Clinical trials and p-values, beware of the extremes
-
Ton J. Cleophas
Abstract
Background: In randomized controlled trials, prior to statistical analysis, the data are checked for outliers and erroneous data. Statistical tests are, traditionally, not very good at distinguishing between errors and outliers, but they should be able to point out main endpoint results closer to expectation than compatible with random sampling.
Objectives: To explain from hypothesized and published examples why extreme p-values like p>0.95 and p<0.0001 may indicate that sampling was not completely random.
Results: Extreme p-values can be readily observed in recent issues ofhigh-impact journals. A p-value >0.95 literally means that we have a >95% chance off inding a result less close to expectation and, consequently, a <5% chance off inding a result this close or closer. Often in studies a statistical power of 80% is agreed upon, corresponding with a p-value of approximately 0.01. The ultimate p-value may then be a bit larger or smaller. However, a p-value much smaller than 0.01 will be rarely observed, because it would indicate that the study is overpowered. If the p-values can be assumed to follow a normal distribution around 0.01, then we will have a less than 5% chance ofobserving a p-value of <0.0001.
Conclusions: In randomized controlled trials, main endpoint p-values larger than p=0.95 will be rare, because they would indicate similarities closer than compatible with a normal distribution ofrandom data samples. Also very low p-values like p<0.0001 will be rarely encountered, because it would mean that the trial was overpowered and should have had a smaller sample size. It would seem appropriate, therefore, to require investigators to explain such results and to consider rejecting the research involved. So far, in randomized controlled trials the null-hypothesis is generally rejected at p<0.05. Perhaps we should consider rejecting the entire study if the main endpoint p-values are >0.95 or <0.0001.
Copyright © 2004 by Walter de Gruyter GmbH & Co. KG
Articles in the same Issue
- Phage-displayed recombinant single-chain antibody fragments with high affinity for cholesteryl ester transfer protein (CETP): cDNA cloning, characterization and CETP quantification
- Stem cell factor and macrophage-colony stimulating factor in patients with pancreatic cancer
- Modulation of plasma fibrinogen levels in acute-phase response after hepatectomy
- Anti-nucleosome, anti-chromatin, anti-dsDNA and anti-histone antibody reactivity in systemic lupus erythematosus
- Expression of activation molecules in neutrophils, monocytes and lymphocytes from patients with unstable angina treated with stent implantation
- Acid ribonuclease and alkaline ribonuclease isoenzymes in plasma of patients with decreased glomerular filtration rate
- Is calcium oxalate nucleation in postprandial urine of males with idiopathic recurrent calcium urolithiasis related to calcium phosphate nucleation and the intensity of stone formation? Studies allowing insight into a possible role of urinary free citrate and protein
- Significance of consecutive international normalized ratio (INR) outcomes using statistical control rules in long-term anticoagulated patients. Optimization of laboratory monitoring and interpretation of borderline measurements
- Clinical trials and p-values, beware of the extremes
- Age dependence of serum β-N-acetylhexosaminidase (NAG) activity
- Elevated plasma total homocysteine in centenarians
- New methodology of influential point detection in regression model building for the prediction of metabolic clearance rate of glucose
- Intra-laboratory analytical variability of biochemical markers of fibrosis (Fibrotest) and activity (Actitest) and reference ranges in healthy blood donors
- The glutathione S-transferase polymorphisms in a control population and in Alzheimer's disease patients
- Near-patient testing for infection using urinalysis and immuno-chromatography strips
- Long-distance mountain biking does not disturb the measurement of total, free or complexed prostate-specific antigen in healthy men
- Development of a new colorimetric method for protein S activity measurement
- Re.: Correction to the IFCC primary reference method for the measurement of catalytic activity concentration of enzymes at 37C- part 2: reference procedure for the measurement of creatine kinase. Clin Chem Lab Med 2002;40:635-42
- Meetings and Awards
Articles in the same Issue
- Phage-displayed recombinant single-chain antibody fragments with high affinity for cholesteryl ester transfer protein (CETP): cDNA cloning, characterization and CETP quantification
- Stem cell factor and macrophage-colony stimulating factor in patients with pancreatic cancer
- Modulation of plasma fibrinogen levels in acute-phase response after hepatectomy
- Anti-nucleosome, anti-chromatin, anti-dsDNA and anti-histone antibody reactivity in systemic lupus erythematosus
- Expression of activation molecules in neutrophils, monocytes and lymphocytes from patients with unstable angina treated with stent implantation
- Acid ribonuclease and alkaline ribonuclease isoenzymes in plasma of patients with decreased glomerular filtration rate
- Is calcium oxalate nucleation in postprandial urine of males with idiopathic recurrent calcium urolithiasis related to calcium phosphate nucleation and the intensity of stone formation? Studies allowing insight into a possible role of urinary free citrate and protein
- Significance of consecutive international normalized ratio (INR) outcomes using statistical control rules in long-term anticoagulated patients. Optimization of laboratory monitoring and interpretation of borderline measurements
- Clinical trials and p-values, beware of the extremes
- Age dependence of serum β-N-acetylhexosaminidase (NAG) activity
- Elevated plasma total homocysteine in centenarians
- New methodology of influential point detection in regression model building for the prediction of metabolic clearance rate of glucose
- Intra-laboratory analytical variability of biochemical markers of fibrosis (Fibrotest) and activity (Actitest) and reference ranges in healthy blood donors
- The glutathione S-transferase polymorphisms in a control population and in Alzheimer's disease patients
- Near-patient testing for infection using urinalysis and immuno-chromatography strips
- Long-distance mountain biking does not disturb the measurement of total, free or complexed prostate-specific antigen in healthy men
- Development of a new colorimetric method for protein S activity measurement
- Re.: Correction to the IFCC primary reference method for the measurement of catalytic activity concentration of enzymes at 37C- part 2: reference procedure for the measurement of creatine kinase. Clin Chem Lab Med 2002;40:635-42
- Meetings and Awards
