None although students will be expected to be able to use basic algebra
OverviewThis module aims to develop key statistical skills in students on their arrival at Kent, which they can build on in their further research and substantive modules in their degree. Learning will be oriented towards:
i. Assessing the strengths and limitations of using regression analysis for the establishment of causal inference; This includes:
o Distinction between causality, correlation or association
o Levels of measurement (e.g. nominal, ordinal, interval, ratio)
o Methods of regression analysis (e.g. OLS and logistic regression) and related assumptions
ii. Learning how to respond to research questions with the application of statistical methods of analysis, mainly regression methods, with the help of statistical software.
iii. Learning how to interpret the outcome of regression models and contextualise the results within broader theories.
This module appears in:
Contact Hours: 22 (one lecture and one seminar each week)
Method of assessment
Class participation (5%) - Students will be assessed on their participation in class, focusing in particular on their contribution to in-class debates, preparing appropriately for the classes, and doing (and putting the requisite effort into) formative assignments.
Group presentation (40%) - Each group will give an in-class presentation on a research question of their choice.
Personal study (coursework) Report (55%) - Students will write a 2500 word report trying to answer a research question. Students will be required to conduct a literature review, operationalise concepts, select the relevant variables for analysis and the statistical method, carry out the analysis and report the outcomes of the analysis.
Blastland, M. & Dilnot, A. (2007) The Tiger That Isn't. Profile Books
Field, A. (2013). Discovering statistics using IBM SPSS statistics. Sage.
Agresti, A. (2013). Categorical Data Analysis. Wiley
Allison, P.D. (1999), Multiple Regression: A Primer. SAGE Publications
Demonstrate knowledge of validity, reliability and transparency issues when carrying out statistical analyses;
Understand the difference between descriptive statistics (i.e. central tendency and dispersion) and inferential statistics (i.e. correlation, regression);
Demonstrate an ability to select the correct method of statistical analysis (description, correlation/association, statistical inference) based on the research question under study, the study design and data available;
Demonstrate an ability to read, understand and report/represent (e.g. tables, graphs) the results of regression analyses;
Demonstrate an ability to carry out multiple forms of regression analysis with the help of statistical software (e.g. SPSS, Excel).
Demonstrate an ability to investigate the assumptions of regression (e.g. heterocedasticity) and assess whether to take appropriate actions when assumptions are not met (e.g. remove outliers);
Understand the underlying principles of causality and main limitations when assessing causal inference;
Understand the advantages and limitations of using regression for the study of causality