When Pearson chi-square, Yates continuity correction, the G likelihood-ratio test, and Fisher's exact test all answer the same question with different assumptions, you need more than a single number to make a defensible inference. This field guide walks through the eight decisions — test choice, Yates vs no-Yates, Fisher for small samples, G as likelihood ratio, effect sizes via Cramer V / phi / C, adjusted residuals with BH-FDR multiplicity, Cochran expected-count rule, and Chapman capture-recapture on 2x2 mark-recapture tables — that the Contingency Table Chi-Square, Fisher Exact, and Cramer V Tutor surfaces side by side on every 2x2 or RxC table you paste in.