Answer for questions of repeated measurements of variance analysis and distribution test of data — Authors’ reply

Dao Wen Wang , Li Ni , Hualiang Jiang

Front. Med. ›› 2022, Vol. 16 ›› Issue (4) : 661 -664.

PDF (263KB)
Front. Med. ›› 2022, Vol. 16 ›› Issue (4) : 661 -664. DOI: 10.1007/s11684-021-0907-9
CORRESPONDENCE
CORRESPONDENCE

Answer for questions of repeated measurements of variance analysis and distribution test of data — Authors’ reply

Author information +
History +
PDF (263KB)

Cite this article

Download citation ▾
Dao Wen Wang, Li Ni, Hualiang Jiang. Answer for questions of repeated measurements of variance analysis and distribution test of data — Authors’ reply. Front. Med., 2022, 16(4): 661-664 DOI:10.1007/s11684-021-0907-9

登录浏览全文

4963

注册一个新账户 忘记密码

null

Thank the journal for sending us the Correspondence of Dr. Jie Wei for our article “Effects of Shuanghuanglian oral liquids on patients with COVID-19: a randomized, open-label, parallel-controlled, multicenter clinical trial” published in Frontiers of Medicine [1]. We appreciate Dr. Jie Wei for agreeing with most of the conclusions in our paper and we address Dr. Jie Wei’s comments carefully as below.

For Dr. Jie Wei’s first comment, “repeated measurements of variance analysis should be used in the random control trial when repeated measurements of the same observation indicator are required at different times.” To investigate whether the repeated measurements of variance analysis was needed, we did repeated measures ANCOVA in this study, using changes from baseline at different time points after the intervention as outcome, and the interventions and time as independent variables. The interaction between interventions and time was also examined. The results showed that the treatment time could independently affect the outcomes, but interaction between interventions and time were not significantly different among the treatment groups (Tab.1−Tab.5). Therefore, it would unlikely affect the authenticity of the original conclusions of the article.

For Dr. Jie Wei’s second comment, “the SW test is the most powerful test for all types of distribution and sample size.” We appreciate this comment. In this study, we used Kolmogorov–Smirnov test to determine the distribution of continuous data. According to the above comment, we used Shapiro–Wilk (SW) test conducted with SPSS (version 22.0, Armonk, USA) to check for normality and distribution of continuous data in our study again (Tab.6−Tab.9), and there were no much difference between these two tests. In addition, in our study, all continuous variables were tested by nonparametric statistical methods, which could be used for both normal distribution data and non-normal distribution data. It would not affect the results and conclusions in this study. We would like to thank Dr. Jie Wei for Dr. Jie Wei’s interests in our paper and for Dr. Jie Wei’s comments that we have addressed above.

References

[1]

NiL, WenZ, HuX, TangW, WangH, ZhouL, WuL, WangH, XuC, XuX, XiaoZ, LiZ, LiC, LiuY, DuanJ, ChenC, LiD, ZhangR, LiJ, YiY, HuangW, ChenY, ZhaoJ, ZuoJ, WengJ, JiangH, WangDW. Effects of Shuanghuanglian oral liquids on patients with COVID-19: a randomized, open-label, parallel-controlled, multicenter clinical trial. Front Med 2021; 15( 5): 704– 717

RIGHTS & PERMISSIONS

Higher Education Press

AI Summary AI Mindmap
PDF (263KB)

1802

Accesses

0

Citation

Detail

Sections
Recommended

AI思维导图

/