Statistics for Business Analytics

2. Course Description

In the age of Big Data, intuition is not enough. This course equips leaders with the "Statistical Thinking" required to distinguish signal from noise. It integrates Python and Advanced Excel to analyze data, test hypotheses (A/B Testing), and build predictive models (Regression) for strategic decisions.

3. Course Objectives (Learning Goals)

1. To summarize and visualize complex business data to detect patterns and outliers.
2. To apply Probability Theory to assess risk and uncertainty in business scenarios.
3. To master Hypothesis Testing for validating business claims (e.g., "Does the new ad increase sales?").
4. To build Predictive Models (Regression) to forecast sales, churn, and market trends.

4. Course Outcomes (COs)

Mapped to Bloom’s Taxonomy and Taxila’s Program Outcomes.

CO Code	Course Outcome Description	Bloom's Level	Primary PO Mapping
CO1	Explain fundamental statistical concepts (Mean, Variance, Normal Distribution, P-Value).	Understand (L2)	PO1 (Mgmt Knowledge)
CO2	Apply probability rules and distributions to solve decision-making problems under uncertainty.	Apply (L3)	PO2 (Critical Thinking)
CO3	Analyze business data using Python/Excel to perform t-tests, ANOVA, and Chi-Square tests.	Analyze (L4)	PO1 (Tech Integration)
CO4	Evaluate the validity of statistical claims and detect "Spurious Correlations" in reports.	Evaluate (L5)	PO7 (Ethics)
CO5	Design a predictive model (Linear/Logistic Regression) to forecast a key business metric.	Create (L6)	PO2 (Data Decision)

 

5. CO-PO Articulation Matrix

Correlation: 3 (High), 2 (Medium), 1 (Low)

CO Code	PO1 (Mgmt/ Tech)	PO2 (Crit. Think)	PO3 (Lead/ Team)	PO4 (Comm.)	PO5 (Entrep.)	PO6 (Global/ ESG)	PO7 (Ethics)	PO8 (Life Learn)
CO1	3	2	-	-	-	-	-	1
CO2	2	3	-	-	1	-	-	2
CO3	3	3	-	1	2	-	-	3
CO4	1	3	-	2	-	1	3	-
CO5	3	3	1	2	3	-	-	3
AVG	2.4	2.8	1.0	1.7	2.0	1.0	3.0	2.25

 

6. Assessment Scheme 

 

Component	Marks	Description	Mapped CO
Simulation	20	Taxila Lab Simulations:   • Sim 1 (7 Marks): The Gambler's Fallacy (Probability).   • Sim 2 (7 Marks): The A/B Tester (Hypothesis).   • Sim 3 (6 Marks): The Prediction Engine (Regression).	CO2, CO3
Case Study	10	"The Moneyball Moment": Analysis of a data-driven turnaround (e.g., Oakland A's or Netflix).	CO4
Presentation	10	"Data Storytelling": Presenting insights from a dataset to a non-technical board.	CO5
Mid Term	10	Written exam covering Modules 1 & 2 (Descriptive & Probability).	CO1, CO2
Project	10	"The Kaggle Challenge": A mini-project predicting an outcome (e.g., Housing Prices) using a real dataset.	CO5
Class Participation	10	Participation in class discussions and coding labs.	All
End Term	30	Comprehensive written exam covering all modules.	All
Total	100

 

7. Detailed Syllabus & Session Plan

Each session assumes 90 minutes of class time + 60 minutes of pre-class preparation.

Module 1: Descriptive Analytics & Data Visualization (Sessions 1-5)

• Session 1: Introduction to Business Analytics

Topic: Types of Analytics (Descriptive, Predictive, Prescriptive). Data Types.

Pre-Class Prep: Read Anderson, Chapter 1 ("Data and Statistics").

Pedagogy: Lecture & Installation of Python/Excel Toolpak.

• Session 2: Visualizing Data

Topic: Histograms, Box Plots, Scatter Plots. Identifying Outliers.

Pre-Class Prep: Watch Video: "Hans Rosling’s 200 Countries" (TED Talk).

Pedagogy: Excel Lab (Creating dynamic dashboards).

• Session 3: Descriptive Statistics

Topic: Measures of Central Tendency (Mean/Median/Mode) and Dispersion (Standard Deviation/Variance).

Pre-Class Prep: Read Anderson, Chapter 3 ("Descriptive Statistics: Numerical Measures").

Pedagogy: Problem Solving.

• Session 4: Taxila Lab Simulation 1

Topic: "The Gambler's Fallacy": Students play a series of risk-based games (Roulette/Dice) to understand Law of Large Numbers and Variance.

Pre-Class Prep: Review "Concept of Variance".

Pedagogy: Simulation Lab (Taxila Lab Sim 1).

• Session 5: Probability Distributions

Topic: Normal Distribution (The Bell Curve), Z-Scores, Binomial Distribution.

Pre-Class Prep: Read Anderson, Chapter 6 ("Continuous Probability Distributions").

Pedagogy: Workshop (Calculating Probabilities).

Module 2: Inferential Statistics (Sampling & Hypothesis) (Sessions 6-10)

• Session 6: Sampling & Estimation

Topic: Central Limit Theorem, Confidence Intervals.

Pre-Class Prep: Read Case: Sampling at the Census Bureau (HBS/IIMA).

Pedagogy: Lecture.

• Session 7: Hypothesis Testing - I (One Sample)

Topic: Null vs. Alternative Hypothesis, Type I & II Errors, p-values.

Pre-Class Prep: Read Anderson, Chapter 9 ("Hypothesis Testing").

Pedagogy: Concept Check.

• Session 8: Hypothesis Testing - II (Two Samples / A/B Testing)

Topic: t-tests, Comparing two means (e.g., "Does Website A convert better than Website B?").

Pre-Class Prep: Read Article: "A/B Testing Guide for Leaders" (HBR).

Pedagogy: Python/Excel Lab (Running t-tests).

• Session 9: Taxila Lab Simulation 2

Topic: "The A/B Tester": Students act as Product Managers for an App, running live A/B tests to optimize features based on user data.

Pre-Class Prep: Review "p-value interpretation".

Pedagogy: Simulation Lab (Taxila Lab Sim 2).

• Session 10: Analysis of Variance (ANOVA)

Topic: Comparing more than two groups (F-test).

Pre-Class Prep: Read Anderson, Chapter 10 ("Analysis of Variance").

Pedagogy: Case Discussion (Comparing sales across 4 regions).

Module 3: Predictive Analytics (Regression) (Sessions 11-15)

• Session 11: Correlation vs. Causation

Topic: Correlation Coefficient (r), Covariance, Spurious Correlations.

Pre-Class Prep: Read Case: Red Bull: A High Energy Correlation? (Available Case).

Pedagogy: Discussion on Ethics in Data.

• Session 12: Simple Linear Regression

Topic: Least Squares Method, Regression Equation ($y = mx + c$), R-squared.

Pre-Class Prep: Read Anderson, Chapter 12 ("Simple Linear Regression").

Pedagogy: Excel Lab (Predicting Sales based on Ad Spend).

• Session 13: Multiple Regression

Topic: Handling multiple variables, Dummy variables (Categorical data).

Pre-Class Prep: Read Anderson, Chapter 13 ("Multiple Regression").

Pedagogy: Lecture.

• Session 14: Taxila Lab Simulation 3

Topic: "The Prediction Engine": Students are given a messy dataset of House Prices. They must build the best regression model to predict prices for a new listing.

Pre-Class Prep: Review "R-squared and Adjusted R-squared".

Pedagogy: Simulation Lab (Taxila Lab Sim 3).

• Session 15: Introduction to Logistic Regression

Topic: Predicting Binary Outcomes (Churn vs. No Churn, Buy vs. No Buy).

Pre-Class Prep: Read Note on "Classification vs. Regression".

Pedagogy: Concept Introduction.

Module 4: Capstone & Review (Sessions 16-20)

• Session 16: Time Series Analysis

Topic: Trends, Seasonality, Moving Averages.

Pre-Class Prep: Read Anderson, Chapter 17 ("Time Series Analysis").

Pedagogy: Forecasting Workshop.

• Session 17: Ethics in AI & Analytics

Topic: Algorithmic Bias, Data Privacy (GDPR/DPDP Act).

Pre-Class Prep: Read Case: Amazon’s AI Recruiting Tool Bias (News Article/Case).

Pedagogy: Ethics Debate.

• Session 18: Project Work & Lab

Topic: Working on "The Kaggle Challenge" project with faculty guidance.

Pre-Class Prep: Clean data for project.

Pedagogy: Lab Session.

• Session 19: Presentation Assessment

Topic: Presentation Component (10 Marks): "Data Storytelling".

Pre-Class Prep: Finalize Dashboard/Slides.

Pedagogy: Student Presentations.

• Session 20: Course Wrap-Up

Topic: Review for End Term + Feedback.

Pedagogy: Review.

8. Textbooks & Resources

1. Mandatory Textbook: Statistics for Business and Economics by Anderson, Sweeney, Williams, Camm, and Cochran (Cengage Learning).
2. Case Studies: Selected cases from Harvard Business School (HBS) & IIM Ahmedabad (IIMA).
3. Lab Resources:

Taxila Lab Sim 1: The Gambler's Fallacy.

Taxila Lab Sim 2: The A/B Tester.

Taxila Lab Sim 3: The Prediction Engine.