+  [0.08,0.15,0.12,-0.02,0.02,0.36,-0.05,-0.03,1]]
+  
+  complete.extend Statsample::CovariateMatrix
+  complete.fields=%w{adhd cd odd sex age monly mwork mage poverty}
+  
+  lr=Statsample::Regression::Multiple::MultipleDependent.new(complete, %w{adhd cd odd})
+  
+  echo "R^2_yx #{lr.r2yx}"
+  echo "P^2_yx #{lr.p2yx}"
+end
+
+
+if __FILE__==$0
+   Statsample::Analysis.run_batch
+end