← All Data Visualization with AI modules

Module 8 — Reproducibility, AI Audit & Capstone Prep

Weeks 15–16 · graduate statistics · adaptive competencies DV15–DV16

Turn the project into a reproducible Quarto/Shiny artifact with prompt logs, verification appendix, peer review, and statistical defense.

Statistics focusreproducibility, prompt logs, source code, peer review, statistical defense, capstone readiness

R/tool focusInline browser R labs; optional desktop RStudio/Positron for capstone; Quarto report; Shiny final artifact; optional ellmer prompt logging or AI critique

Interactive assignmentAI-output audit cards, peer-review rubric, interactive defense Q&A rehearsal

Interactive reading

Predict before reveal

Why is a prompt log not enough by itself for graduate-level AI-assisted statistical work?

A prompt log documents AI use, but graduate work also requires verification: code/output checks, statistical reasoning, corrections, assumptions, limitations, and human interpretation.

Peer-review rubric lab

The peer-review rubric lab needs JavaScript.

Defense rehearsal

The defense rehearsal needs JavaScript.

AI-output audit

This AI audit needs JavaScript.

Hands-on visual lab

One dataset, one question, and four analytic choices any reviewer would accept — so sixteen defensible answers. Find your specification on the curve, then ask what reporting only that one would tell a reader. Then run the browser-R lab below without leaving QuantegyAI.

This visual lab needs JavaScript.

R lab

R / Quarto / Shiny workflow

Finalize a reproducible Quarto report or Shiny artifact with source code, prompt log, verification notes, and statistical defense.

# Suggested R workflow scaffold
library(tidyverse)
# 1. Import or construct the dataset
# 2. Verify summaries before visualizing
# 3. Build the ggplot2 visualization
# 4. Write the statistical interpretation and limitation note
# 5. Log any AI assistance and corrections

Adaptive reflection

What I know / where I go next

I can regenerate every figure in my report from the raw data and a fixed seed. I can show the prompt, output, check, and correction for each AI-assisted step. I can tell a reproducibility gap from a verification gap from a disclosure gap. I can answer a causal challenge by naming what my design does and does not support. I can report a sensitivity analysis, including the specifications that disagree.

Mastery check loading…

Capstone connection Add this module’s evidence to your capstone readiness tracker. If your explanation depends on AI, include the prompt, output, verification method, and final correction.