Merge pull request #95 from marikap00/master

fixed some typos.

toolbox/multivariate/barnardtest.m

@@ -14,7 +14,7 @@
 %
 %       N    :    Contingency table (default) or n-by-2 input dataset.
 %                 Matrix or Table.
-%                 Matrix or table which contains the input contingency
+%                 Matrix or table that contains the input contingency
 %                 table (say of size I-by-J) or the original data matrix.
 %                 In this last case N=crosstab(N(:,1),N(:,2)). As default
 %                 procedure assumes that the input is a contingency table.
@@ -23,17 +23,17 @@
 %
 %   resolution: The resolution of the search space for the nuisance
 %               parameter.
-%               Scalar. Small number which defines the resolution. See the
-%               More About section for more details.
+%               Scalar. Small number that defines the resolution. See the
+%               "More About" section for more details.
 %               The default value of the resolution is 0.001.
 %               Example - 'resolution',0.01
 %               Data Types - single | double
 %
-% datamatrix :  Data matrix or contingency table. Boolean.
-%               If datamatrix is true the first input argument N is forced
-%               to be interpreted as a data matrix, else if the input
-%               argument is false N is treated as a contingency table. The
-%               default value of datamatrix is false, that is the procedure
+%   datamatrix: Data matrix or contingency table. Boolean.
+%               If datamatrix is true, the first input argument N is forced
+%               to be interpreted as a data matrix; otherwise if the input
+%               argument is false, N is treated as a contingency table. The
+%               default value of datamatrix is false; that is, the procedure
 %               automatically considers N as a contingency table.
 %               Example - 'datamatrix',true
 %               Data Types - logical
@@ -42,7 +42,7 @@
 %  Output:
 %
 %         pval:  p-value of the test. Scalar.
-%                pval is the p-value, i.e. the probability of
+%                pval is the p-value, i.e., represents the probability of
 %                observing the given result, or one more extreme, by
 %                chance if the null hypothesis of independence between
 %                rows and columns is true. Small values of pval cast doubt
@@ -70,7 +70,7 @@
 %
 % Barnard's test considers all tables with category sizes $c_1$ and $c_2$ for a
 % given $p$. The p-value is the sum of probabilities of the tables having a
-% score in the rejection region, e.g. having significantly large difference
+% score in the rejection region, e.g., having a significantly large difference
 % in proportions for a two-sided test. The p-value of the test is the
 % maximum p-value calculated over all $p$ between 0 and 1. The input
 % resolution parameter controls the resolution to search for.
@@ -123,19 +123,19 @@
 
 %{
     %%  Barnard test with all the default options.
-    % N= 2x2 Input contingency table
+    % N= 2x2 Input contingency table.
     N=[8,14; 1,3];
     pval=barnardtest(N);
     disp(['The p-value of the test is: ' num2str(pval)])
 %}
 
 %{
     %%  Resolution option.
-    % N= 2x2 Input contingency table
+    % N= 2x2 Input contingency table.
     N=[20,14; 10,13];
-    % pvalue with the default resolution (0.001)
+    % p-value with the default resolution (0.001).
     pval001=barnardtest(N);
-    % p value with a resolution of 0.01
+    % p-value with a resolution of 0.01.
     pval01=barnardtest(N,'resolution',0.01);
     disp(['The p-value with a resolution 0.01 is: ' num2str(pval01)])
     disp(['The p-value a resolution 0.001 is: ' num2str(pval001)])
@@ -158,9 +158,9 @@
 %{
     % An example when the input is a datamatrix.
     N=[40,14;10,30];
-    % Recreate the orginal data matrix
+    % Recreate the original data matrix.
     X=crosstab2datamatrix(N);
-    % barnardtest when input is a datamatrix
+    % barnardtest when input is a datamatrix.
     pval=barnardtest(X,'datamatrix',true);
 %}
 
@@ -171,20 +171,20 @@
     pval=barnardtest(N);
     % our p-value is 0.456054
     % This value coincides with the R implementation (package barnard)
-    % based on a C routine. On the other hand the vectorized implementation
-    % of Barnard test http://www.mathworks.com/matlabcentral/fileexchange/25760
-    % called using mybarnard(N,1000) gives a p-value of   0.456051 
+    % based on a C routine. On the other hand, the vectorized implementation
+    % of the Barnard test http://www.mathworks.com/matlabcentral/fileexchange/25760
+    % called using mybarnard(N,1000) gives a p-value of 0.456051.
 %}
 
 
 %% Beginning of code
 
 % Check MATLAB version. If it is not smaller than 2013b than output is
-% shown in table format
+% shown in table format.
 verMatlab=verLessThan('matlab','8.2.0');
 
 % Check whether N is a contingency table or a n-by-p input dataset (in this
-% last case the contingency table is built using the first two columns of the
+% last case, the contingency table is built using the first two columns of the
 % input dataset).
 if ~isempty(varargin)
     [varargin{:}] = convertStringsToChars(varargin{:});
@@ -200,12 +200,12 @@
 end
 
 % If input is a datamatrix it is necessary to construct the contingency
-% table
+% table.
 if datamatrix == true
     N =crosstab(N(:,1),N(:,2));
 end
 
-% 1. The deafault resolution of the search space.
+% 1. The default resolution of the search space.
 resolution=0.001;
 
 [varargin{:}] = convertStringsToChars(varargin{:});
@@ -216,15 +216,15 @@
 
     UserOptions=varargin(1:2:length(varargin));
     if ~isempty(UserOptions)
-        % Check if number of supplied options is valid
+        % Check if number of supplied options is valid.
         if length(varargin) ~= 2*length(UserOptions)
             error('FSDA:barnardtest:WrongInputOpt','Number of supplied options is invalid. Probably values for some parameters are missing.');
         end
-        % Check if user options are valid options
+        % Check if user options are valid options.
         aux.chkoptions(options,UserOptions)
     end
 
-    % Write in structure 'options' the options chosen by the user
+    % Write in structure 'options' the options chosen by the user.
     if nargin > 2
         for i=1:2:length(varargin)
             options.(varargin{i})=varargin{i+1};
@@ -233,7 +233,7 @@
     resolution=options.resolution;
 end
 
-% transform table in array
+% transform table in array.
 if verMatlab ==0 && istable(N)
     N=table2array(N);
 end
@@ -304,7 +304,7 @@
 
     for i = 0:c1
 
-        % The loop below is replaced by a series of vectorized instructions
+        % The loop below is replaced by a series of vectorized instructions.
         %         for j = 0:c2
         %             if p>0
         %                 S(rI) = exp(F1(end)-F1(end-i)-F1(i+1)+ F2(end)-F2(end-j)-F2(j+1) +(i+j)*log(p)+(C-(i+j))*log(1-p));

toolbox/multivariate/biplotFS.m

@@ -1,5 +1,5 @@
 function biplotFS(Y,varargin)
-%biplotFS calls biplotAPP.mlapp to show a dynamic biplot
+%biplotFS calls biplotAPP.mlapp to show a dynamic biplot.
 %
 %<a href="matlab: docsearchFS('biplotFS')">Link to the help function</a>
 % 
@@ -13,8 +13,8 @@ function biplotFS(Y,varargin)
 % \]
 % where $U_{(2)}$ is $n \times 2$ matrix (first two columns of $U$)  
 % and $V_{(2)}$ is $p \times 2$  (first two columns of matrix $V$,
-% $\Gamma_{(2)}^*$ is a $2 \times 2$ diagonal matrix 
-% which contains the frist two largest singular values of matrix $Z$ 
+% $\Gamma_{(2)}^*$ is a $2 \times 2$ diagonal matrix, 
+% which contains the first two largest singular values of matrix $Z$ 
 % (square root of the eigenvalues of matrix $Z^TZ=(n-1)R$) where $R$ is the
 % correlation matrix.
 %
@@ -53,7 +53,7 @@ function biplotFS(Y,varargin)
 % \[
 % \sqrt{n-1} U_{(2)}= Z  V_{(2)} \Gamma_{(2)}^{-1}
 % \]
-% that is row points are the standardized principal components scores.
+% that is, row points are the standardized principal components scores.
 % \[
 % cov (\sqrt{n-1} U_{(2)}) = I_2= \left(
 %                                   \begin{array}{cc}
@@ -66,10 +66,10 @@ function biplotFS(Y,varargin)
 % \[
 %  \Gamma_{(2)}  V_{(2)}^T
 % \]
-%  that is the arrows are associated with the correlations between the
-%  variables and the first two principal components
-%  The length of the arrow is exactly equal to the communality of the asoociated variable.
-%  In this case the unit circle is also shown on the screen and option axis
+%  that is, the arrows are associated with the correlations between the
+%  variables and the first two principal components.
+%  The length of the arrow is exactly equal to the communality of the associated variable.
+%  In this case, the unit circle is also shown on the screen and option axis
 %  equal is set.
 %
 % On the other hand, if $\omega=1$ and $\alpha=1$
@@ -78,7 +78,7 @@ function biplotFS(Y,varargin)
 % \[
 % \sqrt{n-1} U_{(2)} \Gamma_{(2)} = Z  V_{(2)}
 % \]
-% In this case the row points are the (non normalized) scores, that is 
+% In this case, the row points are the (non normalized) scores, that is 
 %  \[
 % cov(\sqrt{n-1} U_{(2)} \Gamma_{(2)})  =cov( Z  V_{(2)})= \left(
 %                                   \begin{array}{cc}
@@ -92,10 +92,10 @@ function biplotFS(Y,varargin)
 %  \[
 % V_{(2)}^T 
 %  \]
-% Also in this case the unit circle is given and option axis equal is set. 
+% Also in this case, the unit circle is given and option axis equal is set. 
 % 
 % In general if $\omega$ decreases, the length of the arrows increases
-% and the coordinates of row points are squeezed towards the origin
+% and the coordinates of row points are squeezed towards the origin.
 %
 % In the app it is also possible to color row points depending on the
 % orthogonal distance ($OD_i$) of each observation to the PCA subspace.
@@ -107,9 +107,9 @@ function biplotFS(Y,varargin)
 % OD_i=|| z_i- V_{(2)} V_{(2)}' z_i ||
 % \]
 %
-% If optional input argument bsb or bdp is specified it is possible to have
-% in the app two tabs which enable the user to select the breakdown point
-% of the analysis of the subset size to use in the svd. The units which are
+% If an optional input argument, bsb or bdp, is specified, it is possible to have
+% in the app two tabs that enable the user to select the breakdown point
+% of the analysis of the subset size to use in the svd. The units that are
 % declared as outliers or the units outside the subset are shown in the
 % plot with filled circles.
 %
@@ -127,70 +127,70 @@ function biplotFS(Y,varargin)
 %
 %  Optional input arguments:
 %
-%      bsb       : units forming subset on which to perform PCA. vector.
-%                  Vector containing the list of the untis to use to
-%                  compute the svd. The other units are projected in the
-%                  space of the first two PC. bsb can be either a numeric
-%                  vector of length m (m<=n) containin the list of the
-%                  units (e.g. 1:50) or a logical vector of length n
-%                  containing the true for the units which have to be used
-%                  in the calculation of svd. For example bsb=true(n,1),
-%                  bsb(13)=false; excludes from the svd unit number 13.
-%                  Note that if bsb is supplied bdp must be empty.
-%                 Example - 'bsb',[2 10:90 93]
-%                 Data Types - double or logical 
-%
-%         bdp :  breakdown point. Scalar.
+%      bsb    : units forming a subset on which to perform PCA. vector.
+%               Vector containing the list of the units to use to
+%               compute the svd. The other units are projected in the
+%               space of the first two PC. bsb can be either a numeric
+%               vector of length m (m<=n), containing the list of the
+%               units (e.g., 1:50), or a logical vector of length n
+%               containing the true for the units that have to be used
+%               in the calculation of svd. For example, bsb=true(n,1),
+%               bsb(13)=false; excludes from the svd unit number 13.
+%               Note that if bsb is supplied, bdp must be empty.
+%               Example - 'bsb',[2 10:90 93]
+%               Data Types - double or logical 
+%
+%       bdp   : breakdown point. Scalar.
 %               It measures the fraction of outliers the algorithm should
-%               resist. In this case any value greater than 0 but smaller
-%               or equal than 0.5 will do fine. Note that if bdp is
-%               supplied bsb must be empty.
-%                 Example - 'bdp',0.4
-%                 Data Types - double
+%               resist. In this case, any value greater than 0, but smaller
+%               or equal than 0.5, will do fine. Note that if bdp is
+%               supplied, bsb must be empty.
+%               Example - 'bdp',0.4
+%               Data Types - double
 %
 %
-%    standardize : standardize data. boolean. Boolean which specifies
-%               whether to standardize the variables, that is we operate on
+% standardize : standardize data. boolean. Boolean that specifies
+%               whether to standardize the variables, that is, we operate on
 %               the correlation matrix (default) or simply remove column
 %               means (in this last case we operate on the covariance
 %               matrix).
-%                   Example - 'standardize',false
-%                   Data Types - boolean
-%
-%  alpha  : svd parameter. Scalar. Scalar in the interval [0 1] (see
-%           section additional details for more help). This parameter can
-%           be controllad by the corresponding sliding bar when the app is
-%           shown.
-%                   Example - 'alpha',0.6
-%                   Data Types - double
-%
-%  omega  : svd parameter. Scalar. Scalar in the interval [0 1] (see
-%           section additional details for more help). This parameter can
-%           be controllad by the corresponding sliding bar when the app is
-%           shown.
-%                   Example - 'omega',1
-%                   Data Types - double
-%
-% showRowPoints : hide or show row point. Boolean. If showRowPoints is true
-%                   row points are shown in the biplot (default) else there are hidden.
-%                   Example - 'standardize',false
-%                   Data Types - boolean
-%
-%  showRowNames : hide or show labels of row points. Boolean. If showRowNames is true
-%                   labels of row names are shown in the biplot  else (default) there are hidden.
-%                   Example - 'showRowNames',false
-%                   Data Types - boolean
-%
-%  showArrows : hide or show arrows. Boolean. If showArrows is true
-%                   arrows (associated labels) labels are shown in the biplot  (default) 
-%                   else there are hidden.
-%                   Example - 'showArrows',false
-%                   Data Types - boolean
+%               Example - 'standardize',false
+%               Data Types - boolean
+%
+%       alpha : svd parameter. Scalar. Scalar in the interval [0 1] (see
+%               section "additional details" for more help). This parameter can
+%               be controlled by the corresponding sliding bar when the app is
+%               shown.
+%               Example - 'alpha',0.6
+%               Data Types - double
+%
+%       omega : svd parameter. Scalar. Scalar in the interval [0 1] (see
+%               section "additional details" for more help). This parameter can
+%               be controlled by the corresponding sliding bar when the app is
+%               shown.
+%               Example - 'omega',1
+%               Data Types - double
+%
+% showRowPoints : hide or show row point. Boolean. If showRowPoints is true,
+%                 row points are shown in the biplot (default); otherwise they are hidden.
+%                 Example - 'standardize',false
+%                 Data Types - boolean
+%
+%  showRowNames : hide or show labels of row points. Boolean. If showRowNames is true,
+%                 labels of row names are shown in the biplot, otherwise (default) they are hidden.
+%                 Example - 'showRowNames',false
+%                 Data Types - boolean
+%
+%    showArrows : hide or show arrows. Boolean. If showArrows is true,
+%                 arrows (associated labels) labels are shown in the biplot (default);
+%                 otherwise they are hidden.
+%                 Example - 'showArrows',false
+%                 Data Types - boolean
 %
 % Output:  
-%         when the biplotAPP is closed in the base workspace a new variable
-%         called bsbfinalFromAPP is created which contains a logical vector
-%         of length n containing true for the units which have been used in
+%         when the biplotAPP is closed, in the base workspace, a new variable
+%         called bsbfinalFromAPP is created, which contains a logical vector
+%         of length n containing true for the units that have been used in
 %         the svd.
 %         
 %
@@ -214,9 +214,9 @@ function biplotFS(Y,varargin)
     %% use of biplotFS on the ingredients dataset.
     load hald
     % Operate on the correlation matrix (default).
-    % use standardized principal components (for row points) and
+    % Use standardized principal components (for row points) and
     % correlation between variables and principal components (for column
-    % points, arrows)
+    % points, arrows).
     close all
     biplotFS(ingredients,'omega',1,'alpha',0);
 %}