Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You and Your Team.

Learn More →

Errors in Data and Statistical Significance

Errors in Data and Statistical Significance Letters The final paragraph of the Discussion was revised to read “Limitations include a at admission. However, the calculated odds ratios in Table 2 lack of sufficient information on newborns to determine vertical transmission. The were not correct and do not correspond to these numbers. The lack of association between cesarean delivery and risk of NICU admission may have correct crude odds ratio is 1.7 (95% CI, 0.5-5.8; P = .21) and the been related to the lack of statistical power. Also, the 95% CIs around the odds corresponding adjusted odds ratio is 1.2 (95% CI, 0.3-4.5; ratios for cesarean birth and clinical deterioration were wide and the estimates frag- ile.” In Table 2, for the row labeled “Neonatal intensive care unit admission,” the P = .76). The association is therefore not significant. The er- odds ratio and 95% CI for asymptomatic/mild COVID-19 symptoms were revised ror is related to a miscalculation (ie, use of the number 2 in- to “1.7 (0.5-5.8)” and the adjusted odds ratio and 95% CI were revised to “1.2 stead of 8), and the numbers of NICU admissions are correct. (0.3-4.5).” This article was corrected online. We believe that the lack of significant association http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png JAMA American Medical Association

Errors in Data and Statistical Significance

JAMA , Volume 324 (3) – Jul 21, 2020

Errors in Data and Statistical Significance

Abstract

Letters The final paragraph of the Discussion was revised to read “Limitations include a at admission. However, the calculated odds ratios in Table 2 lack of sufficient information on newborns to determine vertical transmission. The were not correct and do not correspond to these numbers. The lack of association between cesarean delivery and risk of NICU admission may have correct crude odds ratio is 1.7 (95% CI, 0.5-5.8; P = .21) and the been related to the lack of statistical power....
Loading next page...
 
/lp/american-medical-association/errors-in-data-and-statistical-significance-9uAy53VJKw
Publisher
American Medical Association
Copyright
Copyright 2020 American Medical Association. All Rights Reserved.
ISSN
0098-7484
eISSN
1538-3598
DOI
10.1001/jama.2020.12271
Publisher site
See Article on Publisher Site

Abstract

Letters The final paragraph of the Discussion was revised to read “Limitations include a at admission. However, the calculated odds ratios in Table 2 lack of sufficient information on newborns to determine vertical transmission. The were not correct and do not correspond to these numbers. The lack of association between cesarean delivery and risk of NICU admission may have correct crude odds ratio is 1.7 (95% CI, 0.5-5.8; P = .21) and the been related to the lack of statistical power. Also, the 95% CIs around the odds corresponding adjusted odds ratio is 1.2 (95% CI, 0.3-4.5; ratios for cesarean birth and clinical deterioration were wide and the estimates frag- ile.” In Table 2, for the row labeled “Neonatal intensive care unit admission,” the P = .76). The association is therefore not significant. The er- odds ratio and 95% CI for asymptomatic/mild COVID-19 symptoms were revised ror is related to a miscalculation (ie, use of the number 2 in- to “1.7 (0.5-5.8)” and the adjusted odds ratio and 95% CI were revised to “1.2 stead of 8), and the numbers of NICU admissions are correct. (0.3-4.5).” This article was corrected online. We believe that the lack of significant association

Journal

JAMAAmerican Medical Association

Published: Jul 21, 2020

References