2 |
26 Feb 07 |
jari |
1 |
<html> |
2 |
26 Feb 07 |
jari |
2 |
<body bgcolor = "#FFFFCC"><basefont face = "Arial"> |
2 |
26 Feb 07 |
jari |
3 |
<h1>TTEST: T-test</h1> <h2> Parameter Information</h2> |
2 |
26 Feb 07 |
jari |
4 |
<hr size = 10> |
2 |
26 Feb 07 |
jari |
5 |
|
2 |
26 Feb 07 |
jari |
6 |
<h2>Group Assignments</h2> |
2 |
26 Feb 07 |
jari |
7 |
<h3>Group Selection Controls</h3> |
2 |
26 Feb 07 |
jari |
8 |
This set of buttons permits each experiment to be placed into |
2 |
26 Feb 07 |
jari |
9 |
group A, group B, or neither group. If an experiment is placed in |
2 |
26 Feb 07 |
jari |
10 |
neither group it will be ignored for the purposes the analysis. |
2 |
26 Feb 07 |
jari |
11 |
<br><br> |
2 |
26 Feb 07 |
jari |
12 |
Note that groups A and B must each have at least two members |
2 |
26 Feb 07 |
jari |
13 |
following the assignment. |
2 |
26 Feb 07 |
jari |
14 |
<h3>Save Grouping</h3> |
2 |
26 Feb 07 |
jari |
15 |
The save grouping button allows you to save the grouping |
2 |
26 Feb 07 |
jari |
16 |
to file. This is particularly useful when there are many experiments. |
2 |
26 Feb 07 |
jari |
17 |
<h3>Load Grouping</h3> |
2 |
26 Feb 07 |
jari |
18 |
This button allows you to select and load a saved grouping. |
2 |
26 Feb 07 |
jari |
19 |
<h3>Reset</h3> |
2 |
26 Feb 07 |
jari |
20 |
The reset button returns all of the group selection control buttons |
2 |
26 Feb 07 |
jari |
21 |
to Group A, the initial state. |
2 |
26 Feb 07 |
jari |
22 |
<br> |
2 |
26 Feb 07 |
jari |
23 |
<h2>Variance assumption</h2> |
2 |
26 Feb 07 |
jari |
24 |
This option applies to between subjects t-test only. By default, degree of freedom is calculated |
2 |
26 Feb 07 |
jari |
25 |
on a gene by gene basis assuming that the two groups have unequal variances. The other option |
2 |
26 Feb 07 |
jari |
26 |
assumes equal variances of the two groups, and calculates degree of freedom as (nA + nB - 2), where |
2 |
26 Feb 07 |
jari |
27 |
nA and nB are the number of valid values in groups A and B respectively. The formula for the t-ratio is also |
2 |
26 Feb 07 |
jari |
28 |
slightly different |
2 |
26 Feb 07 |
jari |
29 |
<br> |
2 |
26 Feb 07 |
jari |
30 |
<h2>P-Value Parameters</h2> |
2 |
26 Feb 07 |
jari |
31 |
This set of controls are used to indicate the method by which p-values are determined for |
2 |
26 Feb 07 |
jari |
32 |
each gene and allows the input of the critical p-value. |
2 |
26 Feb 07 |
jari |
33 |
<br><br> |
2 |
26 Feb 07 |
jari |
34 |
p-values can be computed either from the theoretical t-distribution, or from permutations |
2 |
26 Feb 07 |
jari |
35 |
of the data for each gene between the two groups. |
2 |
26 Feb 07 |
jari |
36 |
<h3>p-values based on t-distribution</h3> |
2 |
26 Feb 07 |
jari |
37 |
Using this option a gene's p-value is taken directly from the theoretical t-distribution |
2 |
26 Feb 07 |
jari |
38 |
based on the gene's calculated t-value. |
2 |
26 Feb 07 |
jari |
39 |
<h3>p-values based on permutation</h3> |
2 |
26 Feb 07 |
jari |
40 |
Using this option a gene's p-value is determined by forming a distribution based on |
2 |
26 Feb 07 |
jari |
41 |
permutations of the data for that gene. The permutations allow each value in the expression |
2 |
26 Feb 07 |
jari |
42 |
vector in group A or group B to be randomly placed into either group (the size of each |
2 |
26 Feb 07 |
jari |
43 |
group is conserved). t-values are constructed following each permutation to construct |
2 |
26 Feb 07 |
jari |
44 |
a distribution which is used to generate p values for each gene based on it's t-value. |
2 |
26 Feb 07 |
jari |
45 |
<br><br> |
2 |
26 Feb 07 |
jari |
46 |
If permutations are used, two buttons allow you to select to permute |
2 |
26 Feb 07 |
jari |
47 |
the values a number of times indicated or to permute the values a number of |
2 |
26 Feb 07 |
jari |
48 |
times equal to the maximum number of permutations possible. |
2 |
26 Feb 07 |
jari |
49 |
<h3>Critical p-value</h3> |
2 |
26 Feb 07 |
jari |
50 |
This text field allows you to enter the alpha or critical p-value. |
2 |
26 Feb 07 |
jari |
51 |
<br> |
2 |
26 Feb 07 |
jari |
52 |
<h2>P-Value / false discovery corrections</h2> |
2 |
26 Feb 07 |
jari |
53 |
The p-values for each p can be adjusted to correct for the large number |
2 |
26 Feb 07 |
jari |
54 |
of observations (genes) and the increased possibility of considering a gene without |
2 |
26 Feb 07 |
jari |
55 |
a real significant change to be considered significant. Three options are given for |
2 |
26 Feb 07 |
jari |
56 |
this correction. |
2 |
26 Feb 07 |
jari |
57 |
<h3>Just Alpha (no correction)</h3> |
2 |
26 Feb 07 |
jari |
58 |
Using this option the alpha is not altered. |
2 |
26 Feb 07 |
jari |
59 |
<h3>Standard Bonferroni Correction</h3> |
2 |
26 Feb 07 |
jari |
60 |
In the standard Bonferroni correction, the user-specified alpha is divided |
2 |
26 Feb 07 |
jari |
61 |
by the number of genes to give the critical p-value. |
2 |
26 Feb 07 |
jari |
62 |
This is much more stringent than using an uncorrected alpha. |
2 |
26 Feb 07 |
jari |
63 |
<h3>Adjusted Bonferroni Correction</h3> |
2 |
26 Feb 07 |
jari |
64 |
In the adjusted Bonferroni correction, the t-values for all the genes are |
2 |
26 Feb 07 |
jari |
65 |
ranked in descending order. For the gene with the highest t-value, the critical |
2 |
26 Feb 07 |
jari |
66 |
p-value becomes (alpha / n), where n is the total number of genes; |
2 |
26 Feb 07 |
jari |
67 |
for the gene with the second-highest t-value, the critical p-value will be (alpha/ n-1), |
2 |
26 Feb 07 |
jari |
68 |
and so on. The stringency of this correction falls somewhere between no correction |
2 |
26 Feb 07 |
jari |
69 |
and the Standard Bonferroni. |
2 |
26 Feb 07 |
jari |
70 |
<H3>False discovery control</H3> |
2 |
26 Feb 07 |
jari |
71 |
Under this option, with confidence of (1 - alpha), the number or proportion of false positives |
2 |
26 Feb 07 |
jari |
72 |
in the significant gene list should not exceed the input value. |
2 |
26 Feb 07 |
jari |
73 |
<br> |
2 |
26 Feb 07 |
jari |
74 |
<h2> Hierarchical Clustering </h2> |
2 |
26 Feb 07 |
jari |
75 |
This check box selects whether to perform hierarchical clustering on the elements in each cluster |
2 |
26 Feb 07 |
jari |
76 |
created. |
2 |
26 Feb 07 |
jari |
77 |
<br> |
2 |
26 Feb 07 |
jari |
78 |
</basefont> |
2 |
26 Feb 07 |
jari |
79 |
</body> |
2 |
26 Feb 07 |
jari |
80 |
</html> |
2 |
26 Feb 07 |
jari |
81 |
|
2 |
26 Feb 07 |
jari |
82 |
|