def RunResampleTest(firsts, others): """Tests differences in means by resampling. firsts: DataFrame others: DataFrame """ data = firsts.prglngth.values, others.prglngth.values ht = DiffMeansResample(data) p_value = ht.PValue(iters=10000) print('\nmeans permute preglength') print('p-value =', p_value) print('actual =', ht.actual) print('ts max =', ht.MaxTestStat()) data = (firsts.totalwgt_lb.dropna().values, others.totalwgt_lb.dropna().values) ht = hypothesis.DiffMeansPermute(data) p_value = ht.PValue(iters=10000) print('\nmeans permute birthweight') print('p-value =', p_value) print('actual =', ht.actual) print('ts max =', ht.MaxTestStat())
plt.hist(est_L, bins=max(est_L) - min(est_L) + 1) plt.axvline(x=est_90ci[0], linewidth=2, color='r', label="90% CI") plt.axvline(x=est_90ci[1], linewidth=2, color='r') plt.suptitle("Simulated sample distribution of estimated L (lambda)") plt.title("time interval distribution=exponential; lambda=" + str(lam) + "; simulation size=10000", fontsize=9) plt.xlabel("Estimated L (lambda)") plt.ylabel("Frequency") plt.legend() # ci_str = "90% CI ["+str(round(est_90ci[0], 2))+","+str(round(est_90ci[1], 2))+"]" # plt.text(0, 10, "mean error "+str(round(meanError, 4))+"\nRMSE "+str(round(RMSE, 4))+"\n"+ci_str+"\nSE "+str(round(np.array(est_L).std(), 4))) plt.show() # Q11. Think Stats Chapter 9 Exercise 2 (resampling) first_len = live.loc[preg["birthord"] == 1, "prglngth"] other_len = live.loc[preg["birthord"] != 1, "prglngth"] data = first_len, other_len ht_perm = h0.DiffMeansPermute(data) pvalue_perm = ht_perm.PValue() ht_resamp = DiffMeansResample(data) pvalue_resamp = ht_resamp.PValue() first_wt = live.loc[preg["birthord"] == 1, "totalwgt_lb"] other_wt = live.loc[preg["birthord"] != 1, "totalwgt_lb"] data = first_wt, other_wt ht_perm = h0.DiffMeansPermute(data) pvalue_perm = ht_perm.PValue() ht_resamp = DiffMeansResample(data) pvalue_resamp = ht_resamp.PValue()