我必须通过收缩因子(λ)将方差-协方差矩阵中的值向方差收缩(矩阵中的对角线值),因此: lambda * shrinkagematrix +(1-lambda)* variancecovariancematrix,其中:
方差协方差矩阵为:
Function VarCovar(rng As Range) As Variant
Dim i As Integer
Dim j As Integer
Dim numcols As Integer
numcols = rng.Columns.Count
numrows = rng.Rows.Count
Dim matrix() As Double
ReDim matrix(numcols - 1, numcols - 1)
For i = 1 To numcols
For j = 1 To numcols
matrix(i - 1, j - 1) = Application.WorksheetFunction.Covar(rng.Columns(i), rng.Columns(j)) * numrows / (numrows - 1)
Next j
Next i
VarCovar = matrix
,这给了我一个矩阵,例如:
0.40 -0.10 0.11
-0.10 0.17 -0.03
0.11 -0.03 0.19
然后我在创建看起来像如下的收缩矩阵时遇到了麻烦:
0.40 0.00 0.00
0.00 0.17 0.00
0.00 0.00 0.19
即在所有其他单元格中仅返回对角线值(=变量的方差)且为零。
所以以某种方式,使其返回仅包含row = column number的值的矩阵,即 (1,1),(2,2)和(3,3)值。
有什么可以帮助您的吗?
答案 0 :(得分:0)
您只需要一个从i = 1 to 3
开始的循环来使用Matrix(1, 1)
填充Matrix(2, 2)
,Matrix(3, 3)
和Matrix(i, i)
Function VarCovar(InputMatix As Range) As Variant
Dim MatrixColumns As Long
MatrixColumns = InputMatix.Columns.Count
Dim MatrixRows As Long
MatrixRows = InputMatix.Rows.Count
Dim Matrix() As Double
ReDim Matrix(1 To MatrixColumns, 1 To MatrixColumns)
Dim i As Long
For i = 1 To MatrixColumns
Matrix(i, i) = Application.WorksheetFunction.Covar(InputMatix.Columns(i), InputMatix.Columns(i)) * MatrixRows / (MatrixRows - 1)
Next i
VarCovar = Matrix
End Function
请注意,我将Matrix
尺寸Matrix(1 To MatrixDimension, 1 To MatrixDimension)
更改为以1
而不是0
开头,因此您可以轻松地将其写入单元格:
Sub test()
Range("A5:C7").Value = VarCovar(Range("A1:C3"))
End Sub