print(f"T-statistic: t_stat") print(f"P-value: p_value")
| Pitfall | Solution | |--------|----------| | Using ttest_ind without alternative | Default is two-tailed. For Project 2’s first test, use alternative='greater' . | | Forgetting ddof=1 in np.std | This calculates sample standard deviation, not population. | | Misinterpreting p-value | P-value is not the probability that H₀ is true. It’s P(data | H₀). | | Copying code without understanding | The Codio autograder checks variable names exactly. Use historical_relative_skill not hist_skill . | | Skipping assumptions | Mention the Central Limit Theorem (n > 30) to justify normality. |
ci_lower = (mean_new - mean_hist) - margin ci_upper = (mean_new - mean_hist) + margin print(f"95% CI = (ci_lower:.2f, ci_upper:.2f)")
print(f"T-statistic: t_stat") print(f"P-value: p_value")
| Pitfall | Solution | |--------|----------| | Using ttest_ind without alternative | Default is two-tailed. For Project 2’s first test, use alternative='greater' . | | Forgetting ddof=1 in np.std | This calculates sample standard deviation, not population. | | Misinterpreting p-value | P-value is not the probability that H₀ is true. It’s P(data | H₀). | | Copying code without understanding | The Codio autograder checks variable names exactly. Use historical_relative_skill not hist_skill . | | Skipping assumptions | Mention the Central Limit Theorem (n > 30) to justify normality. |
ci_lower = (mean_new - mean_hist) - margin ci_upper = (mean_new - mean_hist) + margin print(f"95% CI = (ci_lower:.2f, ci_upper:.2f)")
*We respect your confidentiality and all information are protected.
