Biological Data Analysis: Homework 6

Due Thursday, May 4


You must type this and all other homework assignments. Do not e-mail the assignment to me; turn it in early (at 322 Wolf) for a foreseeable absence, or turn it in late after an unexpected absence from class.


1. For the last time, you're going to analyze the balance data set. Pick one of the measurement variables and do a linear regression/correlation between it and log-transformed balance time. Draw a nice graph showing the regression line and dots for the individual data points; don't use the graph that's included on my spreadsheet, draw your own Excel graph from scratch. Report the equation of the line, the r2, and the P-value. Write a couple of sentences interpreting your results.

2. Now do polynomial regression on the same data set. Report the P-values and R2 for the quadratic and cubic equations, and report the P-values for the increase in R2 at each step. Write a couple of sentences interpreting your results.

3. Pick one of the nominal variables with two values, and use it and the data from question one in an ancova, using this online ancova calculator. Give the P-value for the difference in slopes (called "between regressions" on the web page) and the P-value for the difference in intercepts (called "adjusted means" on the web page). Draw another graph like the one in question 1, only use different symbols for the two values of the nominal variable, and draw the two separate regression lines. You can just draw the regression line ("trend line") for each set of points, you don't need to draw the parallel lines that the ancova tests. Write a couple of sentences interpreting your results.

Return to the Biological Data Analysis syllabus