Applied Data Science is a comprehensive, competency-based curriculum that develops practical data problem-solving skills through a consistent five-step framework applied across 10 progressively complex data science topics. Each chapter follows the same problem-solving lifecycle—Plan, Prepare, Analyze, Interpret, Communicate—ensuring learners develop transferable analytical thinking skills rather than isolated statistical knowledge. Through authentic scenarios spanning survey design, probability analysis, statistical inference, correlation, regression, classification, clustering, and time-series analysis, learners master the complete data analysis process from problem definition through actionable communication.
Applied Data
Science
A comprehensive, competency-based course that equips learners with practical data science skills through a structured five-step problem-solving framework applied across 10 progressively complex data science topics. From survey design and probability analysis through regression modeling, classification, clustering, and time-series analysis, learners master the complete analytical lifecycle: Plan, Prepare, Analyze, Interpret, and Communicate.
www.quanthub.com
Proposal: Applied Data Science
888-208-6840 | sales@quanthub.com
www.quanthub.com
www.quanthub.com
Course Overview
Course Outcomes & Content
Key Course Objectives
By the end of this course, participants will be able to:
- Apply the data problem-solving framework (Plan, Prepare, Analyze, Interpret, Communicate) systematically across diverse analytical scenarios including surveys, probability analysis, statistical inference, correlation, regression, classification, clustering, and time-series analysis
- Select and justify appropriate analytical methods based on research questions, data types, and business objectives—including frequency analysis, probability calculations, hypothesis testing, correlation analysis, linear regression, decision trees, k-means clustering, and time-series decomposition
- Prepare and assess data quality by identifying and correcting data issues (missing values, formatting inconsistencies, outliers, validity problems), performing data transformations (encoding, aggregation, concatenation), and evaluating dataset appropriateness for analytical goals
- Construct and interpret visualizations that effectively communicate analytical findings by selecting appropriate chart types, applying visual design principles (highlighting, sequential emphasis, cross-highlighting), and crafting explanatory titles and narratives aligned with stakeholder needs
- Translate analytical findings into actionable insights by interpreting statistical results in business context, evaluating practical versus statistical significance, assessing study limitations and biases, and constructing evidence-based recommendations with clear calls-to-action
- Design effective research questions and problem statements that guide statistical investigations by identifying appropriate objectives (description, comparison, association, prediction, classification, clustering), specifying measurable success criteria, and aligning analytical approaches with stakeholder needs
Topics Covered
| Topic Area | Content |
|---|---|
| 📊 Survey Design & Categorical Data | Survey construction, frequency tables, relative frequency, cumulative frequency, sorting and filtering, unbiased question design |
| 🎲 Probability Analysis | Joint probability, conditional probability, contingency tables, probability interpretation, simulation-based testing |
| 📈 Descriptive Statistics | Mean, median, range, Mean Absolute Deviation (MAD), five-number summary, measures of central tendency and variability |
| 🔍 Data Quality & Preparation | Completeness assessment, validity checks, formatting consistency, missing values, erroneous data, outlier identification and handling |
| 🔄 Data Manipulation | Concatenation (row-wise and column-wise), aggregation, datetime variable transformation, categorical encoding (one-hot encoding) |
| 🎯 Sampling & Study Design | Random sampling, sample size selection, data collection planning, generalizability assessment, cognitive bias identification |
| 📉 Hypothesis Testing & Inference | P-values, statistical significance, practical significance, sample proportions, inferential research questions |
| 🔗 Correlation & Association | Pearson's correlation coefficient, scatterplots, association interpretation, interpolation and extrapolation |
| 📐 Linear Regression | Model fitting, prediction calculations, prediction intervals, R-squared, residual analysis, model evaluation |
| 🌲 Classification | Decision trees, classification rules, decision boundaries, confusion matrices, performance metrics |
| 🎪 Clustering | K-means clustering, cluster evaluation (similarity, cardinality, magnitude), segment labeling and prioritization |
| ⏰ Time-Series Analysis | Temporal patterns, trends, seasonality, moving averages, aggregation by time intervals, time-series narratives |
| 📊 Visualization Design | Chart selection (bar, pie, histogram, scatterplot, box plot, line), visual highlighting, sequential emphasis, cross-highlighting, explanatory titles |
| 💬 Data Communication | Problem statements, research questions, data storytelling, narrative structure, big idea statements, calls-to-action, evidence-based claims |
Delivery & Logistics
| Aspect | Details |
|---|---|
| ⏱️ Duration | 50 hours of active learning across 50 competency modules |
| 📱 Platform | QuantHub Upskill platform with lesson plans that support in-classroom delivery for each module |
| 📅 Delivery Format | Self-paced with optional instructor-paced milestones, typically completed over a 14-16 week semester (3-4 hours per week) or potentially accelerated 4-5 week format (10-12 hours per week) |
| 🎓 Deployment Options | Full 50-hour course, individual chapters (5 hours each), or individual modules (1 hour each) to supplement traditional courses |
Module Structure
The course follows a spiral curriculum design where learners encounter the same five-step framework across progressively complex topics:
- Competency Modules (50 × 60 min): Each module includes interactive learning articles with embedded visualizations, scenario-based activities with narrative context, and case-based task activities
- Learning Sequence: Foundational topics (surveys, probability, descriptive statistics) → Inferential statistics (hypothesis testing, correlation, comparative analysis) → Predictive modeling (regression, classification) → Advanced topics (time-series, clustering)
- Assessment Model: Scenario activities provide formative assessment with 3-life gamification system; task activities provide summative assessment with 0-3 star weighted scoring
- Framework Consistency: Each chapter reinforces the complete data lifecycle: Plan (problem statements, research questions), Prepare (data quality, transformations), Analyze (statistical calculations, model building), Interpret (results interpretation, significance assessment), Communicate (visualizations, narratives, recommendations)
Course Chapters
The course is organized into 10 chapters, each containing 5 competency modules that apply the five-step data problem-solving framework to a specific analytical topic. Learners progress from foundational descriptive statistics through advanced machine learning applications, developing both breadth (diverse methods) and depth (complete analytical lifecycle) in data science practice.
Conducting Surveys and Summarizing Data
Chapter 1
Master the fundamentals of survey design and categorical data analysis. Learn to construct effective surveys with clear, unbiased questions, create and analyze frequency tables, and communicate findings through appropriate visualizations and evidence-based recommendations.
Chapter Focus
Develop practical skills in survey design, frequency analysis, and data storytelling to answer real-world business questions about customer preferences, market trends, and operational patterns.
Modules (5 × 1 hour)
- Analyzing survey results: Construct and analyze frequency tables to summarize and answer analytical questions
- Creating surveys: Design effective surveys with clear, unbiased questions aligned to research objectives
- Making recommendations: Interpret frequency data and visualizations to make evidence-based recommendations
- Selecting charts: Select and evaluate appropriate chart types to effectively communicate categorical data and comparisons
- Writing a problem statement: Write and evaluate problem statements that include goals, problems, and success criteria
Applying Probability
Chapter 2
Develop probability analysis skills by constructing contingency tables, calculating joint and conditional probabilities, and interpreting probability statements. Learn to combine datasets appropriately and select analytical methods based on variable types and research goals.
Chapter Focus
Apply probability concepts to real-world scenarios, understanding how to measure relationships between categorical variables and make data-driven claims supported by probability evidence.
Modules (5 × 1 hour)
- Calculate probabilities: Construct contingency tables and calculate joint and conditional probabilities
- Choose an analysis method: Identify analytical goals and select appropriate statistical analysis methods
- Combine datasets: Determine when and how to combine datasets using appropriate concatenation methods
- Interpret probabilities: Interpret joint and conditional probabilities to craft and evaluate evidence-based claims
- Visually highlight a chart: Apply and evaluate visual highlighting techniques to emphasize key takeaways
Analyzing Center and Spread
Chapter 3
Master descriptive statistics by calculating and interpreting measures of central tendency (mean, median) and variability (range, MAD). Develop critical data literacy skills including data quality assessment, understanding data types and measurement levels, and evaluating study limitations.
Chapter Focus
Build foundational statistical thinking by understanding distributions, identifying data quality issues, and communicating findings through effective chart titles and subtitles that support data narratives.
Modules (5 × 1 hour)
- Analyze center and spread: Calculate and interpret measures of central tendency and variability
- Assess data quality: Identify and evaluate data quality issues including completeness, validity, and formatting
- Define data requirements: Differentiate between data types and levels of measurement
- Evaluate study limitations: Identify cognitive biases and evaluate generalizability of results
- Summarize findings visually: Construct effective explanatory titles and descriptive subtitles for charts
Making Inferences About Association
Chapter 4
Develop hypothesis testing skills by conducting simulation-based inference, calculating p-values, and distinguishing between statistical and practical significance. Learn to design random sampling strategies and craft compelling data narratives that translate technical findings into actionable insights.
Chapter Focus
Apply inferential statistical thinking to investigate associations between categorical variables, evaluate evidence strength, and communicate findings through structured data stories with clear policy or business implications.
Modules (5 × 1 hour)
- Calculate sample proportions: Conduct simulations and determine statistical significance using p-values
- Craft a narrative: Create compelling data stories that translate statistical findings into actionable insights
- Craft a research question: Formulate and evaluate inferential research questions for statistical investigations
- Make a statement about association: Interpret p-values and assess statistical and practical significance
- Use random sampling: Design and implement random sampling strategies with appropriate sample sizes
Measuring Association Strength
Chapter 5
Master correlation analysis by calculating and interpreting Pearson's correlation coefficient, using scatterplots to visualize relationships, and making predictions through interpolation and extrapolation. Learn to identify and handle outliers that impact association strength.
Chapter Focus
Understand relationships between quantitative variables through correlation analysis, assess prediction confidence, and select appropriate visualizations to communicate association findings effectively.
Modules (5 × 1 hour)
- Analyze association: Measure and interpret the strength of association using correlation analysis
- Craft a research question for association: Construct research questions investigating quantitative associations
- Estimate the value of a quantitative variable: Use interpolation and extrapolation to predict values
- Identify and handle outliers: Identify outliers, evaluate their impact, and determine handling strategies
- Select charts to communicate association: Choose appropriate chart types and visual elements for associations
Comparing Quantitative Variables Across Groups
Chapter 6
Develop comparative analysis skills using grouped box plots to compare distributions across categories. Learn to calculate five-number summaries, construct probability statements, and craft compelling big idea statements with actionable calls-to-action for stakeholder audiences.
Chapter Focus
Apply comparative statistical methods to answer research questions about group differences, explore metadata to understand secondary data sources, and present findings through structured 3-minute data stories.
Modules (5 × 1 hour)
- Calculate quantiles and use box plots: Calculate five-number summaries and construct grouped box plots
- Craft a big idea statement: Identify key takeaways and construct compelling statements with calls-to-action
- Craft a research question to compare across groups: Construct effective comparative research questions
- Draw conclusions about distributions: Interpret grouped box plots and construct probability statements
- Explore metadata: Identify and evaluate secondary data using metadata to assess relevance
Linear Regression for Prediction
Chapter 7
Master linear regression by defining machine learning tasks, making predictions with prediction intervals, evaluating model fit using R-squared and residuals, and designing ethical data collection plans. Learn to visualize uncertainty in predictions and interpret results in business context.
Chapter Focus
Apply supervised machine learning concepts to build predictive models, evaluate their performance, and communicate predictions with appropriate uncertainty measures to support decision-making.
Modules (5 × 1 hour)
- Define the machine learning task: Identify regression applications and construct problem statements
- Design a chart for uncertainty: Design charts that encode and display prediction intervals
- Design a data collection plan: Create ethical data collection plans with informed consent
- Evaluate a regression model: Analyze model fit, residuals, and R-squared metrics
- Make a prediction: Use regression formulas to calculate predictions with intervals
Predicting Categorical Variables
Chapter 8
Develop classification skills by constructing and refining decision trees, identifying decision boundaries, and evaluating model performance using confusion matrices. Learn to clean data, define data requirements for classification, and visualize decision pathways using sequential highlighting.
Chapter Focus
Apply classification methods to predict categorical outcomes, evaluate predictions in business context, and understand the implications of relying on model predictions for critical decisions.
Modules (5 × 1 hour)
- Apply sequential highlighting: Plan and apply techniques to visualize decision tree pathways
- Classify new examples: Use decision trees to classify and evaluate predictions with performance metrics
- Clean your data: Identify and correct data quality issues including formatting and missing values
- Create classification rules: Construct and refine decision trees by analyzing distributions
- Define data requirements: Identify requirements including labeled examples and appropriate sample sizes
Time-Series Analysis
Chapter 9
Master time-series analysis by aggregating temporal data at appropriate intervals, calculating and visualizing moving averages, and identifying patterns including trends, seasonality, and key events. Learn to craft temporal research questions and build compelling time-series narratives with historical context.
Chapter Focus
Develop skills to analyze temporal patterns, smooth noisy data with moving averages, and present time-series findings through narratives that connect data patterns to real-world events and business implications.
Modules (5 × 1 hour)
- Aggregate data by a time variable: Choose appropriate time intervals and metrics for temporal aggregation
- Build a time-series narrative: Construct compelling narratives by adding context and identifying key events
- Calculate and plot a moving average: Determine window sizes and visualize moving averages as overlays
- Craft a temporal research question: Construct research questions investigating temporal patterns and trends
- Identify a pattern of variability: Interpret trends, recurring patterns, and key events in time-series data
Cluster Analysis and Segmentation
Chapter 10
Master unsupervised learning through k-means clustering. Learn to convert categorical data using encoding methods, construct problem statements for clustering tasks, evaluate cluster quality using similarity and cardinality metrics, and prioritize segments aligned with business goals using cross-highlighting visualization techniques.
Chapter Focus
Apply clustering methods to discover natural groupings in data, label segments meaningfully, evaluate clustering model performance, and communicate segment characteristics to support targeted business strategies.
Modules (5 × 1 hour)
- Convert categorical data: Apply encoding methods to transform categorical variables for cluster analysis
- Craft a problem statement for unsupervised learning: Determine when to use clustering and construct problem statements
- Design with cross-highlighting: Implement cross-highlighting techniques to visualize segment relationships
- Determine segment prioritization: Analyze cluster characteristics, label segments, and prioritize aligned with goals
- Evaluate a clustering model: Evaluate models by analyzing similarity, cardinality, and magnitude metrics