A maximum test in lieu of forcing a choice between the two dependent samples t-test and Wilcoxon signed-ranks test is proposed. The maximum test, which requires a new table of critical values, maintains nominal α whi...A maximum test in lieu of forcing a choice between the two dependent samples t-test and Wilcoxon signed-ranks test is proposed. The maximum test, which requires a new table of critical values, maintains nominal α while guaranteeing the maximum power of the two constituent tests. Critical values, obtained via Monte Carlo methods, are uniformly smaller than the Bonferroni-Dunn adjustment, giving it power superiority when testing for treatment alternatives of shift in location parameter when data are sampled from non-normal distributions.展开更多
Objective: To take advantage of Epi Info to manage and analyze disease data. Methods: After selecting the living examples for independent sample T-Test, Epi Info 5.00, 5.01a(Chinese), 6.00, 6.04 b, 6.04 d, 2000, 2...Objective: To take advantage of Epi Info to manage and analyze disease data. Methods: After selecting the living examples for independent sample T-Test, Epi Info 5.00, 5.01a(Chinese), 6.00, 6.04 b, 6.04 d, 2000, 2002(Chinese)were used to do the independent sample T-Test on the two living examples. Then, Intercooled StataT, Microsoft Excel(2002) and SPSS 10.0 for Windows were used to verify the results. Results: The statistical results from the Epi Info 5.00, 5.01a(Chinese) and 6.00 were the same while that from Epi Info 6.04 b, 6.04 d, 2000,2002 (Chinese), Intercooled StataT, Microsoft Excel(2002) and SPSS 10.0 for Windows were identical In independent sample T-Test,. But the former result is different with the latter. Conclusion: There was an error in the result of T-Test from Epi Info 6.00 and former versions. Thus, it's important to be alert to select the versions of Epi Info to manage and analyze disease data. On the other hand, it's also quite pivotal to distinguish the adopted Epi Info versions when referring to the articles ane use the statistical results.展开更多
文摘A maximum test in lieu of forcing a choice between the two dependent samples t-test and Wilcoxon signed-ranks test is proposed. The maximum test, which requires a new table of critical values, maintains nominal α while guaranteeing the maximum power of the two constituent tests. Critical values, obtained via Monte Carlo methods, are uniformly smaller than the Bonferroni-Dunn adjustment, giving it power superiority when testing for treatment alternatives of shift in location parameter when data are sampled from non-normal distributions.
文摘Objective: To take advantage of Epi Info to manage and analyze disease data. Methods: After selecting the living examples for independent sample T-Test, Epi Info 5.00, 5.01a(Chinese), 6.00, 6.04 b, 6.04 d, 2000, 2002(Chinese)were used to do the independent sample T-Test on the two living examples. Then, Intercooled StataT, Microsoft Excel(2002) and SPSS 10.0 for Windows were used to verify the results. Results: The statistical results from the Epi Info 5.00, 5.01a(Chinese) and 6.00 were the same while that from Epi Info 6.04 b, 6.04 d, 2000,2002 (Chinese), Intercooled StataT, Microsoft Excel(2002) and SPSS 10.0 for Windows were identical In independent sample T-Test,. But the former result is different with the latter. Conclusion: There was an error in the result of T-Test from Epi Info 6.00 and former versions. Thus, it's important to be alert to select the versions of Epi Info to manage and analyze disease data. On the other hand, it's also quite pivotal to distinguish the adopted Epi Info versions when referring to the articles ane use the statistical results.