Schools
 
Undergraduate
Stats
Papers
STAT241
 
Department

Search Maths/Stats: 
 
Advanced Search




Preferred habitat

Habitat selection by wild animals is a major issue in environmental science, in particular in protecting the habitat of endangered species to ensure the survival of such a species

The New Zealand Hector’s dolphin is an endangered animal and a study is being carried out to establish factors which may determine a preferred habitat. These factors include water temperature, water clarity and water depth, as well as seasonal effects and prey abundance. Regression analysis identifies those factors that influence the dolphins’ choice of habitat. A set of data based on an investigation of 980 sites around the South Island, half the sites having dolphins present, is analysed in this paper. Some seasonal effects have been identified.






Folate in flour?

Low folate levels in mothers can result in abnormalities in new-born babies. A nutrition study is presently investigating factors influencing folate levels in women of child-bearing age to establish the impact of diet and also to measure lifestyle effects such as smoking, exercise and alcohol.

The addition of folate to flour by law is being proposed as a way of increasing folate intake naturally; flour is a component of basic foods such as cereal, pasta and bread. Regression procedures identify potential causal diet and lifestyle variables. Early results confirm folate in cereal has a significant effect on folate levels in women of child-bearing age. The data for this research are used in the paper.

STAT241 Regression & Modelling 1

First Semester, 18 points
Regression and modeling, the “core techniques” of modern statistical analysis, appear regularly in the research journals of many fields ranging from the health sciences, nutrition, epidemiology, ecology, environmental science, zoology and botany to sociology, marketing, economics and finance. In many settings there is a response or outcome being researched and a number, often quite large, of potential causal factors. A regression analysis develops equations which assist in identifying important influences on the outcome measure. The data are frequently observational and the regression procedures allow correction for potential confounding effects as well as suggesting hypotheses for future investigation with designed experiments. The paper uses the statistical packages IBM SPSS 19 and R.

This paper is central for the advanced study of statistics and biostatistics. It is the first in a regression sequence which extends from second to fourth year in the subject. It is also a prerequisite for the applied time series paper at third year level.

Paper details

Regression essentially summarises (or models) complex data in a compact way and identifies factors which explain variability in an outcome measure. Economists use regression for forecasting, ecologists employ regression to study the effects of acid rain, sociologists build regression based causal models, a nutrition scientist models dietary factors which inhibit and enhance iron storage levels in newborn babies, epidemiologists investigate factors which influence cot death. All these studies involve the systematic assessment of various exposure variables on an outcome of interest and make adjustments for covariates or confounders which also affect the outcomes. The methods for achieving this are all covered in this paper and involve simple linear, multiple and logistic regression procedures along with conditions required for the correct use of these methods. IBM SPSS Version 19 and R are used for data analysis during the semester.

Potential students

All students who intend to major in statistics or biostatistics should take this paper. There is no mathematics prerequisite and therefore the paper can be taken with a background of either STAT 110 or STAT 115. The paper is particularly useful, therefore, as an advanced service statistics paper for all students majoring in any of the subjects listed above or for postgraduates in a wide range of other subjects. It has the added advantage that it also leads into the third year STAT 341, STAT 352 and STAT 380 as well as being helpful for Stat 342. These four papers can also be taken without mathematics prerequisites.

Main topics

  • Simple linear regression including split line regression
  • Multiple linear regression
  • Model building
  • Outliers and influential points
  • Dummy variables, categorical predictors
  • The single factor experiment
  • Two factor unbalanced experiments
  • Sequential data
  • Logistic regression
  • Comparison of logistic models
  • Confidence intervals for odds ratios
  • Adjustments for covariates and confounders

Prerequisites

STAT 110 or STAT 115

Required text

None, course notes will be available for purchase at the University Print Shop.

Lecturer

John Harraway, Room 238, Science III

Lectures

Three lectures each week for the first half of the course and two lectures each week for the second half, giving 33 lectures in total. Times are Tuesday, Thursday and Friday at 1pm. Some timetable clashes can be reduced by choice of the two lecture times only in the second half of the semester.

Tutorials

One hour per week at times to be arranged. The tutorials begin in the second week of lectures.

Internal Assessment

Ten exercises contributing 50 marks. A mid semester test in the third week before the end of the semester will be worth 50 marks. Total internal assessment (A) is therefore out of 100 marks.

Exam format

A three-hour written examination, also worth 100 marks.

Final mark

The final mark F is calculated from:
F = max { E, (2E + A)/3 }
where E (exam mark) is out of 100, A (internal assessment) is out of 100.

The “max” corresponds to plussage: if your internal assessment mark is greater than your exam mark then it is combined in the proportion shown. If it is less then it is ignored and the exam mark itself is used.


Plagiarism

Students should make sure that all submitted work is their own. “Plagiarism is a form of dishonest practice. Plagiarism is defined as copying or paraphrasing another’s work and presenting it as one’s own” (University of Otago Calendar). In practice this means that plagiarism includes any attempt in any piece of submitted work (e.g. an assignment or test) to present as one’s own work the work of another (whether of another student or a published authority). Any student found to be responsible for plagiarism in any piece of work submitted for assessment shall be subject to the University’s dishonest practice regulations which may result in various penalties, including forfeiture of marks for the piece of work submitted, a zero grade for the paper, or in extreme cases exclusion from the University. The University of Otago reserves the right to use plagiarism detection tools.

While we strive to keep details as accurate and up-to-date as possible, information given here should be regarded as provisional. Individual lecturers will confirm teaching and assessment methods.