3200
|
1 ## Copyright (C) 1995, 1996, 1997 Kurt Hornik |
3426
|
2 ## |
3200
|
3 ## This program is free software; you can redistribute it and/or modify |
|
4 ## it under the terms of the GNU General Public License as published by |
|
5 ## the Free Software Foundation; either version 2, or (at your option) |
|
6 ## any later version. |
3426
|
7 ## |
3200
|
8 ## This program is distributed in the hope that it will be useful, but |
|
9 ## WITHOUT ANY WARRANTY; without even the implied warranty of |
|
10 ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
3426
|
11 ## General Public License for more details. |
|
12 ## |
3200
|
13 ## You should have received a copy of the GNU General Public License |
|
14 ## along with this file. If not, write to the Free Software Foundation, |
|
15 ## 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. |
|
16 |
|
17 ## usage: cor_test (X, Y [, ALTERNATIVE [, METHOD]]) |
|
18 ## |
|
19 ## Test whether two samples X and Y come from uncorrelated populations. |
|
20 ## |
|
21 ## The optional argument string ALTERNATIVE describes the alternative |
|
22 ## hypothesis, and can be "!=" or "<>" (non-zero), ">" (greater than 0), |
|
23 ## or "<" (less than 0). The default is the two-sided case. |
|
24 ## |
|
25 ## The optional argument string METHOD specifies on which correlation |
|
26 ## coefficient the test should be based. |
|
27 ## If METHOD is "pearson" (default), the (usual) Pearson's product |
|
28 ## moment correlation coefficient is used. In this case, the data |
|
29 ## should come from a bivariate normal distribution. Otherwise, the |
|
30 ## other two methods offer nonparametric alternatives. |
|
31 ## If METHOD is "kendall", then Kendall's rank correlation tau is used. |
|
32 ## If METHOD is "spearman", then Spearman's rank correlation rho is used. |
|
33 ## Only the first character is necessary. |
|
34 ## |
|
35 ## The output is a structure with the following elements: |
3426
|
36 ## pval The p-value of the test. |
|
37 ## stat The value of the test statistic. |
|
38 ## dist The distribution of the test statistic. |
|
39 ## params The parameters of the null distribution of the |
|
40 ## test statistic. |
|
41 ## alternative The alternative hypothesis. |
|
42 ## method The method used for testing. |
3200
|
43 ## |
|
44 ## If no output argument is given, the pval is displayed. |
|
45 |
|
46 ## Author: FL <Friedrich.Leisch@ci.tuwien.ac.at> |
|
47 ## Adapted-by: KH <Kurt.Hornik@ci.tuwien.ac.at> |
|
48 ## Description: Test for zero correlation |
|
49 |
|
50 function t = cor_test (X, Y, ALTERNATIVE, METHOD) |
3426
|
51 |
3200
|
52 if ((nargin < 2) || (nargin > 4)) |
|
53 usage ("cor_test (X, Y [, ALTERNATIVE [, METHOD]])") |
|
54 endif |
|
55 |
|
56 if (!is_vector (X) || !is_vector (Y) || length (X) != length (Y)) |
|
57 error ("cor_test: X and Y must be vectors of the same length") |
|
58 endif |
|
59 |
|
60 if (nargin < 3) |
|
61 ALTERNATIVE = "!="; |
|
62 elseif !isstr (ALTERNATIVE) |
|
63 error ("cor_test: ALTERNATIVE must be a string"); |
|
64 endif |
|
65 |
|
66 if (nargin < 4) |
|
67 METHOD = "pearson"; |
|
68 elseif !isstr (METHOD) |
|
69 error ("cor_test: METHOD must be a string"); |
|
70 endif |
|
71 |
|
72 n = length (X); |
|
73 m = METHOD (1); |
|
74 |
|
75 if (m == "p") |
|
76 r = cor (X, Y); |
|
77 df = n - 2; |
|
78 t.method = "Pearson's product moment correlation"; |
|
79 t.params = df; |
|
80 t.stat = sqrt (df) .* r / sqrt (1 - r.^2); |
|
81 t.dist = "t"; |
|
82 cdf = t_cdf (t.stat, df); |
|
83 elseif (m == "k") |
|
84 tau = kendall (X, Y); |
3426
|
85 t.method = "Kendall's rank correlation tau"; |
3200
|
86 t.params = []; |
|
87 t.stat = tau / sqrt ((2 * (2*n+5)) / (9*n*(n-1))); |
|
88 t.dist = "stdnormal"; |
|
89 cdf = stdnormal_cdf (t.stat); |
|
90 elseif (m == "s") |
|
91 rho = spearman (X, Y); |
|
92 t.method = "Spearman's rank correlation rho"; |
|
93 t.params = []; |
|
94 t.stat = sqrt (n-1) * (rho - 6/(n^3-n)); |
3426
|
95 t.dist = "stdnormal"; |
3200
|
96 cdf = stdnormal_cdf (t.stat); |
|
97 else |
|
98 error ("cor_test: method `%s' not recognized", METHOD) |
|
99 endif |
|
100 |
|
101 if (strcmp (ALTERNATIVE, "!=") || strcmp (ALTERNATIVE, "<>")) |
|
102 t.pval = 2 * min (cdf, 1 - cdf); |
|
103 elseif (strcmp (ALTERNATIVE, ">")) |
|
104 t.pval = 1 - cdf; |
|
105 elseif (strcmp (ALTERNATIVE, "<")) |
|
106 t.pval = cdf; |
|
107 else |
|
108 error ("cor_test: alternative `%s' not recognized", ALTERNATIVE); |
|
109 endif |
|
110 |
|
111 t.alternative = ALTERNATIVE; |
|
112 |
|
113 if (nargout == 0) |
|
114 printf ("pval: %g\n", t.pval); |
|
115 endif |
3426
|
116 |
3200
|
117 endfunction |