|
Upon successful completion of the course, students will be conversant with the R programming language and will be able to manage different types of variables and data structures, perform various parametric and nonparametric statistical analysis, graphically display descriptive and inferential results, and interpret the results of various statistical output. Students will also be able to critically evaluate and judge the appropriateness of the use of various analytic techniques presented in the scientific literature. Most importantly, students who successfully complete the course will be able to describe the theoretical underpinnings of frequentist and Bayesian approaches to statistical inference, perform various general and generalized linear models, report (in text and figures) and interpret results of these analyses, and be able to choose and utilize appropriate statistical techniques in their subsequent research.
|
|
Multivariate statistical techniques are basic tools for experimental and non-experimental research in the psychological and educational sciences. This course provides an overview of parametric and non-parametric analytic methods, and represents the foundation of the statistical knowledge and skills required for subsequent statistical courses in the Behavioural Science Research Master (BSRM). This course also introduces R as a statistical platform for the analysis and graphical representation of multivariate statistical techniques. The flexibility of this program offers students a general statistical “solution” for analyzing simple and complex data structures and allows for a wealth of analytic functionality. R will also be featured in the Mixed-Effects Modeling and Structural Equation Modeling statistical courses, and is compatible with the Python program, which is described in the programming skills course of the BSRM. R is a free, open-source platform that is continuously maintained, ensuring that students will be able to use their newly mastered skills in any future context.
This course begins with a review of the basic descriptive statistics, probability distributions, confidence intervals, significance tests, effect sizes, statistical power, and bivariate analyses. Data management and issues associated with pre-processing of data in R are covered with special attention paid to the visualization of data, both in terms of descriptive and inferential results. Lectures then expand upon the differences between frequentist (null hypothesis testing), maximum likelihood, and Bayesian approaches to statistical inference. Numerous statistical techniques are elaborated in terms of the types of research questions they address, their test statistics, and their underlying statistical assumptions. These techniques include, but are not limited to linear and logistic regression analyses, analyses of variance and covariance (ANOVA/ANCOVA), and exploratory factor analysis. This course provides students with the fundamental tools needed for their statistical toolbox so they are able to independently perform analyses that address their own research questions.
Exam information
Course grades are based on the results of three evaluative components: two take-home exams (each worth 45%) and weekly homework assignments (10%). The take-home exams require students to perform an appropriate set of analyses, and write up the results in APA style. The 12 weekly homework assignments will each be graded as pass/fail and the total points earned for this component will be determined as a function of the proportion of assignments that were successfully completed.
Teaching methods: Online lectures, online lab and Q & A sessions, and homework assignments.
|
 |
|
|
|
|
|