matrix.hlp

是一个经济学管理应用软件 很难找的 但是经济学学生又必须用到

{smcl}
{* 14mar2005}{...}
{cmd:help matrix}
{hline}

{title:Title}

{p2colset 5 19 21 2}{...}
{p2col :{hi:[P] matrix} {hline 2}}Summary of matrix commands{p_end}
{p2colreset}{...}


{title:Description}

{pstd}
Comments are provided below under the following headings.

	 Subject{col 57}Also see help
    {hline 72}
     1.  Inputting matrices by hand{col 57}{helpb matrix define}
     2.  Setting the maximum matrix size{col 57}{helpb matsize}
     3.  Matrix expressions
	   Matrix operators{col 57}{help matrix operators}
	   Matrix functions{col 57}{help matrix functions}
     4.  Matrix subscripting{col 57}{help matrix subscripting}
     5.  Submatrix extraction{col 57}{help matrix extraction}
     6.  Submatrix substitution{col 57}{help matrix substitution}
     7.  Data <{hline 3}> Matrix conversion{col 57}{helpb mkmat}
     8.  Obtaining copies of system matrices{col 57}{helpb get()}
     9.  Matrix decomposition
	   Eigenvalues & vectors of symmetric matrices{col 57}{helpb matrix symeigen}
	   Eigenvalues of nonsymmetric matrices{col 57}{helpb matrix eigenvalues}
	   Singular value decomposition{col 57}{helpb matrix svd}
    10.  Setting row and column names{col 57}{helpb matrix rownames}
    11.  Macro extended functions regarding matrices{col 57}{help matmacfunc}
    12.  Accumulating cross-product matrices{col 57}{helpb matrix accum}
    13.  Generating scores from coefficient vectors{col 57}{helpb matrix score}
    14.  (Dis)similarity measures{col 57}{helpb matrix dissimilarity}
    15.  Constraint processing{col 57}{helpb makecns}
    16.  Matrix utilities{col 57}{help matrix utility}
    {hline 72}


{pstd}
In the syntax diagrams, capital letters {it:A}, {it:B}, ..., {it:Z} stand
for matrix names.  Full details can be found in {hi:[P] matrix}.


{title:1.  Inputting matrices by hand}{...}
{right:(see {hi:[P] matrix} and {hi:[P] matrix define};  }
{right:{helpb matrix define})  }

{p 8 19 2}{cmdab:mat:rix} {cmdab:in:put} {it:A} {cmd:= (}{it:#}[{cmd:,}{it:#...}]
		[{cmd:\} {it:#}[{cmd:,}{it:#...}] [{cmd:\} [{it:...}]]]{cmd:)}

    Examples:
{phang2}{cmd:. matrix input mymat = (1,2\3,4)}{p_end}
{phang2}{cmd:. matrix input myvec = (1.7, 2.93, -5, 3)}{p_end}
{phang2}{cmd:. matrix input mycol = (1.7\ 2.93\ -5\ 3)}

{pstd}
Each of the above would also work if you omitted the subcommand {cmd:input}:

{phang2}{cmd:. matrix mymat = (1,2\3,4)}{p_end}
{phang2}{cmd:. matrix myvec = (1.7, 2.93, -5, 3)}{p_end}
{phang2}{cmd:. matrix mycol = (1.7\ 2.93\ -5\ 3)}

{pstd}
There is a subtle difference:  The first method uses the {cmd:matrix input}
command; the second uses the matrix expression parser.  In one sense, using
the second method is better because

{phang2}{cmd:. matrix xmpl = (1+1, 2*3/4 \ 5/2, 3)}

{pstd}
is understood but would be a syntax error with {cmd:matrix input}.

{pstd}
{cmd:matrix input}, however, has two other advantages:

{phang2}1){space 2}{cmd:matrix input} will allow you to input very large
matrices.  (The expression parser is limited because it must "compile" the
expression and, if it is too long, will produce an error message.)

{phang2}2){space 2}{cmd:matrix input} will allow you to omit the commas.

{pstd}
It does not matter which you use.


{title:2.  Setting the maximum matrix size}{right:(see {hi:[R] matsize}; {helpb matsize})  }

{pstd}
Your maximum matrix size currently is {ccl matsize} by {ccl matsize}.  This
can be increased to {ccl max_matsize} by {ccl max_matsize}.  The details of
changing this limit are found in {hi:[R] matsize}; see {helpb matsize}.

{pstd}
The maximum matrix size limit may seem restrictive.  Since Stata does not
need to load the data into a matrix to compute estimation results this does
not pose a problem in practice.  See "Accumulating cross-product matrices"
below for pointers to the details.


{title:3.  Matrix expressions}{right:(see {hi:[P] matrix define};  }
{right:{help matrix operators}   }
{right:and {help matrix functions})  }

{pstd}
Complex matrix expressions are allowed within Stata.

{p 8 14 2}{cmdab:mat:rix} {it:A} {cmd:=} {it:matrix_expression}

    Examples:
{phang2}{cmd:. matrix D {space 2} = B}{p_end}
{phang2}{cmd:. matrix beta = invsym(X'*X)*X'*y}{p_end}
{phang2}{cmd:. matrix C {space 2} = (C+C')/2}{p_end}
{phang2}{cmd:. matrix sub{space 2}= x[1..., 2..5]/2}{p_end}
{phang2}{cmd:. matrix L = cholesky(0.1*I(rowsof(X)) + 0.9*X)}

{pstd}
The available matrix operators and functions are detailed in
{hi:[P] matrix define}; see {help matrix operators} and
{help matrix functions}.


{title:4.  Matrix subscripting}{right:(see {hi:[P] matrix define};  }
{right:{help matrix subscripting})  }

{p 8 14 2}
{cmdab:mat:rix} {it:A} {cmd:=} {it:...} {it:B}{cmd:[}{it:r}{cmd:,}{it:c}{cmd:]} {it:...}

{pstd}
where {it:r} and {it:c} are numeric or string scalar expressions.

    Examples:
{phang2}{cmd:. matrix A = A/A[1,1]}{p_end}
{phang2}{cmd:. matrix B = A["weight","displ"]}{p_end}
{phang2}{cmd:. matrix D = G[1,"eq1:l1.gnp"]}

{pstd}
Subscripting with numeric expressions may be used in any expression context
(such as {helpb generate}, {helpb replace}, etc.)  Subscripting by row/column
name may only be used in a matrix context.  (This latter is not a constraint;
see the {cmd:rownumb()} and {cmd:colnumb()} matrix functions returning scalar
in {hi:[P] matrix define} and {help matrix functions}; they may be used
in any expression context.)


{title:5.  Submatrix extraction}{right:(see {hi:[P] matrix define};  }
{right:{help matrix extraction})  }

{p 8 14 2}{cmdab:mat:rix} {it:A} {cmd:=} {it:...} {it:B}{cmd:[}{it:r0}{cmd:..}{it:r1}{cmd:,}
				{it:c0}{cmd:..}{it:c1}{cmd:]} {it:...}

{pstd}
where {it:r0}, {it:r1}, {it:c0}, and {it:c1} are numeric or string scalar
expressions.

    Examples:
{phang2}{cmd:. matrix A = B[2..4, 3..6]}{p_end}
{phang2}{cmd:. matrix A = B[2..., 2...]}{p_end}
{phang2}{cmd:. matrix A = B[1, "price".."mpg"]}{p_end}
{phang2}{cmd:. matrix A = B["eq1:", "eq1:"]}


{title:6.  Submatrix substitution}{right:(see {hi:[P] matrix define};  }
{right:{help matrix substitution})  }

{p 8 14 2}{cmdab:mat:rix} {it:A}{cmd:[}{it:r}{cmd:,}{it:c}{cmd:]} {cmd:=} {it:...}

{pstd}
where {it:r} and {it:c} are numeric scalar expressions.

{pstd}
If the matrix expression to the right of the equal sign evaluates to a
scalar or 1 x 1 matrix, the indicated element of {it:A} is replaced.  If the
matrix expression evaluates to a matrix, the resulting matrix is placed in
{it:A} with its upper left corner at ({it:r},{it:c}).

    Examples:
{phang2}{cmd:. matrix A[2,2] = B}{p_end}
{phang2}{cmd:. matrix A[rownumb(A,"price"), colnumb(A,"mpg")] = sqrt(2)}


{title:7.  Data <{hline 3}> Matrix conversion}{right:(see {hi:[P] matrix mkmat}; {helpb mkmat})  }

{pstd}
Variables can be converted into matrices and likewise matrices can be
converted into variables.  The details are found in {hi:[P] matrix mkmat}; see
{helpb mkmat}.


{title:8.  Obtaining copies of system matrices}{right:(see {hi:[P] matrix get}; {helpb get()})  }

{pstd}
The usual way to obtain matrices after a command that produces matrices is
simply to refer to the returned matrix in the standard way.  For instance all
estimation commands return

{p 8 20 2}{hi:e(b)} {space 6} coefficient vector{p_end}
{p 8 20 2}{hi:e(V)} {space 6} variance-covariance matrix of the estimates (VCE)

{pstd}
And these matrices can be referenced directly.

    Examples:
{phang2}{cmd:. matrix list e(b)}{p_end}
{phang2}{cmd:. matrix myV = e(V)}

{pstd}
Other matrices are returned by various commands.  They are obtained in the
same way.  Alternatively, the {cmd:matrix get} command also obtains matrices
after certain commands; see {hi:[P] matrix get} and {helpb get()}.


{title:9.  Matrix decomposition}{right:(see {hi:[P] matrix symeigen},     }
{right:{hi:[P] matrix eigenvalues},  }
{right:and {hi:[P] matrix svd};          }
{right:{helpb matrix symeigen},     }
{right:{helpb matrix eigenvalues},  }
{right:and {helpb matrix svd})          }

{pstd}
Obtaining the eigenvalues and eigenvectors from a symmetric matrix is
detailed in {hi:[P] matrix symeigen}; see {helpb matrix symeigen}.
Obtaining the real and complex parts of the eigenvalues of a square matrix is
detailed in {hi:[P] matrix eigenvalues}; see {helpb matrix eigenvalues}.
Obtaining the singular value decomposition of a matrix is detailed in
{hi:[P] matrix svd}; see {helpb matrix svd}.  If you desire the Cholesky
factorization or the matrix sweep function, then see the {cmd:cholesky()} and
{cmd:sweep()} functions in {hi:[P] matrix define}; see 
{help matrix functions}.


{title:10.  Setting row and column names}{right:(see {hi:[P] matrix rownames};  }
{right:{helpb matrix rownames})  }

{pstd}
Row and column names of matrices in Stata have special meaning -- they tell
the names of the variables, equations, and time-series operators that helped
create the matrix.  Stata automatically carries these names along during
matrix operations and uses the names to produce appropriately labeled
command output.

{pstd}
In most cases you do not need to worry about setting matrix row and column
names yourself.  See {hi:[P] matrix rownames} and {helpb matrix rownames}
for details of how to manually set matrix row and column names.


{title:11.  Macro extended functions regarding matrices}{...}
{right:(see {hi:[P] matrix};  }
{right:{help matmacfunc})  }

{pstd}
The following extended macro functions are allowed with {cmd:local} and
{cmd:global}:

	{cmd:: rowfullnames} {it:A}
	{cmd:: colfullnames} {it:A}

	{cmd:: rownames} {it:A}
	{cmd:: colnames} {it:A}

	{cmd:: roweq} {it:A}
	{cmd:: coleq} {it:A}

    Examples:
{phang2}{cmd:. local names : rownames mymat}{p_end}
{phang2}{cmd:. local names : rowfullnames mymat}{p_end}
{phang2}{cmd:. local names : colfullnames e(b)}


{title:12.  Accumulating cross-product matrices}{...}
{right:(see {hi:[P] matrix accum};  }
{right:{helpb matrix accum})  }

{pstd}
Most statistical computations involve matrix operations such as X'X or
X'WX.  In these cases X may have a very large number of rows and usually a
small to moderate number of columns.  W usually takes on a restricted form
(diagonal, block diagonal, or is known in some functional form and need not be
stored).  Computing X'X or X'WX by storing the matrices and then directly
performing the matrix multiplications is inefficient and wasteful.  Stata has
matrix cross-product accumulation commands that will compute these results
efficiently.  See {hi:[P] matrix accum} and {helpb matrix accum}.


{title:13.  Generating scores from coefficient vectors}{...}
{right:(see {hi:[P] matrix score};  }
{right:{helpb matrix score})  }

{pstd}
Scoring refers to forming linear combinations of variables in the data with
respect to a coefficient vector.  This is easily accomplished using the
{cmd:matrix score} command; see {hi:[P] matrix score} and 
{helpb matrix score}.


{title:14.  (Dis)similarity measures}{...}
{right:(see {hi:[P] matrix dissimilarity};  }
{right:{helpb matrix dissimilarity})  }

{pstd}
Many similarity, dissimilarity, and distance measures for continuous or binary
data are available; see {help measure option}.  {cmd:matrix dissimilarity}
allows you to compute these (dis)similarities between observations or
variables; see {helpb matrix dissimilarity}.


{title:15.  Constraint processing}{...}
{right:(see {hi:[P] makecns}; {helpb makecns})  }

{pstd}
Estimation commands that allow constrained estimation define constraints
using the {helpb constraint} command.  Program writers can incorporate these
same features using the commands in {hi:[P] makecns}; see {helpb makecns}.


{title:16.  Matrix utilities}{right:(see {hi:[P] matrix utility};  }
{right:{help matrix utility})  }

{pstd}
There are matrix utilities to

{p 8 27 2}{cmd:matrix dir} {space 6} List the currently defined matrices{p_end}
{p 8 27 2}{cmd:matrix list} {space 5} Display the contents of a matrix{p_end}
{p 8 27 2}{cmd:matrix rename} {space 3} Rename a matrix{p_end}
{p 8 27 2}{cmd:matrix drop} {space 5} Drop a matrix

{pstd}
See {hi:[P] matrix utility} and {help matrix utility} for details.


{title:Also see}

{psee}
Manual:  {bf:[P] matrix}

{psee}
Online:  
{helpb get()},
{helpb makecns},
{help matmacfunc},
{helpb matrix accum},
{helpb matrix define},
{help matrix dissimilarity},
{helpb matrix eigenvalues},
{help matrix extraction},
{help matrix functions},
{help matrix operators},
{helpb matrix rownames},
{helpb matrix score},
{help matrix subscripting},
{help matrix substitution},
{helpb matrix svd},
{helpb matrix symeigen},
{help matrix utility},
{helpb matsize},
{helpb mkmat},
{helpb ml}
{p_end}