Biostats Calculator

Features > Hypothesis testing

Hypothesis tests tell us whether patterns we observe in sample data are likely to be real (caused by patterns in the population) or due to chance.

• A test starts by assuming a 'null hypothesis' - that there is no relationship in the population, and that any observed relationship is due to random variation.
• Then it determines how likely it is that this random variation causes the strength of pattern that is observed in our sample.
• If it is sufficiently unlikely, the null hypothesis can be rejected and we decide that the relationship exists - it is statistically significant.
• Otherwise, the null hypothesis is accepted and the relationship might be explained by chance.

Hypothesis testing is a powerful tool, but the statistics involved is often complex. Biostats Calculator performs the most common hypothesis tests automatically and presents the results in a clear and easy-to-understand way.

Biostats Calculator performs 10 common hypothesis tests and several other calculations from the convenience of your iPhone or iPod Touch. Buy it today!

p values

The result of a hypothesis test is a p value. This is the probability that random chance would cause the pattern that was observed.

Typically, a p value of less than 0.05 is regarded as evidence that a real relationship exists. This is known as the 95% confidence level, and Biostats Calculator indicates this by turning green if the relationship is significant, and red if it is not.

Of course, Biostats Calculator also reports the p value for all hypothesis tests, so you are free to use a different criterion.

Related tests

Biostats Calculator can perform the following hypothesis tests:

• Significance of odds ratio
• Significance of relative risk
• Chi-square test
• Fisher's exact test
• Unpaired t-test
• Mann-Whitney U test
• One-way ANOVA
• Paired t-test
• Wilcoxon signed-rank test
• Pearson correlation
• Spearman rank correlation