General Linear Models - Lab Exercises

Exercise 1: Descriptive statistics

1. Download the file "CichlidBrains.txt". Save the content of the file as a TEXT file and you will be able to view and edit it with any text editor, such as BBEdit. Note that there are 159 rows representing single individuals of 159 species of cichlids of the African Great Lakes. The file contains 5 variables for each individual, namely the lake it came from (LAKE), ecological classification with respect to feeding (TROPHIC), sex (SEX), standard length (STANDLEN), and eye diameter (EYEDIAM). Note, this is a subset of the data used in a series of publications:
   • van Staaden MJ, R Huber, LS Kaufman, & K Liem. 1995. Brain evolution in cichlids of the African Great Lakes: brain and body size, general patterns and evolutionary trends. ZACS 98: 165-17
   • Huber R, MJ van Staaden, LS Kaufman, & K Liem. 1997. Microhabitat use, trophic patterns, and the evolution of brain structure in African cichlids. Brain, Behav. Evol 50: 167-182
2. Using your favourite statistics program, exam whether the dependent variables - STANDLEN and EYEDIAM are suitable for parametric analyis. What are your conclusions?

Exercise 2: Does size vary with sex

1. Statistically test whether body size (STANDLEN) differs between sexes (1 - female, 0 - male).
2. What method do you use? What are the assumptions of this method? Are these assumptions met?
3. Perform the analysis using your favourite statistics program and report these results along with your conclusions.

Exercise 3: Does size vary with respect to lake, feeding type, or an interaction between the two

1. Statistically test whether body size (STANDLEN) differs among lakes, or feeding types. Perform separate analyses with lake and feeding type as factors. Report the results and explain your conclusions.
2. Perform a two-way, complete model Analysis of Variance using your favourite statistics program. Report the results as an ANOVA table and explain your conclusions. Compare the results from this full-model 2-way analysis to the two 1-way models from part 1.

Exercise 4: Does variation in eyesize relate to body size?

1. Explain your view on how the two variables are causally related.
2. What analysis would you use to examine the relationship. Why is your method applicable?
3. Perform the analysis using your favourite statistics program. Report the results and explain your conclusions.

Competences earned this week:

1. understand multi-factor, univariate analyses, including interaction terms and ANOVA tables with multiple MS_model terms
2. understand the assumptions of parametric methods and how to deal with situations in which they are violated