A comparison of parametric and non-parametric statistical testsBMJ 2015; 350 doi: https://doi.org/10.1136/bmj.h2053 (Published 17 April 2015) Cite this as: BMJ 2015;350:h2053
- Philip Sedgwick, reader in medical statistics and medical education
- 1Institute for Medical and Biomedical Education, St George’s, University of London, London, UK
Researchers investigated the effectiveness of corticosteroids in reducing respiratory disorders in infants born at 34-36 weeks’ gestation. A randomised placebo controlled trial was performed. The intervention was treatment with betamethasone, 12 mg intramuscularly daily for two consecutive days at 34-36 weeks of pregnancy. Participants were 320 women at 34-36 weeks of pregnancy who were at risk of imminent premature delivery. Women were randomised to the intervention (n=163) or placebo (n=157).1
The primary outcome was the incidence of neonatal respiratory disorders, including respiratory distress syndrome and transient tachypnoea. Secondary outcomes included perinatal measurements in the infant, including birth weight, plus Apgar score at five minutes. Statistical hypothesis testing used a two sided alternative and a critical level of significance of 0.05 (5%). Distributional assumptions were verified before statistical testing. The rate of respiratory distress syndrome was higher in the intervention group than in the control group (two (1.4%) v one (0.8%)), although the difference was not significant (P=0.54), as was the rate of transient tachypnoea (34 (24%) v 29 (22%); P=0.77). Babies born to mothers in the intervention group had a higher mean birth weight, although the difference was not significant (2640 (standard deviation 445) v 2627 (452) g; Student’s t test P=0.80). There was no difference between the intervention and control groups in Apgar scores at five minutes (median 9 (interquartile range 9-10) v 9 (9-10); Mann-Whitney U test P=0.77).
The researchers concluded that antenatal treatment with corticosteroids at 34-36 weeks of pregnancy does not reduce the incidence of respiratory disorders in newborn infants.
Which of the following statements, if any, are true?
a) The use of the Student’s t test assumed that birth weight was normally distributed in the population for each treatment group
b) The use of the Mann-Whitney U test assumed that the variance of Apgar …