What did wage rates depend on? How many medals was a nation predicted to win at the next Olympics? Could we predict a student’s exam score based on their age and which qualification they were studying? I explored questions like these using statistical modelling techniques. This module took a practical approach, emphasizing the fitting of models and the interpretation of results.

 

Learning Outcomes

  • Mastering Linear Models: In this segment, learners will revisit the basics of simple linear regression and extend their understanding to include models with both multiple continuous and categorical variables. Using R, a statistical software, participants will enhance their ability to build and interpret complex regression models. This foundation sets the stage for predictive modeling exercises, such as forecasting Olympic success, emphasizing the practical application of theoretical knowledge.
  • Advancing with Generalised Linear Models: The curriculum progresses to generalised linear models to accommodate various types of data beyond the normal distribution. This part of the course introduces learners to binomial, Poisson, and exponential distributions, broadening their analytical capabilities. Special focus is given to loglinear models for examining relationships among categorical variables in complex datasets, providing a deeper understanding of statistical analyses in diverse scenarios.
  • Specializing in Applications: Applying statistical models in specific fields like econometrics and data science allows learners to tackle real-world challenges. The econometrics section addresses time-dependent data in economic analyses, while the data science portion covers clustering and big data problems. This tailored approach prepares students for the nuanced application of statistics in professional contexts, emphasizing problem-solving and analytical skills.
  • Vocational Relevance: The module not only enhances statistical modeling skills but also stresses the vocational relevance of these competencies. Skills in data analysis and interpretation are vital across numerous sectors, including government, healthcare, and business. Practical experience with R and the focus on statistical report writing equip learners with essential tools and communication skills for a career in data science and related fields.

Feedback on my assingments

The feedback across the assignments indicates a journey of improvement and learning, with specific areas highlighted for further development. Initially, difficulties in applying R for data analysis and interpretation were evident, particularly in visualizing data distributions and using diagnostic tools effectively. The feedback points towards a need for deeper engagement with the statistical tools and methods provided in the course materials, as well as a more thorough interpretation of results.   As the assignments progressed, there was notable improvement in understanding and applying statistical methods, although some challenges persisted with model selection and fulfilling specific question requirements. The feedback consistently encourages seeking further clarification and utilizing resources like student forums, online tutorials, and course notebooks to enhance understanding and application of statistical analyses.

Reflections

  • Assignment 1: Reflecting on this assignment, it's clear that my foundational skills in R and statistical interpretation needed strengthening. The feedback highlighted gaps in my ability to choose appropriate visualizations and diagnostic tools. This was a valuable learning moment, underscoring the importance of not only applying statistical methods but also critically evaluating the results.
  • Assignment 2: The feedback for this assignment was encouraging, pointing out a significant improvement in my understanding and application of statistical methods. However, the mistake in model selection for specific questions reminds me of the importance of carefully reading and understanding assignment questions. This experience has taught me to double-check my work against the assignment requirements.
  • Assignment 3: This assignment's feedback reflects further improvement, particularly in coding for analyses. The partial marks lost due to incomplete interpretations and missing answers to some parts of questions highlight the need for thoroughness in my responses. Moving forward, I aim to improve my attention to detail and ensure all parts of a question are addressed.
  • Assignment 4: The feedback indicates a misunderstanding of some assignment requirements and a reminder of the specifics of R functions. This assignment has reinforced the necessity of following instructions precisely and the importance of understanding the tools I'm using. It has prompted me to seek deeper insights into R's functionalities.
  • Assignment 5: In this assignment, selecting incorrect models and variables led to lost marks. This experience underscores the importance of model selection and variable identification in statistical analysis. It has motivated me to enhance my understanding of model frameworks and the criteria for selecting appropriate variables.

Professional Skills Matrix learnt and Action Plan

 

Skills Gained or Enhanced:

  • Statistical Analysis: Improved understanding and application of statistical methods using R.
  • Critical Evaluation:: Enhanced ability to critically evaluate data visualizations and statistical outputs.
  • Problem-Solving: Developed problem-solving skills through identifying and correcting errors in statistical models and coding.
  • Attention to Detail: Recognized the importance of thoroughness in addressing all parts of assignment questions.

Action Plan:

  • Strengthen R Proficiency: Dedicate time to practicing R outside of assignment requirements, focusing on visualizations, diagnostic checks, and model selection.
  • Engage with Resources: Actively participate in student forums, attend online tutorials, and review course notebooks to clarify uncertainties and learn from others' questions.
  • Critical Review of Assignments: Before submission, critically review assignments against the question requirements and feedback from previous assignments to ensure all aspects are covered and correctly addressed.
  • Seek Feedback: Where possible, seek early feedback on assignment drafts to identify areas of improvement before final submission.