P-value and confidence interval: connection and difference, misuse and argument

Published on Jan. 28, 2023Total Views: 5001 times Total Downloads: 2898 times Download Mobile

Author: Shen HUANG Qing-Qing JIANG Shi-Qi WANG  Shi-Yi CAO

Affiliation: School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China

Keywords: P value Confidence interval Connection Difference Misuse Argument

DOI: 10.12173/j.issn.1004-4337.202212021

Reference: Huang S, Jiang QQ, Wang SQ, Cao SY. 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.[Article in Chinese]  Copied

Abstract
Full-text
References

Abstract

The P value and confidence interval are the two most widely used statistical infer-ence tools. The American Statistical Association issued a warning statement on the use of the P value due to the misuse and abuse of the P value. There are some mistakes in understanding the P value and confidence interval which caused the wrong use of the P value. Furthermore, the readers may have never considered the relationship and difference between the P value and confidence interval. There-fore, this paper expects to introduce the definition of P value and confidence interval in a simple way, and we also hope to analyze the relationship and difference between the P value and confidence interval, to help readers understand the P value and confidence interval correctly. In addition, this paper also lists the misuse and arguments about the P value and confidence interval, to help readers use the P value and confidence interval correctly in the future.

Full-text

Please download the PDF version to read the full text: download

References

1.Lytsy P. P in the right place: revisiting the evidential value of P-values[J]. J Evid Based Med, 2018, 11(4): 288-291. DOI: 10.1111/jebm.12319.

2.Tam CWM, Khan AH, Knight A, et al. How doctors conceptualise p values: a mixed methods study[J]. Aust J Gen Pract, 2018, 47(10): 705-710. DOI: 10.31128/AJGP-02-18-4502.

3.Goodman S. A dirty dozen: twelve p-value misconceptions[J]. Semin Hematol, 2008, 45(3): 135-140. DOI: 10.1053/j.seminhematol.2008.04.003.

4.Gao J. P-values - a chronic conundrum[J]. BMC Med Res Methodol, 2020, 20(1): 167. DOI: 10.1186/s12874-020-01051-6.

5.Lakens D. The practical alternative to the p value is the correctly used p value[J]. Perspect Psychol Sci, 2021, 16(3): 639-648. DOI: 10.1177/1745691620958012.

6.Palesch YY. Some common misperceptions about P values[J]. Stroke, 2014, 45(12): e244-e246. DOI: 10.1161/Strokeaha.114.006138.

7.Altman DG, Bland JM. How to obtain the P value from a confidence interval[J]. BMJ, 2011, 343: d2304. DOI: 10.1136/bmj.d2304.

8.Taggart DP, D'Amico R, Altman DG. Effect of arterial revascularisation on survival: a systematic review of studies comparing bilateral and single internal mammary arteries[J]. Lancet, 2001, 358(9285): 870-875. DOI: 10.1016/S0140-6736(01)06069-X.

9.Altman DG, Bland JM. How to obtain the confidence interval from a p value[J]. BMJ, 2011, 343: d2090. DOI: 10.1136/bmj.d2090.

10.Roy SK, Hossain MJ, Khatun W, et al. Zinc supplementation in children with cholera in Bangladesh: random-ised controlled trial[J]. BMJ, 2008, 336(7638): 266-268. DOI: 10.1136/bmj.39416.646250.AE.

11.Nuzzo R. Scientific method: statistical errors[J]. Nature, 2014, 506(7487): 150-152. DOI: 10.1038/506150a.

12.Chavalarias D, Wallach JD, Li AH, et al. Evolution of reporting p values in the biomedical literature[J]. JAMA, 2016, 315(11): 1141-1148. DOI: 10.1001/jama.2016.1952.

13.Wasserstein RL , Lazar NA. The ASA statement on p-Values: context, process, and purpose[J]. The American Statistician, 2016, 70(2): 129-133. DOI: 10.1080/ 00031305.2016.1154108.

14.Hopewell S, Loudon K, Clarke MJ, et al. Publication bias in clinical trials due to statistical significance or di-rection of trial results[J]. Cochrane Database Syst Rev, 2009, (1): MR000006. DOI: 10.1002/14651858.MR000006.pub3.

15.Greenland S, Senn SJ, Rothman KJ, et al. Statistical tests, p values, confidence intervals, and power: a guide to misinterpretations[J]. Eur J Epidemiol, 2016, 31(4): 337-350. DOI: 10.1007/s10654-016-0149-3.

16.Halsey LG, Curran-Everett D, Vowler SL, et al. The fickle p value generates irreproducible results[J]. Nat Methods, 2015, 12(3): 179-185. DOI: 10.1038/nmeth.3288.

17.Colquhoun D. An investigation of the false discovery rate and the misinterpretation of p-values[J]. Roy Soc Open Sci, 2014, 1(3): 140216. DOI: 10.1098/rsos.140216.

18.Lang JM, Rothman KJ, Cann CI. That confounded P-value[J]. Epidemiology, 1998, 9(1): 7-8. DOI: 10.1097/00001648-199801000-00004.

19.Berger JO, Berry DA. Statistical analysis and the illusion of objectivity[J/OL]. (1988-03-01) [2022-12-26]. https://si.biostat.washington.edu/sites/default/files/modules/BergerBerry.pdf.

20.Knol MJ, Pestman WR, Grobbee DE. The (mis)use of overlap of confidence intervals to assess effect modifi-cation[J]. Eur J Epidemiol, 2011, 26(4): 253-254.DOI: 10.1007/s10654-011-9563-8.

21.Morey RD, Hoekstra R, Rouder JN, et al. Continued misinterpretation of confidence intervals: response to Miller and Ulrich[J]. Psychon Bull Review, 2016, 23(1): 131-140. DOI: 10.3758/s13423-015-0955-8.

22.Tijssen JGP. More confidence intervals and fewer p values: a positive trend?[J]. J Am Coll Cardiol, 2021, 77(12): 1562-1563. DOI: 10.1016/j.jacc.2021.02.004.

23.Park SY. Replacing p values with confidence intervals may not achieve anything[J]. J Thorac Cardiovasc Surg, 2021, 161(4): 1379-1380. DOI: 10.1016/j.jtcvs.2020.04.139.