Applied Data Analysis Curriculum (Graduate Level)

Focus: 20% Theory | 80% Practice (with tools & real datasets)

Module 1: Introduction & Basics

Theory (Short):

• What is data analysis?

• Data types: structured, unstructured, categorical, numeric

• Data analysis vs. data science

• Data-driven decision-making process

Practice:

• Importing datasets (CSV, Excel, JSON)

• Exploring datasets in Excel (sorting, filtering, pivot tables, charts)

• Hands-on with Python (Pandas) for dataset preview

• Overview of data analytics lifecycle

Tools: Excel, Python (Pandas)

Module 2: Data Collection & Management

Practice-Focused:

• Collect data using Google Forms → Excel

• Import data from SQL databases

• Use APIs and web scraping (Python requests/BeautifulSoup)

• Manage large datasets in Power Query

Tools: MS Excel, SQL, Python, Google Sheets

Outcome: Students can gather and manage structured and unstructured data efficiently.

Module 3: Data Cleaning & Preprocessing

Practice:

• Handle missing values (Excel formulas, Python .fillna())

• Remove duplicates and handle outliers

• Standardize and normalize data

• Encode categorical variables

• Real-world dataset cleaning

Tools: Excel, Python (Pandas, NumPy), OpenRefine

Outcome: Students can prepare high-quality, analysis-ready datasets.

Module 4: Exploratory Data Analysis (EDA)

Practice:

• Descriptive statistics (mean, variance, standard deviation)

• Visualizations: histograms, scatter plots, pivot charts

• Correlation and heatmaps in Python (Seaborn, Matplotlib)

• Interactive EDA using Tableau and Power BI

Tools: Excel, Python, Tableau, Power BI

Outcome: Students can explore datasets and uncover insights visually and statistically.

Module 5: Statistical & Predictive Analysis

Theory (Minimal):

• Sampling, probability, and hypothesis testing

• Regression fundamentals

Practice:

• Run t-tests and regressions in Excel (Data Analysis ToolPak)

• Multiple regression in Python (Statsmodels, Sklearn)

• Logistic regression for classification problems

Tools: Excel, R (Basic), Python (Statsmodels, Sklearn)

Outcome: Students can build simple predictive models and interpret statistical results.

Module 6: Advanced Data Analysis

Practice:

• Clustering (K-Means in Python & Excel add-ins)

• Time Series Forecasting in Excel (Forecast Sheet) & Python (ARIMA)

• Dimensionality Reduction (PCA in Python)

Tools: Excel Forecast Tool, Python (Scikit-learn, Statsmodels)

Outcome: Students can apply advanced modeling techniques for business insights.

Module 7: Machine Learning for Data Analysis

Practice:

• Build predictive models (Random Forest, XGBoost)

• Use AutoML tools in Excel (XLSTAT, Solver)

• Evaluate models with confusion matrix and ROC curve

Tools: Python (Scikit-learn, XGBoost), Excel XLSTAT, Orange ML

Outcome: Students can perform automated machine learning for data-driven prediction.

Module 8: Data Visualization & Storytelling

Practice:

• Build dashboards in Excel (Pivot dashboards)

• Create Tableau and Power BI dashboards

• Data storytelling principles — choosing the right chart for each dataset

• Visual presentation of findings

Tools: Excel, Tableau, Power BI, Python (Plotly, Seaborn)

Outcome: Students can create professional reports and dashboards that communicate insights effectively.

Module 9: Real-World Applications

Practical Domains:

• Business Analytics: Sales forecasting and KPI reporting

• Healthcare Analytics: Patient data cleaning and trends

• Social Media Analytics: Data collection via APIs (Twitter, Facebook)

• Research Analytics: Survey data cleaning and visualization

Outcome: Students apply techniques to real industry datasets.

Module 10: Capstone Project

Practice:

• • Choose a dataset (Business, Finance, Healthcare, or Social Data)

  • Apply full cycle: Collection → Cleaning → Analysis → Visualization → Reporting

  • Present results as:

    • Written Report (Word/LaTeX)

    • Interactive Dashboard (Excel, Tableau, Power BI)

    • Oral Presentation with Slides

Outcome: Graduates produce a complete analytical project aligned with global data standards.