Overemphasis on hypothesis testing--and the use of P values to dichotomise significant or non-significant results--has detracted from more useful approaches to interpreting study results, such as estimation and confidence intervals. In medical studies investigators are usually interested in determining the size of difference of a measured outcome between groups, rather than a simple indication of whether or not it is statistically significant. Confidence intervals present a range of values, on the basis of the sample data, in which the population value for such a difference may lie. Some methods of calculating confidence intervals for means and differences between means are given, with similar information for proportions. The paper also gives suggestions for graphical display. Confidence intervals, if appropriate to the type of study, should be used for major findings in both the main text of a paper and its abstract.

https://www.bmj.com/content/bmj/292/6522/746.full.pdf

Confidence intervals rather than P values: estimation rather than hypothesis testing.

Statistics with Confidence is a widely acclaimed classic introduction to confidence intervals. The second edition, with contributions from leading medical statisticians, has been thoroughly revised and expanded. New chapters include: * diagnostic studies. * clinical trials and meta analyses. * confidence intervals and sample sizes. The Windows computer software (CIA) in the accompanying disk enables confidence intervals to be calculated using the methods described in the book. This comprehensive collection of methods includes some that are not readily available elsewhere. Featuring methods for using confidence intervals, illustrative worked examples and helpful checklists this is a truly practical guide for clinical readers to a fundamental aspect of medical statistics.

Statistics with Confidence : Confidence Intervals and Statistical Guidelines

https://www.thelancet.com/pdfs/journals/lancet/PIIS0140-6736(00)02528-9.pdf

Relation between tumour response to first-line chemotherapy and survival in advanced colorectal cancer: a meta-analysis

This statistical primer presents the landmark analysis method, exploring its appropriate use and interpretation while recognizing its limitations. This observational method is used for comparing time-to-event outcome between groups determined during study follow-up. The goal of the landmark method is to estimate in an unbiased way the time-to-event probabilities in each group conditional on the group membership of patients at a specific time point, the landmark time. The need that led to its development, the impact of the method, and its pros and cons, along with available alternative approaches, are presented. Simulations explore its performance, using realistic parameters from a recent cardiovascular study. As long as the limitations of the method are recognized and the interpretation of its results clearly reflect their "conditional" nature, landmark analysis, 25 years from its introduction, can still be of value.

Landmark Analysis at the 25-Year Landmark Point

Between October 1981 and June 1983, the Eastern Cooperative Oncology Group (ECOG) conducted a prospectively randomized trial (EST 1581) of the four most active chemotherapy regimens for metastatic non-small-cell lung cancer (NSCLC). Four hundred eighty-six good performance status patients (PS 0 or 1; 81%) were randomized to receive cyclophosphamide, doxorubicin, methotrexate, and procarbazine (CAMP); mitomycin, vinblastine, and cisplatin (MVP); etoposide and cisplatin (VP-P); or vindesine and cisplatin (VDA-P). All regimens were administered in the doses and schedules originally reported. Complete response (CR) plus partial response (PR) rates for the four regimens were CAMP, 17%; MVP, 31%; VP-P, 20%; and VDA-P, 25%. The response rate for MVP was significantly higher in patients with squamous and adenocarcinoma histologies, but there was no impact on median survival (overall, 24.5 weeks). The duration of response did not differ by treatment as previously suggested for VDA-P. There were 15 CRs (CAMP, one; ...

A randomized trial of the four most active regimens for metastatic non-small-cell lung cancer.

Comparing survival of responders and nonresponders after treatment: A potential source of confusion in interpreting cancer clinical trials

A 52-year-old man with Ph1-positive chronic myelogenous leukemia (CML) developed a blastic transformation in which the predominant cell type micromegakaryocytes. He did not respond to treatment. A review of the 15 previously reported cases of patients with circulating megakaryocyte abnormalities in association with either CML or a Ph1 chromosome positive myeloproliferative disorder suggests a female predominance rather than the usual male predominance of CML. Survival of the six patients reported as megakaryoblastic transformation of CML as well as this patient was poor.

Megakaryoblastic transformation of chronic myelogenous leukemia.

Avoiding ambiguity when reporting variability in biomedical data

KIE: A persistent ethical dilemma in research is the potential conflict between the patient-subject's best interests and the principles of scientific methodology. Vanderpool and Weiss discuss the problem in cancer research when a physician falsifies data in order to increase a patient's chances of being selected to participate in a clinical trial. While raising the question of whether such lying is justified if it may prolong the life of a cancer patient for whom there are no other therapeutic options, the authors point out that the inclusion of ineligible subjects may render trial results invalid.

False data & the therapeutic misconception: two urgent problems in research ethics. False data and last hopes: enrolling ineligible patients in clinical trials

A significant positive association between antigens HLA Aw 19 and/or HLA B5 and a disease-free survival time of one year for patients with lung cancer has been reported but not confirmed. We have HLA-typed 20 white patients with non-oat-cell bronchogenic carcinoma who have survived at least a year from the time of diagnosis. Half these patients possessed these antigens (P < 0.08). This highly suggests that the presence of these antigens is associated with prolonged survival time. Now may be the time for performing large scale clinical trials using these antigens as stratification factors. Cancer 46:38–40, 1980.

Gary B. Weiss

Papers

Comparing survival of responders and nonresponders after treatment: A potential source of confusion in interpreting cancer clinical trials

Megakaryoblastic transformation of chronic myelogenous leukemia.

Avoiding ambiguity when reporting variability in biomedical data

False data & the therapeutic misconception: two urgent problems in research ethics. False data and last hopes: enrolling ineligible patients in clinical trials

HLA type and survival in lung cancer.