Fall 2017: APPLIED MULTIVARIATE STATISTICS USING R

   
Instructor Christopher Chizinski
Office 407 Hardin Hall
Office hours Drop by or by appointment
Email cchizinski

Course Aims

Course Description This course provides students with an understanding of how to apply multivariate statistical methods. Emphasis is placed on developing conceptual and practical understanding of how to apply these techniques with real-world data. While many of the examples will be with ecological data, the information is applicable to other disciplines. Topics include introduction to coding and use of the statistical program R, screening data, distance matrices, classification approaches, ordination, multivariate regression. No previous experience in R is required.

Course Objectives:

By the end of this course, students should be able to:

  1. Demonstrate a working knowledge of the coding in the statistical program R.
  2. Demonstrate a working knowledge of manipulating and summarizing data sets and producing presentation or publication graphics in R
  3. Use appropriate techniques to screen and standardize multivariate data.
  4. Use the appropriate analysis technique to identify and characterize groups in multivariate data.
  5. Use the appropriate analysis techniques in the ordination of multivariate data.
  6. Demonstrate an ability to model multivariate data using the appropriate techniques.

This course will:

  1. Provide a forum for discussion on problem solving with R and multivariate data.
  2. Enable students to utilize approaches to evaluate questions using multivariate data
  3. Familiarize students with common R packages (e.g., psych, vegan) to conduct multivariate analysis in R
  4. Provide each student a suite of analytical and coding skills that will can be applied in graduate school and their careers.

Material repository

Material can be found in the SNR R User group repository on github and through the group’s github page

Books

  • No text book is required
  • Readings, data sets, and problem sets will be available on the courses github page

Schedule

This schedule is tentative and we may change the schedule a depending on the interest of the class.

Week Date Topic
1 25-Aug Introduction to R and coding; Data structures in R; Importing data
2 1-Sep Data manipulation and summarization
3 8-Sep Graphing with ggplot2
4 15-Sep Introduction to multivariate techniques; Multivariate data, Data standardization, Distance matrices
5 22-Sep Identifying groups in multivariate data; Cluster analysis, Discrimination among groups
6 29-Sep Characterizing multivariate data; Factor analysis, Latent class analysis
7 6-Oct Testing groups; Multivariate analysis of variance (MANOVA), Multi-response permutation procedure (MRPP), analysis of group similarities (ANOSIM), and Mantel’s test (MANTEL)
8 13-Oct Testing groups (continued)
9 19-Oct Unconstrained ordination; Principal components analysis (PCA), Principal coordinate Analysis (PCoA), and multidimensional scaling (MDS/NMDS)
10 27-Oct Constrained ordination; Correspondence analysis (CA/DCA)
11 2-Nov Indirect Gradient analysis
12 9-Nov Direct Gradient analysis, Canonical correspondence analysis (CCA, Redundancy analysis (RDA)
13 17-Nov Multivariate regression
14 25-Nov No class – Thanksgiving break
15 1-Dec Dealer’s choice #1
16 8-Dec Dealer’s choice #2