Now, let's get back to our friends the leaf-cutter ants... What kinds of hypotheses can we test with data we can obtain from these images? There are LOTS of possibilities. To help you out, let's constrain ourselves to data that can be measured on a numerical scale: like # of ants passing by per minute, walking speed, body size, leg length, or leaf area. Avoid categorical variables like worker caste (soldier vs. worker), time of day (morning, noon, evening), or the direction of travel of ants (left/right). [NOTE: Some instructors may not follow this constraint, so be sure to listen to YOUR instructor!!!]
So, pick a numerical variable that you can measure and that you are interested in... then choose another numerical variable (that you could measure) that YOU THINK may in part determine or influence the first.
Why this constraint? FIrst, we impose this constraint just to help you narrow down what you'd like to study. Second, choosing to look at the relationship between two numerical variables constrains the type of statistical analyses we will need to a single approach, simple linear regression. Ordinarily in research, we would follow our biological interests and use whatever tools we needed.
Before you begin collecting data, consider:
How many individuals will you need to measure?
Given the structure of the data (i.e. ants photographed during three periods during the day, more ants than you can measure during the lab period), how will you select which ants to measure?
How will you keep track of the data?
If you are working in a group, how will you ensure that different people don't measure the same animals?
Go for it! Here are all the images and videos, starting with some information about how these images were collected (metadata).
Now go collect that data!
Next->
image analysis basics image analysis instructions hypothesis formation regression basics regression instructions post-lab bibliography
image and video sets regression practice