Welch's t-test: Difference between revisions
Content added Content deleted
m (→{{header|R}}: removed semicolons) |
(Added description, made minor modifications to C code) |
||
Line 2: | Line 2: | ||
Given two lists of data, calculate the [[wp:p-value|p-Value]] used for null hypothesis testing. |
Given two lists of data, calculate the [[wp:p-value|p-Value]] used for null hypothesis testing. |
||
P-values are significance tests to gauge the probability that the difference in means between two data sets is significant, or due to chance. A threshold level, alpha, is usually chosen, 0.01 or 0.05, where p-values below alpha are worth further investigation and p-values about alpha are considered not significant. The p-value is not considered a final test of significance, only whether the given variable should be given further consideration. |
|||
This uses [[wp:Welch's_t_test|Welch's t-test]], which assumes that the variances between the two sets are not equal. Welch's t-test statistic can be computed thus: |
This uses [[wp:Welch's_t_test|Welch's t-test]], which assumes that the variances between the two sets are not equal. Welch's t-test statistic can be computed thus: |
||
Line 39: | Line 41: | ||
<math> p = 1-\frac{1}{2}\times\frac{\int_0^\frac{\nu}{t^2+\nu} \frac{r^{\frac{\nu}{2}-1}}{\sqrt{1-r}}\,\mathrm{d}r}{ \exp((\ln(\Gamma(\frac{\nu}{2})) + \ln(\Gamma(0.5)) - \ln(\Gamma(\frac{\nu}{2}+0.5))) }</math> |
<math> p = 1-\frac{1}{2}\times\frac{\int_0^\frac{\nu}{t^2+\nu} \frac{r^{\frac{\nu}{2}-1}}{\sqrt{1-r}}\,\mathrm{d}r}{ \exp((\ln(\Gamma(\frac{\nu}{2})) + \ln(\Gamma(0.5)) - \ln(\Gamma(\frac{\nu}{2}+0.5))) }</math> |
||
for a 1-tail p-value. The 2-tail p-value is simply twice the 1-tail value. |
|||
=={{header|C}}== |
=={{header|C}}== |
||
{{works with|C99}} |
{{works with|C99}} |