BOF: 2.62
In a cohort study, the
occurrence of infertility was recorded for smokers and non-smokers in the
reproductive age group, over a decade. The difference in incidences between
the 2 groups was reported to be significant at the p > 0.05 level. Which is
the most appropriate interpretation that can be made from the results of this
study?
a) The null
hypothesis can be rejected; results may have occurred by chance up to 5% of
the time
b) A
significant difference between the 2 groups may occur 5% of the time or less
c) The null
hypothesis may be accepted as the difference between the 2 groups is only 5%
of the time
d) The
alternate hypothesis may be rejected
e) A causal
relationship between exposure and outcome may be established at significance
level 0.05
Answer:
a)
Most researchers use the 0.05
significance value to reject the null hypothesis. This is arbitrary but
universally accepted as the probability that differences observed are purely
due to chance is less than 5% at this significance level. The larger the
numbers and longer the study (especially for observational studies such as a
cohort study) the more meaningful the results if p < 0.05.
Author:
Dr. Sumantra Ray R.Nutr.
MBBS (Hons), DNHE, MICR
(UK), MRIPH (UK)
Clinical Research & Teaching Fellow
The Institute of Cardiovascular Research
University of Dundee Division of Medicine & Therapeutics
/ NHS Tayside
Honorary Invited Lecturer
Clinical Research Centre & Centre for Public Health
Nutrition Research
University of Dundee College of Medicine, Dentistry &
Nursing / NHS Tayside
Ninewells Hospital & Medical School
Dundee DD1 9SY
The Institute of Cardiovascular Research
University of Dundee Division of Medicine & Therapeutics
/ NHS Tayside
Honorary Invited Lecturer
Clinical Research Centre & Centre for Public Health
Nutrition Research
University of Dundee College of Medicine, Dentistry &
Nursing / NHS Tayside
Ninewells Hospital & Medical School
Dundee DD1 9SY
