Welcome to visit Zhongnan Medical Journal Press Series journal website!

Home Articles Vol 37,2024 No.3 Detail

The size of P value does not equal to the magnitude of difference or  correlation

Published on Mar. 27, 2024Total Views: 419 times Total Downloads: 709 times Download Mobile

Author: ZHENG Qiaolan LIN Yanwei WANG Jingzhou

Affiliation: Journal Center, The Third Affiliated Hospital, Sun Yat-sen University, Guangzhou 510630, China

Keywords: P value t-test Chi-square test Pearson linear correlation analysis Logistic regression analysis

DOI: 10.12173/j.issn.1004-4337.202401131

Reference: Zheng QL, Lin YW, Wang JZ. The size of P value does not equal to the magnitude of difference or correlation[J]. Journal of Mathematical Medicine, 2024, 37(3): 158-163. DOI: 10.12173/j.issn.1004-4337.202401131[Article in Chinese]

  • Abstract
  • Full-text
  • References
Abstract

Objective  To explore the relationship between P value and the size of difference or correlation.

Methods  Fixing sample statistics including mean and standard deviation, sample rate, correlation coefficient and OR (95%CI), then the data of independent sample t-test, chi-square test for comparing two sample rates, Pearson linear correlation analysis and univariate Logistic regression analysis were simulated respectively to observe the difference of P value under different sample size.

Results  When the difference in statistics between two sample groups is the same or the statistics within a single sample group are consistent but the sample size is different, the obtained P values may be﹥0.05, between 0.001 and 0.05, or﹤0.001.

Conclusion  The P value is greatly affected by the sample size, and its size does not equal to the magnitude of difference or correlation.

Full-text
Please download the PDF version to read the full text: download
References

1.Wasserstein RL, Lazar NA. The ASA statement on p-values: context, process, and purpose[J]. Am Stat, 2016, 70(2): 129-133. DOI: 10.1080/00031305.2016.1154108.

2.周敏林. 临床试验中P值的意义及结果解读[J]. 肾脏病与透析肾移植杂志, 2017, 26(2): 170-173, 183. [Zhou ML. Interpretation of P value in clinical trials[J]. Chinese Journal of Nephrology, Dialysis & Transplantation, 2017, 26(2): 170-173, 183.] DOI: 10.3969/cndt.j.issn.1006-298X.2017.02.015.

3.杨灵敏. 分析超声诊断乳腺癌腋窝淋巴结转移的影像学表现及其临床效果[J]. 中国医药指南, 2023, 21(9): 106-108. [Yang LM. To analyze the imaging features and clinical effects of ultrasound diagnosis of axillary lymph node metastasis in breast cancer[J]. Guide of China Medicine, 2023, 21(9): 106-108.] DOI: 10.15912/j.cnki.gocm.2023.09.012.

4.王晓玲. 益肺健脾汤与三伏灸贴联合治疗老年慢性支气管炎的临床效果[J].中医临床研究, 2021, 13(25): 101-103. [Wang XL. Clinical effects of the Yifei Jianpi decoction plus Sanfu moxibustion plaster on chronic bronchitis in the elderly[J]. Clinical Journal of Chinese Medicine, 2021, 13(25): 101-103.] DOI: 10.3969/j.issn. 1674-7860.2021.25.030.

5.姚梦, 唐东辉, 白爽. 综合干预对肥胖男性青少年血管生成素样蛋白2和血管内皮功能的影响[J]. 中国学校卫生, 2021, 42(12): 1888-1891. [Yao M, Tang DH, Bai S. Effect of comprehensive intervention on ANGPTL2 and vascular endothelial function in obese male adolescents[J]. Chinese Journal of School Health, 2021, 42(12): 1888-1891.] DOI: 10.16835/j.cnki.1000-9817.2021.12.031.

6.中国新药杂志编辑部. 《中国新药杂志》投稿须知[EB/OL]. (2023-03-03) [2023-12-01]. [Editorial of Chinese Journal of New Drugs. Guideline of Chinese Journal of New Drugs [EB/OL]. (2023-03-03) [2023-12-01].] http://www.newdrug.cn/CN/column/column9.shtml.

7.万里, 孙劲楠, 丁佐奇. 封面论文和非封面论文的学术影响力对比研究——基于药学类核心期刊的实证研究[J]. 科技与出版, 2022(11): 145-151. [Wan L, Sun JN, Ding ZQ. Comparative study on academic influence of cover papers and non-cover papers—an empirical study based on pharmaceutical core journals[J]. Science-Technology and Publication, 2022(11): 145-151.] DOI: 10.16510/j.cnki.kjycb.20221012.009.

8.吴艳妮, 周春兰, 江霞, 等. 国内护理学统计源期刊论文中报告精确P值常见错误: P=0.000[J]. 编辑学报, 2016, 28(2): 133-134. [Wu YN, Zhou CL, Jiang X, et al. Common errors in reports on accurate P value in papers from domestic nursing journals[J]. Acta Editologica, 2016, 28(2): 133-134.] DOI: 10.16811/j.cnki.1001-4314. 2016.02.010.

9.汪媛, 张爽爽, 应倩, 等. 国内肿瘤学期刊论文中P值为零的误用分析[J]. 编辑学报, 2017, 29(1): 46-47. [Wang Y, Zhang SS, Ying Q, et al. Misuse of the P value equal to zero in papers of Chinese oncology journals[J]. Acta Editologica, 2017, 29(1): 46-47.] DOI: 10.16811/j.cnki.1001-4314.2017.01.015.

10.方积乾. 卫生统计学(第6版) [M]. 北京: 人民卫生出版社, 2008. [Fang JQ. Medical Statistic (6th edition) [M]. Beijing: People's Medical Publishing House, 2008.].

11.钱俊, 陈平雁. 假设检验中计算观察检验效能的意义的探讨[J]. 中国卫生统计, 2005, 22(3): 133-137. [Qian J, Chen PY. What's the meaning of observed power in hypothesis testing[J]. Chinese Journal of Health Statistics, 2005, 22(3): 133-137.] DOI: 10.3969/j.issn.1002-3674.2005.03.002.

12.王雅洁, 李亚琴. 医学科技论文中常见统计学问题分析及建议[J]. 护理研究, 2021, 35(10): 1757-1760. [Wang YJ, Li YQ. Analysis and suggestions on common statistical problems in medical scientific papers[J]. Chinese Nursing Research, 2021, 35(10): 1757-1760.] DOI: 10.12102/j.issn.1009-6493.2021.10.010.

13.Rumsey DJ. Statistics for dummies[M]. Hoboken NJ: Wiley Publishing, 2011.

14.冯国双. 统计学中P值的含义及其应用中的误解 [J]. 中华全科医师杂志, 2017, 16(1): 83-84. [Feng GS. The interpretation and misunderstanding about P value in statistics[J]. Chinese Journal of General Practitioners, 2017, 16(1): 83-84.] DOI: 10.3760/cma.j.issn.1671-7368. 2017.01.021.

15.Harrington D, D'Agostino RB Sr, Gatsonis C, et al. New guidelines for statistical reporting in the journal[J]. N Engl J Med, 2019, 381(3): 285-286. DOI: 10.1056/NEJMe1906559.

16.The New England Journal of Medicine. Statistical Reporting Guidelines[EB/OL]. [2023-12-09]. https://www.nejm.org/author-center/new-manuscripts.

17.相丹风, 高永, 周英智. 医学论文中成组t检验P值错误及其原因分析[J]. 中国科技期刊研究, 2018, 29(12): 1224-1228. [Xiang DF, Gao Y, Zhou YZ. P-value errors in two-sample t-test of medical papers and reason analysis[J]. Chinese Journal of Scientific and Technical Periodicals, 2018, 29(12): 1224-1228.] DOI: 10.11946/cjstp.201807300679.

18.郑巧兰, 林燕薇, 洪悦民, 等. 科技期刊编辑如何利用统计知识筛查学术不端行为[J]. 编辑学报, 2021, 33(1): 74-77. [Zheng QL, Lin YW, Hong YM, et al. How can editors of scientific journals use statistical method to screen academic misconduct[J]. Acta Editologica, 2021, 33(1): 74-77.] DOI: 10.16811/j.cnki.1001-4314.2021.01.017.

19.中国高校医学期刊论文统计报告规范编写组. 中国高校医学期刊论文统计报告推荐清单(2023版)[J]. 郑州大学学报(医学版), 2023, 58(6): 875-882. [Chinese university medical journal paper statistical report standard compilation group. Recommended list of statistical reports of medical journals in colleges and universities in China (2023 edition)[J]. Journal of Zhengzhou University (Medical Sciences), 2023, 58(6): 875-882.] DOI: 10.13705/j.issn. 1671-6825.2023.10.004.

20.黄申, 蒋青青, 王世琦, 等. P值和置信区间: 联系与区别、误用与争论[J]. 数理医药学杂志, 2023, 36(1): 3-8. [Huang S, Jiang QQ, Wang SQ, et al. P-value and confidence interval: connection and difference, misuse and argument[J]. Journal of Mathematical Medicine, 2023, 36(1): 3-8.] DOI: 10.12173/j.issn.1004-4337.202212021.

21.彭佳师. P值争论对生物统计学课程教学的影响[J]. 生物学杂志, 2020, 37(6): 120-122, 129. [Peng JS. P-value controversy and its impact on biostatistics teaching[J]. Journal of Biology, 2020, 37(6): 120-122, 129.] DOI: 10.3969/j.issn.2095-1736.2020.06.120.

22.李晓炜, 王春燕, 王希营, 等. 医学期刊青年编辑统计学素养的影响因素和提升策略[J]. 编辑学报, 2020, 32(2): 225-227. [Li XW, Wang CY, Wang XY, et al. Influence factors and promotion strategies of statistical accomplishment for young editors of medical journals[J]. Acta Editologica, 2020, 32(2): 225-227.] DOI: 10.16811/j.cnki.1001-4314.2020.02.028.

23.李玥, 栾嘉, 邓强庭, 等. 编辑因素对我国中文医学期刊学术质量影响的实证研究[J]. 中国科技期刊研究, 2023, 34(3): 288-296. [Li Y, Luan J, Deng QT, et al. Empirical study on the influence of factors related to editors on the academic quality of Chinese medical journals[J]. Chinese Journal of Scientific and Technical Periodicals, 2023, 34(3): 288-296.] DOI: 10.11946/cjstp. 202210100766.

24.李伟. 2016—2022年中国科技期刊编辑继续教育培训的特征分析[J]. 中国科技期刊研究, 2023, 34(5): 647-652. [Li W. Characteristics of continuing education training for Chinese scientific journal editors from 2016 to 2022[J]. Chinese Journal of Scientific and Technical Periodicals, 2023, 34(5): 647-652.] DOI: 10.11946/cjstp.202303090147.

25.易耀森. 医学期刊稿约中统计报告规范的现状及完善建议[J]. 编辑学报, 2022, 34(5): 510-514. [Yi YS. Constructive suggestions on statistical reporting standards of author guidelines inmedical journals[J]. Acta Editologica, 2022, 34(5): 510-514.] DOI: 10.16811/j.cnki.1001-4314.2022.05.008.

Popular papers
Last 6 months