Workshop: Statistical Analysis with R

Date: 1 Feb 2023 (Wed) & 8 Feb 2023 (Wed)

Time: 14:30 - 17:00

Venue: Online via MS Teams

Target Audience: All Students

Medium of Instruction: English

Prerequisite:

• Basic R programming skill
• Basic knowledge of statistics

Course Description:

• Understand how to summarize and organize characteristics of a dataset by finding means, medians, standard deviations, frequencies and proportions for variables
• Understand how to inspect the data graphically and statistically by R plotting functions
• Understand how to find p-values for validating a hypothesis against observed data
• Understand how to calculate confidence intervals for measuring the degree of uncertainty or certainty
• Understand how to perform t-tests, z-tests, one factor ANOVA and Chi-square tests for drawing conclusions based on your data
• Understand how to examine the association between two variables
  

Course Outline:

• Lesson 1
• Importing data into R from an external file
• Accessing individual variables from an imported data
• Creating categorical variables from an imported data
• Finding means, medians and standard deviations for all the variables in the dataset
• Finding means and standard deviations for subgroups
• Finding frequencies and proportions for categorical variables
• Inspecting the data graphically and statistically by R plotting functions
  • Histogram
  • Box Plot
  • Bar Chart
  • Scatter Plot
• Statistical table functions in R
  • The normal distribution
  • The standard normal distribution
  • T-distribution
  • Chi-squared distribution
• Confidence intervals
  • Single Group
  • Comparing Means
  • Comparing Frequencies
• Lesson 2
• T-tests for means to determine whether a process actually has an effect on the population of interest, or whether two groups are different from one another
  • The one-sample t-test for a mean
  • The independent samples t-test to compare two means
  • The paired samples t-test
• Z-tests for proportions to evaluate whether a finding or an association is statistically significant or not
  • One-sample z-test for a proportion
  • Two-sample z-test comparing two proportions
• One factor ANOVA comparing means across several groups to determine whether there are any statistically significant differentiations
• Chi-square tests for categorical outcomes to compare observed results and expected results
• Examining the association between two measurement variables
  • Scatter Plots
  • Correlation

• Practical coursework throughout the workshop