When we collect data to help us address questions in biology, we must have a way to determine what those data mean. We use statistics to allow us to describe patterns in our data (Gotelli and Ellison 2013). Often statistics are used to estimate parameters, which are population characteristics that we are interested in learning about.
What are Statistics?
Biological hypotheses vs. statistical hypotheses
In biology, we often approach a question by making a related hypothesis or hypotheses and then seeking to evaluate these hypotheses based on experiments, field observations, etc. We assess the validity of the hypotheses using our data from these sources using statistical tests. Each statistical test has an associated null and alternative hypothesis that differ…
Null and alternative hypotheses
Biological hypotheses, like the one on the previous page (Biological vs. statistical hypotheses) that suggests atrazine will result in lower abundance of amphibians, have specific associated predictions. Furaha predicted that survival would be lower for leopard frogs living in a particular habitat that contained atrazine than a habitat that did not. Another student, Diego, suggests…
Steps in a hypothesis test
Start with the question you are asking or the biological hypothesis you are testing and make a testable prediction. Look at your data. Make an appropriate graph. Determine which statistical test would be appropriate. If there is not a test that would be appropriate, you may want to return to your prediction and revise…
Understanding p-values
The P-value gives you a means by which you may assess your null and alternative hypotheses. “The P-value is the probability of observing data at least as favorable to the alternative hypothesis as our current data set, if the null hypothesis is true” (Diez 2015). We are looking to see how often we would get…
Sample Size
Sample size plays an important role as you evaluate hypotheses using statistics. As sample size decreases, it is more difficult to detect an existing difference. For instance, if we only looked at 10 moths in the population above, we could randomly collect 10 white individuals, whereas if we were to collect 100 moths, we would…
Effect size
Sample size is not the only factor that can make it more difficult to detect an existing difference. Suppose you are assessing length differences on average between male and female crabs, using a millimeter scale. Scenario 1: The major claw of male and female fiddler crabs differs in length by an average of 4 mm.…
Conclusions
When working through a question in biology, we often have specific hypotheses we wish to test. By designing your study to address the question and picking appropriate test statistics, we can evaluate the biological hypothesis. While designing our study and examining our findings, it is important to consider both sample and effect size and how…