Confidence Intervals for Reporting Results of Clinical Trials
Annals of Internal MedicinePublished 1 September 1986
Richard Simon
Citations421
SJR quartileQ1
SJR score3.38
SNIP3.27
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
Tests of statistical significance are often used by investigators in reporting the results of clinical research. Although such tests are useful tools, the significance levels are not appropriate indices of the size or importance of differences in outcome between treatments. Lack of "statistical significance" can be misinterpreted in small studies as evidence that no important difference exists. Confidence intervals are important but underused supplements to tests of significance for reporting the results of clinical investigations. Their usefulness is discussed here, and formulas are presented for calculating confidence intervals with types of data commonly found in clinical trials.
Keywords
MedicineDecision SciencesMathematics
Springer series in statisticsNonparametric Estimation from Incomplete Observations
45,533 Citations1992Edward L. Kaplan, Paul Meier
Journal of the Royal Statistical Society Series B (Statistical Methodology)Regression Models and Life-Tables
39,259 Citations1972D. R. Cox
Journal of the American Statistical AssociationNonparametric Estimation from Incomplete Observations
39,052 Citations1958Edward L. Kaplan, Paul Meier
British Journal of CancerDesign and analysis of randomized clinical trials requiring prolonged observation of each patient. II. Analysis and examples
8,392 Citations1977Richard Peto, M. C. Pike +8 more
Efficient methods of analysis of randomized clinical trials in which the authors wish to compare the duration of survival among different groups of patients are described.
Progress in Cardiovascular DiseasesBeta blockade during and after myocardial infarction: An overview of the randomized trials
3,239 Citations1985Salim Yusuf, Richard Peto +3 more
The aim has been not only to review the 65-odd randomized beta blocker trials but also to demonstrate that when many randomized trials have all applied one general approach to treatment, it is often not appropriate to base inference on individual trial results.
New England Journal of MedicineThe Importance of Beta, the Type II Error and Sample Size in the Design and Interpretation of the Randomized Control Trial
1,641 Citations1978Jennie A. Freiman, Thomas C. Chalmers +2 more
BiometricsA Confidence Interval for the Median Survival Time
892 Citations1982Ron Brookmeyer, John Crowley
BiometricsTesting for Qualitative Interactions between Treatment Effects and Patient Subsets
646 Citations1985Mitchell H. Gail, Richard Simon
A likelihood ratio test is developed to test for qualitative interactions and a non-crossover interaction arises when there is variation in the magnitude, but not in the direction, of treatment effects among subsets.
New England Journal of MedicineReporting on Methods in Clinical Trials
500 Citations1982Rebecca DerSimonian, L. Joseph Charette +2 more
Survey of clinical trials published in the New England Journal of Medicine, the Lancet, and the British Medical Journal found information about statistical analyses, statistical methods used, and random allocation of subjects was reported, yet only 19 per cent reported the method of randomization.
BiometricsAn Improved Approximate Formula for Calculating Sample Sizes for Comparing Two Binomial Distributions
435 Citations1978John T. Casagrande, Malcolm C. Pike +1 more
Fisher's "exact" (one-sided) test may be used to test the null hypothesis p1 = p2, against the alternative hypothesis that pl > p2.
Journal of neurosurgeryPrediction of survival in glioma patients by means of positron emission tomography
410 Citations1985Nicholas J. Patronas, Giovanni Di Chiro +5 more
It is postulated that PET-FDG scans reflect the biological behavior of high-grade astrocytomas and may be used to predict the survival time of patients harboring such neoplasms.
New England Journal of MedicineA Show of Confidence
303 Citations1978Kenneth J. Rothman
The preoccupation with significance tests is embodied in the focus on whether the P value is less than 0.05; results are considered "significant" or "not significant" according to whether or not the P values are less than or greater than this value.
Journal of Chronic DiseasesEstimation of confidence limits for the cumulative probability of survival in life table analysis
288 Citations1978Kenneth J. Rothman
Cutler and Ederer illustrated how the life table approach could provide considerably more information on 5-yr survival than would be available from only those subjects followed for at least 5 yr.
Journal of Chronic DiseasesPlanning the duration of a comparative clinical trial with loss to follow-up and a period of continued observation
269 Citations1981Larry Rubinstein, Mitchell H. Gail +1 more
A method is developed to compute the approximate trial length required to assure a desired statistical power for given significance level, hazard ratio, accrual rate, loss to follow-up rate, and length of the period of continued observation in the Mantel-Haenszel test.
BMJMisuse of statistical methods: critical assessment of articles in BMJ from January to March 1976.
239 Citations1977S M Gore, Iolen Jones +1 more
Sixty-two reports that appeared as Papers and Originals in 13 consecutive issues of the British Medical journal included statistical analysis; thirty-two had statistical errors of one kind or another; in 18 fairly serious faults were discovered.
Statistics in MedicineStatistics in medical journals
228 Citations1982Douglas G. Altman
The general standard of statistics in medical journals is poor and the reasons for this are considered with illustrations of the types of error that are common, and the consequences of incorrect statistics in published papers are discussed.
Archives of Internal MedicineWhen Was a 'Negative' Clinical Trial Big Enough?
215 Citations1985Allan S. Detsky
This work suggests that this "prospective" sample size calculation is incorrect, for once the trial is over the authors have "hard" data from which to estimate the actual size of the treatment effect.
British Journal of Clinical PharmacologyPatient subsets and variation in therapeutic efficacy.
132 Citations1982Richard Simon
In order to obtain the degree of reliability usually demanded of clinical therapeutic evaluations, "statistically significant' interactions between relative treatment efficacy and subsets should be demonstrated.
Journal of the American Statistical AssociationA Comparison of Some Approximate Confidence Intervals for the Binomial Parameter
128 Citations1979B. K. Ghosh
BiometricsA Comparison of Reflected Versus Test-Based Confidence Intervals for the Median Survival Time, Based on Censored Data
85 Citations1984Eric Slud, David P. Byar +1 more
The small-sample performance of some recently proposed nonparametric methods of constructing confidence intervals for the median survival time, based on randomly right-censored data, is compared with that of two new methods.
BiometricsApproximate Confidence Intervals for Probabilities of Survival and Quantiles in Life-Table Analysis
81 Citations1982James R. Anderson, Leslie Bernstein +1 more
The proposed confidence limits are shown to be asymptotically correct for continuous survival data, and the intervals suggested by Rothman are preferred for smaller samples.
Journal of Chronic DiseasesSample size considerations for non-randomized comparative studies
80 Citations1980Robert Makuch, Richard Simon
The equations and tables presented in this paper reflect the extent to which the number of patients required to receive the new therapy depends on thenumber of historical controls selected for comparison.
BiometricsEstimation of the Proportional Hazard in Two-Treatment-Group Clinical Trials
61 Citations1981Leslie Bernstein, James R. Anderson +1 more
The O/E method is biased but, within the range of values of the ratio of the hazard rates of interest in clinical trials, it is more efficient in terms of mean square error than either CML or the Mantel-Haenszel method for all but the largest trials.
BiometricsNonparametric Confidence Intervals for the Median in the Presence of Right Censoring
61 Citations1982John D. Emerson
BMJIs the statistical assessment of papers submitted to the "British Medical Journal" effective?
47 Citations1983M. J. Gardner, Douglas G. Altman +2 more
A study to judge the effectiveness of the statistical assessment scheme for papers submitted to the "British Medical Journal" found little evidence that the papers that had been assessed were statistically more acceptable than those that had not been assessed but re-emphasised the subjectivity of refereeing and assessment.
Lecture notes in medical informaticsThe reporting of non-significant results in clinical trials
14 Citations1979J. L. Haybittle
A large number of clinical trials that have been run to date, particularly in the cancer field, have ended with a ‘non-significant’ result i.e. the authors have reported ‘no significant difference at the 5 percent level’ or some equivalent statement.
BiometricsJerome Cornfield and Statistical Applications to Laboratory Research: A Personal Reminiscence
8 Citations1982Nathan Mantel
Jerome Cornfield's adventures in statistics have already been effectively and expertly encapsulated by Cornfield himself in his Presidential Address to the American Statistical Association, but it is evident that he has identified himself as a member of the investigative team with which he was working, largely biochemists, making their concerns his concerns.