FOR50040 GIS and MANOVA II

Academic Year 2020/2021

This is an advanced applied GIS and multivariate analysis of variancve (MANOVA) module. The objective of this module is to understand the logic behind geospatial multivariate analysis of balanced p-dimensional data from repeatedly measured experiments.
A secondary objective is to provide PhD students with the opportunity to learn and advanced multivariate techniques within a geospatial context.
Topics covered may include: Computation of the mean vector, sums of squares and cross products, variance-covariance and correlation matrices using matrix algebra. Eigenvalue-eigenvector decomposition of covariance matrices. Testing the significance of non-zero eigenvalues. The fundamental equation of multivariate analysis of variance (MANOVA). The multivariate normal and Wishart distribution. Reduction of dimensionality using principle component analysis and factor analysis. Minimum and Mahalnobis distances. Independent verification of MANOVA analyses using Microsoft Excel, Mathematica 9 and R 6. Application of GIS and MANOVA technaiques to balanced data from repeatedly measured experimental designs. Issues relating to multivariate analysis of Coillte-COFORD permanent sample plot data from long-term forestry experiments will be aluded to.
This 10 credit GIS and MANOVA module is offered as a postgraduate elective to all MSc and Structured PhD students, interested post-doctorates, academic staff and professionals registered in a Continuous Professional Development programme. This module is designed for researchers and professionals required to undertake GIS and multivariate analysis of p-dimensiuonal data.
Upon completion of the module the 10 credits will appear on your UCD transcript. There is no formal end-of-trimester examination. Digital scientific papers on each exercise will account for 100% of the examination. The entire assessment is open-book, digital and encourages student's self-improvement of work. All examination files will be submitted as Winzip files, *.zip, through Blackboard. Grades will based be on the criteria specified at the following URL: http://www.ucd.ie/registry/assessment/

Show/hide contentOpenClose All

Curricular information is subject to change

Learning Outcomes:

On completion of this GIS and MANOVA II module postgraduates and professionals should be able to demonstrate understanding competencies under the following themes:
1. Understanding geospatial eigenvalue-eigenvector decomposition
2. Understanding geospatial principal component analysis
3. Understanding geospatial MANOVA of repeatedly measured data from randomized block designs
4. Understanding geospatial factor analysis
5. Understanding analysis of p-dimensional geospatial data
6. Understanding the creation and improvement of a portfolio of error-free scientific papers
7. Understanding digital submission of all examination Winzip files saved through Blackboard

This module may be taken as a directed study by mutual agreement between the postgraduate, the postgraduate Supervisor and the Lecturer. The credits from this module may be accumulated, along with the credits from other related modules, towards a Masters or PhD Degree which incorporates GIS.

Student Effort Hours: 
Student Effort Type Hours
Lectures

30
Computer Aided Lab

30
Specified Learning Activities

60
Autonomous Student Learning

60
Total

180
Approaches to Teaching and Learning:
Not yet recorded 
Requirements, Exclusions and Recommendations
Learning Requirements:

1. Proficiency in the use of Microsoft Word and Excel, Winzip, Blackboard, UCD Connect and the UCD
Library are required.
2. Competence in producing short, error-free, fully referenced scientific papers.
3. Proficiency in the use of ESRI ArcGIS 9.3 is desirable but not essential.

The ideal background for this module would be:
FOR 20100 Applied Biostatistics,
FOR 30310 GIS and Remote Sensing.
FOR 30360 GIS and Forest Sampling,
FOR 40080 GIS and Forest Inventory.
FOR 40120 GIS and Experimental Design,
FOR 50010 GIS and Remote Sensing 2,
FOR 50020 GIS and Biological Modeling
FOR 50030 GIS and MANOVA 1
or equivalent modules.

The GIS component of this module will focus on the gospatial distribution of experimental units for three experimental designs for which multivariate data are recorded.

Learning Recommendations:

The recommended texts for this module include

Braun, John W. and Duncan J. Murdoch. 2007. A first course in statistical programming with R. Cambridge University Press. 162p. ISBN 978-051-87265-2 (hardback).
www.cambrigge.org/9780521872652

Crawley, Michael, J. 2007. The R Book. John Wiley & Sons Ltd. 942p. ISBN-13: 978-0-470-51024-7. cs-books@wiley.co.uk www.wiley.com

Johnson R. A. and D. W. Wichern. 2002. Applied Multivariate Statistical Analysis. Fifth Edition. Prentice Hall. Upper Saddle River, New Jersey. 767 pp. ISBN 0-13-092553-5. www.prenhall.com.

Khattree, R. and D. N. Naik. 1999.
Applied Multivariate Analysis with SAS? Software. Second Edition. SAS Institute Inc., Cary, N.C. 360 pp.

Kuehl, Robert, O. 2000. Design of Experiments: Statistical Principles of Research Design and Analysis. Second Edition. Duxbury Press at Brooks/Cole Publishing Company, California. 666 pp. ISBN 0-534-36834-4. ?50.30. www.duxbury.com

Mac Si?rt?, M. P. 2000. Multivariate Analysis of Spectral Reflectance Profiles in Forest Seedling Remote Sensing Experiments. PhD Thesis. National University of Ireland. 447p.

Pallant, Julie. 2005. SPSS Survival Manual. Second Edition. A step by step guide to data analysis using SPSS for Windows (Version 12). Open University Press. 318p. ISBN 0 335 21640 4. UCD Campus Bookstore ?41.80. www.openup.co.uk

Montgomery, Douglas, C. 1997. Design and Analysis of Experiments. Fourth Edition. John Wiley & Sons Inc. 704 p. ISBN 0-471-15746-5.


Module Requisites and Incompatibles
Not applicable to this module.
 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Continuous Assessment: 5. Submission of improved zip files to Blackboard each Friday by 1500 Varies over the Trimester n/a Graded No

5
Assignment: 3. Understanding geospatial MANOVA of repeatedly measured data from randomized block designs. Week 7 n/a Graded No

25
Assignment: 6. Submission of feedback, self assessment and time management Varies over the Trimester n/a Graded No

5
Assignment: 1. Understanding geospatial eigenvalue-eigenvector decomposition. Week 3 n/a Graded No

20
Assignment: 2. Understanding geospatial principal component analysis. Week 5 n/a Graded No

20
Assignment: 4. Understanding geospatial factor analysis. Week 9 n/a Graded No

25

Carry forward of passed components
Not yet recorded
 

Not yet recorded
Please see Student Jargon Buster for more information about remediation types and timing. 
Not yet recorded