Undergraduate Course: Applied Statistics (MATH10096)
|School||School of Mathematics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 10 (Year 4 Undergraduate)
||Availability||Available to all students
|Summary||Many standard statistical tests depend on the assumption that the population being sampled follows a parametric model. For instance, a t-test relies on the fact that our data distribution is (at least approximately) normally distributed. However, in many practical settings, the data distribution does not follow a simple form and there is a need for procedures that do not depend on a parametric model.
The course will focus on applied statistical techniques for analysing data and conducting hypothesis tests, including goodness-of-fit, permutation and nonparametric tests.
In this course we will study a variety of statistical tests. These include:
1) Goodness of fit tests that assess whether the data are sampled from a prespecified distribution.
2) Permutation tests for comparing two or more populations, including the Mann-Whitney test, the Wilcoxon signed-rank test, the sign test and randomisation tests.
3) Nonparametric tests such as the runs test, the Kruskal-Wallis test.
We will also carry out the tests in R.
Information for Visiting Students
|Pre-requisites||Visiting students are advised to check that they have studied the material covered in the syllabus of any pre-requisite course listed above before enrolling.
|High Demand Course?
Course Delivery Information
|Not being delivered|
On completion of this course, the student will be able to:
- formulate appropriate statistical hypotheses for scientific tests
- construct goodness of fit tests, permutation tests and other standard nonparametric tests
- distinguish between parametric and nonparametric tests, select the appropriate tests and apply them to a range of different forms of data
- carry out hypothesis tests in R and interpret the results accordingly
|Recommended, but not essential:|
W. J. Conover, (1999), Practical Nonparametric Statistics, 3rd edition, Wiley.
J. Kloke and J. W. McKean, (2015), Nonparametric Statistical Methods Using R, CRC Press.
B. F. J. Manly, (1997), Randomisation, Bootstrap and Monte Carlo Methods in Biology,
Chapman & Hall.
I. P. Sprent and N.C. Smeeton, (2001), Applied Nonparametric Statistical Methods, 3rd
edition, Chapman & Hall.
|Graduate Attributes and Skills
|Course organiser||Dr Timothy Cannings