Webmedcentral.us

Meaning of p-value in Medical Research
Corresponding Author:
Dr. Brijesh Sathian,
Assistant Professor & Managing and Chief Editor NJE, Community Medicine, Manipal College of Medical
Sciences, Department of Community Medicine, Manipal College of Medical Sciences, 155 - Nepal
Submitting Author:
Dr. Brijesh Sathian,
Assistant Professor & Managing and Chief Editor NJE, Community Medicine, Manipal College of Medical
Sciences, Department of Community Medicine, Manipal College of Medical Sciences, 155 - Nepal
Article ID: WMC003338
Article Type: Review articles
Submitted on:06-May-2012, 05:57:50 PM GMT Published on: 07-May-2012, 04:21:33 PM GMT
Article URL:
Subject Categories:BIOSTATISTICS
Keywords:Medical Research, Testing of Hypothesis, p-value
How to cite the article:Sathian B, Sreedharan J. Meaning of p-value in Medical Research . WebmedCentral
BIOSTATISTICS 2012;3(5):WMC003338
Copyright: This is an open-access article distributed under the terms of the , which permits unrestricted use, distribution, and reproduction in any medium, provided the original
author and source are credited.
WebmedCentral > Review articles Page 1 of 5
Downloaded from http://www.webmedcentral.com on 07-May-2012, 04:21:33 PM Meaning of p-value in Medical Research
Author(s): Sathian B, Sreedharan J
choosing H if the actual observations fall in the critical region, and choosing H if they do not. More clearly in large sample test, we will check the calculated value of the test formula is greater than the tabular value from Any researcher begins the research with null the Z- table. Value is 1.96 for 95% and 2.58 for 99% hypothesis and alternative hypothesis. Null will be for Confidence Interval. The other method is so called supporting the old fact and alternative will be for the software adopted method or widely used method p- new fact invented/ doubted by the researcher/ scientist.
value. It is described by Cox and Hinkley. Several Next step is to select one of this scientifically by using people described p-value in several manners but the science of statistics. For that the researcher should finally it is the supporting probability of Null Hypothesis calculate the likelihood or probability that the difference observed in the study, however big or small, could have arisen purely by chance. This probability is A p-value is a measure of how much evidence we known as p-value and it is sufficiently small, you can have against the null hypothesis. The null hypothesis conclude that you have obtained a statistically H , represents the hypothesis of no change or no significant difference. Confidence intervals and effect, population mean and sample mean equal, p-values take as their starting point the results population proportion or sample proportion equal. It is observed in a study. Crucially, we must check first that also known as producer’s hypothesis, if customer is doing research. The smaller the p-value, the more evidence we have against H . It is also a measure of how likely we are to get a certain sample result or a result more extreme, assuming H is true. Medical
research involves making a hypothesis and then
“Medicine is a science of uncertainty and an art of collecting data to test that hypothesis. The p-value
probability”, mused William Osler. Medical journals measures consistency by calculating the
are a confluence of medicine, science and probability of observing the results from your
journalism—and are expected to have the values of all sample of data or a sample with results more
three. Medical journals differ fundamentally from extreme, assuming the null hypothesis is true. We
scientific journals in that the former is read mainly by will reject H when p-value is less than 0.05.
practising doctors and not by scientists. Medical Sometimes, though, researchers will use a stricter journals will continue to be the main vehicle of cut-off (e.g., 0.01) or a more liberal cut-off (e.g., 0.10).
scientific information for years to come, particularly The general rule is that a small p-value is evidence
where access to computer and internet facilities are against the null hypothesis while a large p-value
relatively limited. Nowadays the output—and means little or no evidence against the null
rewards— of research are based almost entirely on hypothesis.
published papers in scientific journals. Scientists in Suppose that a Viagra medicine company alleges that low-income and middle income settings want an only 40% of all patients who take it have a side
opportunity to analyze data for their populations effect of headache. If, you prescribed Viagra for
according to their own concerns. They want to be in effective treatment for Erectile Dysfunction and believe the frontlines of national and global communications that the adverse event rate is much higher in patients.
about their country’s experiences. The basic In a sample of 100 patients, all hundred have a
assumption of inferential statistics is that we’re headache. The data supports your belief because
observing a sample of finite size drawn from a it is inconsistent with the assumption of a 40%
population that is effectively infinite. By making headache rate. It would be like tossing a coin 100
observations about the sample, we are trying to make times and getting heads each time. The p-value, the generalizations about the population. The probability of getting a sample result of 100 headache
Neyman-Pearson theory of hypothesis testing events in all 100 patients assuming that the headache
addresses the problem of choosing between two event rate is 40%, is a measure of this inconsistency.
statistical hypotheses, H and H . The solution involves The p-value, 0.00000001, is small enough that we
selecting, before the data are observed, a set of would reject the hypothesis that the headache event
potential observations (the critical region), then WebmedCentral > Review articles Page 2 of 5
Downloaded from http://www.webmedcentral.com on 07-May-2012, 04:21:33 PM rate was only 40%. Researcher see a large p- value,
4. Sackett DL, Richardson WS, Rosenberg W, he will decide null hypothesis is wrong. But if the
Haynes RB. Evidence based medicine: how to sample size is not adequate and the sample is not
practice and teach EBM. London: Churchill the proper representative part then automatically p
value will be high even though null hypothesis
5. Crombie IK. The pocket guide to critical clinically right. So, the researcher should also look
appraisal. London: BMJ Publishing, 1996.
for one of two things: First one is the power of the test 6. Brennan P, Croft P. Interpreting the results of which confirms that the sample size in that study was observa- tional research: chance is not such a fine adequate for detecting a clinically relevant difference.
Second one is confidence interval that lies entirely
7. Burls A. What is critical appraisal? London: within the range of clinical indifference. Researcher Hayward Medical Communications, 2009.
should also be cautious about a small p-value, but for 8. Gardner MJ, Altman DG. Confidence intervals different reasons. In some situations, the sample
rather than p values: estimation rather than hypothesis size is so large than required then the researcher
can prove the medically insignificant result
9. Last JM. A dictionary of epidemiology. Oxford: statistically significant [1-30].
International Journal of Epidemiology, 1988.
Consultant is reading a research paper for finding a 10. The Heart Outcomes Prevention Evaluation better drug for a particular disease. In a good research S t u d y I n v e s t i g a t o r s . E f f e c t s o f a n paper author of the research paper should inform you angiotensin-converting- enzyme inhibitor, ramipril, on what size difference is clinically relevant and what cardiovascular events in high-risk patients. N Engl J sized difference is trivial. But all the manuscripts are not good. So, the reader has to find out how much of
11. Altman DG, Bland JM. Absence of evidence is a difference would be large enough. Then compare
not evi- dence of absence. BMJ 1995; 311: 485.
this to the confidence interval in the research paper. If
12. Guyatt GH, Sackett DL, Cook DJ. Users’ guides both limits of the confidence interval are smaller
to the medical literature. II. How to use an article about than a clinically relevant difference, then
therapy or prevention. B. What were the results consultant should not change the drug, no matter
and will they help me in caring for my patients? what the p-value tells.
13. Mittal A , Sathian B, Chandrasekharan N , Lekhi A, Farooqui M S, Pandey N. Diagnostic Accuracy of Serological Markers in Viral Hepatitis and Non Alcoholic Fatty Liver Disease. A Comparative Study in P-value is a very important concept for any
Tertiary Care Hospital of Western Nepal. Nepal medical researcher for understanding the research
Journal of Epidemiology 2011;1(2): 60-3.
articles published and for making correct
14. Mittal A, Sathian B, Kumar A, Chandrasekharan N, statistical and medical inferences in his own paper.
Dwedi S. The Clinical Implications of Thyroid Researcher should not interpret the p-value as the
Hormones and its Association with Lipid Profile: A probability that the null hypothesis is true. Such an
Comparative Study from Western Nepal. Nepal interpretation is problematic because a hypothesis is Journal of Epidemiology 2010; 1(1): 11-6.
not a random event that can have a probability. 15. Sathian B. Methodological Rigors in Medical Journals from Developing Countries: An Appraisal of the Scenario in Asia. Nepal Journal of Epidemiology 1 6 . S a t h i a n B , S r e e d h a r a n J , M i t t a l A , 1. Davies HT. Interpreting measures of treatment Chandrasekharan N, Baboo NS, Abhilash ES, et.al.
effect. Hosp Med 1998; 59: 499–501.
Case Control Studies in Medical Research. Nepal 2. Guyatt GH, Sackett DL, Cook DJ. Users’ guides to Journal of Epidemiology 2011;1(3): 77-8.
the medical literature. II. How to use an article about 17. Sathian B. Reporting dichotomous data using therapy or prevention. A. Are the results of the study Logistic Regression in Medical Research: The scenario in developing countries. Nepal Journal of 3. Sackett DL, Haynes RB, Guyatt GH, Tugwell P.
Clinical epidemiology: A basic science for clinical 18. Sathian B, Sreedharan J, Baboo NS, Sharan K, medicine, 2nd edn. Boston, Massachusetts: Little, Abhilash E S, Rajesh E. Relevance of Sample Size Determination in Medical Research. Nepal Journal of WebmedCentral > Review articles Page 3 of 5
Downloaded from http://www.webmedcentral.com on 07-May-2012, 04:21:33 PM Mellitus: Risk Factors, Pathophysiology and with its 19. Roy B, Banerjee I, Sathian B, Mondal M, Saha CG.
Clinical Implications: A Hospital Based Case Control Blood Group Distribution and Its Relationship with Study in Western Region of Nepal. Nepal Journal of Bleeding Time and Clotting Time: A Medical School Based Observational Study among Nepali, Indian and 29. Banerjee I, Roy B, Banerjee I, Sathian B, Mondol Srilankan Students. Nepal Journal of Epidemiology M, Saha A. Depression and its Cure : A Drug Utilization Study from a Tertiary Care Centre of 20. Sreeramareddy CT, Ramakrishnareddy N, Harsha Western Nepal. Nepal Journal of Epidemiology 2011;1 KumarHN, Sathian B, Arokiasamy JT. Prevalence, distribution andpredictors of tobacco smoking and 30. Mittal A, Sathian B, Kumar A, Chandrasekharan N, chewing in Nepal: a secondary data analysis of Nepal Sunka A. Diabetes mellitus as a Potential Risk Factor Demographic and HealthSurvey-2006. Substance for Renal Disease among Nepalese: A Hospital Based Abuse Treatment, Prevention, and Policy 2011;6:33.
Case Control Study. Nepal Journal of Epidemiology 21. Roy B, Banerjee I, Sathian B, Mondal M, Kumar SS, Saha CG. Attitude of Basic Science Medical Students towards Post Graduation in Medicine and Surgery: A Questionnaire based Cross-sectional Study from Western Region of Nepal. Nepal Journal of 22. Banerjee I, Roy B, Sathian B, Banerjee I, Kumar SS, Saha A. Medications for Anxiety: A Drug utilization study in Psychiatry Inpatients from a Tertiary Care Centre of Western Nepal. Nepal Journal of 23. Mittal A, Sathian B, Kumar A, Chandrasekharan N, Farooqui MS, Singh S, Yadav KS. Hyperuricemia as an Additional Risk Factor for Coronary Artery Disease: A Hospital Based Case Control Study in Western Region of Nepal. Nepal Journal of Epidemiology 2 4 . B a s h a A S , M a t h e w E , S r e e d h a r a n J , Muttappallymyalil J, Sharbatti AS, Shaikh BR. Pattern of Blood Pressure Distribution among University Students in Ajman, United Arab Emirates. Nepal Journal of Epidemiology 2011;1(3):86-9.
25. Banerjee I, Jauhari AC, Bista D, Johorey AC, Roy B, Sathian B. Medical Students View about the Integrated MBBS Course: A Questionnaire Based Cross-sectional Survey from a Medical College of Kathmandu Valley. Nepal Journal of Epidemiology 26. Mittal A, Sathian B, Poudel B, Farooqui MS, Chandrasekharan N, Yadav KS. The Significance of Hepatobiliary Enzymes for Differentiating Liver and Bone Diseases: A Case Control Study from Manipal Teaching Hospital of Pokhara Valley. Nepal Journal of 27. Poudel B, Mittal A, Yadav BK, Sharma P, Jha B, Raut KB. Estimation and Comparison of Serum Levels of Sodium, Potassium, Calcium and Phosphorus in Different Stages of Chronic Kidney Disease. Nepal Journal of Epidemiology 2011;1 (5): 160-7.
28. Mittal A, Sathian B, Chandrasekharan N, Lekhi A, Rahib R, Dwedi S. Hepatic Steatosis and Diabetes WebmedCentral > Review articles Page 4 of 5
Downloaded from http://www.webmedcentral.com on 07-May-2012, 04:21:33 PM This article has been downloaded from WebmedCentral. With our unique author driven post publication peer review, contents posted on this web portal do not undergo any prepublication peer or editorial review. It is completely the responsibility of the authors to ensure not only scientific and ethical standards of the manuscript but also its grammatical accuracy. Authors must ensure that they obtain all the necessary permissions before submitting any information that requires obtaining a consent or approval from a third party. Authors should also ensure not to submit any information which they do not have the copyright of or of which they have transferred Contents on WebmedCentral are purely for biomedical researchers and scientists. They are not meant to cater to the needs of an individual patient. The web portal or any content(s) therein is neither designed to support, nor replace, the relationship that exists between a patient/site visitor and his/her physician. Your use of the WebmedCentral site and its contents is entirely at your own risk. We do not take any responsibility for any harm that you may suffer or inflict on a third person by following the contents of this website.
WebmedCentral > Review articles Page 5 of 5

Source: http://webmedcentral.us/wmcpdf/Article_WMC003338.pdf