Biological Data Analysis: Homework 4

Due Tuesday, April 11

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. You're going to use the balance data set again. Analyze the same nominal and measurement variable that you analyzed in homework 3. Enter into the histogram spreadsheet the values of the measurement variable for the values of the nominal variable with the largest number of observations (for example, the measurements of height for people with bare feet). Print the histogram, and say whether you think it looks close enough to normal to analyze using one-way anova.

2. Plot three more histograms; one for the data from question 1 after it has been log transformed; one with a square-root transformation; and one with a transformation that you invent. When you invent a transformation, keep in mind that simply adding, subtracting, multiplying, or dividing by a constant won't change the shape of the distribution; you'll have to do something more advanced than that.

3. Enter the measurement data for all of your groups into the spreadsheet for Bartlett's test. Record the P-value for the untransformed data; the log transformed data; the square-root transformed data; and the data transformed using the transformation you invented for question 2. Based on these P-values and on just looking at the standard deviations, which do you think are homoscedastic enough to analyze using one-way anova?

4. Analyze the untransformed data using one-way anova. Report the F-statistic, the degrees of freedom, and the P-value. Also do the Tukey-Kramer test and report the results in either a graph or table. Write a couple of sentences interpreting your results.

5. Even if you thought the untransformed data were normal and homoscedastic enough, pick the best transformation and analyze the transformed data using one-way anova and Tukey-Kramer. Report the results as you did in question 4.

Return to the Biological Data Analysis syllabus