Course Overview
- Course Title: Statistical Inference & Hypothesis Testing for Data Science
- Instructor: Muhammad Shafiq (Data Scientist | AI & ML Engineer | Lecturer | Researcher)
- Target Audience:
- Aspiring data scientists and data analysts
- Professionals in market research, quality control, or A/B testing
- Students or researchers needing statistical inference skills
- Intermediate learners with basic statistics or probability knowledge
- Prerequisites:
- Basic understanding of descriptive statistics (mean, median, variance)
- Familiarity with probability distributions (recommended but not mandatory)
Curriculum Highlights
- Key Topics Covered:
- Fundamentals of statistical inference and population vs. sample dynamics
- Hypothesis testing framework: null/alternative hypotheses, test statistics, p-values
- Parametric tests:
- t-tests (one-sample, two-sample, paired)
- ANOVA (one-way and two-way)
- Chi-Square tests (goodness-of-fit, independence)
- Non-parametric alternatives (Mann-Whitney U, Kruskal-Wallis)
- Confidence intervals and margin of error calculations
- A/B testing principles and experimental design
- Common statistical fallacies and bias mitigation
- Key Skills Learned:
- Formulating testable hypotheses for data-driven problems
- Selecting appropriate statistical tests based on data type and research questions
- Conducting tests in Python/R (conceptual focus; code templates provided)
- Interpreting p-values, effect sizes, and confidence intervals
- Designing rigorous experiments (e.g., A/B tests) with statistical validity
- Critically evaluating statistical claims in research or business contexts
Course Format
- Duration:
- 3 hours of on-demand video
- 3 practice tests (quizzes for reinforcement)
- Format:
- Self-paced online course (lifetime access)
- Mobile and TV accessibility
- Resources:
- Downloadable lecture slides and cheat sheets
- Practice datasets for hands-on exercises
- Python/R code snippets (no prior coding experience required)