🛠️ Projects¶
12 hands-on projects, each one a complete analysis rather than a single formula. Every project ships the same dataset three ways, so you can do the work in whichever tool you have open — and compare the results.
04-NN-project-name/
├── README.md ← the brief, the checkpoints, and the full EXCEL BUILD GUIDE
├── data/ ← the shared CSV — all three routes read this same file
├── r/analysis.R ← the R route
└── python/analysis.py ← the Python route
Tip
The Excel guide lives in each project's README — formulas, Analysis ToolPak dialogs, and chart setup, step by step. Work through it first, then run the R script and check that you get the same numbers.
Project Index¶
| # | Project | Chapters | Focus | Difficulty |
|---|---|---|---|---|
| 01 | Survey Data Organizer | 01 | Cleaning, coding, codebooks, quality checks | ⭐ |
| 02 | Frequency Distribution Builder | 02 | Classes, boundaries, histogram, polygon, ogive | ⭐⭐ |
| 03 | Descriptive Statistics Dashboard | 03–04 | Centre, spread, position, outliers, by group | ⭐⭐ |
| 04 | Probability Simulator | 05 | Theory vs. simulation, conditional, Bayes, counting | ⭐⭐ |
| 05 | Binomial & Poisson Calculator | 06, 12 | Discrete distributions, fitting, goodness-of-fit | ⭐⭐ |
| 06 | Normal Distribution Explorer | 04, 07 | Both directions, z-scores, normality checks | ⭐⭐ |
| 07 | Sampling & CLT Simulator | 08 | Four designs compared, the CLT demonstrated | ⭐⭐⭐ |
| 08 | Confidence Interval Estimator | 09 | Mean, proportion, variance, sample size, coverage | ⭐⭐⭐ |
| 09 | Hypothesis Testing Toolkit | 10–11 | One-sample, two-sample, paired, proportion | ⭐⭐⭐ |
| 10 | Chi-Square & ANOVA Suite | 12 | Goodness-of-fit, independence, ANOVA, Tukey | ⭐⭐⭐ |
| 11 | Correlation & Regression Analyzer | 13 | Correlation, regression, diagnostics, multicollinearity | ⭐⭐⭐ |
| 12 | Capstone: Business Statistics | all 13 | Full pipeline: describe → estimate → test → model → report | ⭐⭐⭐ |
Recommended Order¶
Projects map onto the chapters, so the natural route is straight down the list:
after chapters 01 → Project 01
after chapter 02 → Project 02
after chapters 03–04 → Project 03
after chapter 05 → Project 04
after chapter 06 → Project 05
after chapter 07 → Project 06
after chapter 08 → Project 07
after chapter 09 → Project 08
after chapters 10–11 → Project 09
after chapter 12 → Project 10
after chapter 13 → Project 11
at the end → Project 12 (the capstone)
Setup¶
Excel — enable the Analysis ToolPak once: File ▸ Options ▸ Add-ins ▸ Manage: Excel Add-ins ▸ Go ▸ tick "Analysis ToolPak". It then appears as Data ▸ Data Analysis.
R
Python
Then, from inside any project folder:
Both scripts read from data/ using relative paths, so run them from the project folder, not from the repository root.
About the Data¶
Every dataset is generated by tools/make_project_data.py from a fixed seed, so the numbers quoted in each README, script, and expected-output block stay reproducible. Regenerate them all at any time:
The data is synthetic but built with realistic structure — deliberate skew, a real association between exercise and health, genuine multicollinearity between sqft and bedrooms, one authentic high earner in the salary data. That is what makes the diagnostics worth running.
What Every Project Asks For¶
Regardless of the topic, each project holds you to the same standards:
| Check before you compute | Quality report, assumption checks, and a plot — before any statistic |
| State the method | Which test, which formula, and why it is the right one here |
| Report an effect size | A p-value alone is never the deliverable |
| Report an interval | The plausible range is what a decision-maker actually needs |
| Conclude in context | Plain language about the problem, not "reject H₀" |
| Name the limitation | Observational data means association, never causation |