Estimands: a new way of interpreting the results of clinical essays

Javier Martín-Vallejo, Department of Statistics, Universidad de Salamanca. Biostatistics Service, IBSAL, Salamanca, Spain
José P. Miramontes-González, Internal Medicine Service, Hospital Universitario Río Hortega. Department of Medicine, Dermatology and Toxicology. School of Medicine, Universidad de Valladolid, Valladolid, Spain
Ricardo Gómez-Huelgas, Internal Medicine Service, Hospital Regional Universitario de Málaga. Instituto de Investigación Biomédica de Málaga (IBIMA), Universidad de Málaga, Málaga. CIBER Fisiopatología de la Obesidad y Nutrición, Instituto de Salud Carlos III, Madrid, Spain

Considering the need to homogenize and strengthen the principles of statistical methodology in clinical trials, and to prevent biases in trial design and losses in results, regulatory authorities have encouraged the use of new statistical concepts that help avoid these problems. Based on this idea, estimands were developed with the special purpose of solving the problem of missing data at the end of clinical trials, a fact that conditions the reliability of the results and the fulfillment of the objectives of a study. Estimands can be seen as a bridge between objectives and statistical tools, allowing a clear and coherent presentation of results. In this article, we explain in simple terms the concept of estimands, and the benefits of incorporating them into the interpretation of clinical trials.

Keywords: Estimands. Clinical trials. Statistical methodology. Intercurrent events.