The statistical analysis can be divided in two main components: descriptive analysis and inferential analysis. An inference is to elaborate conclusions from the tests performed with the data obtained from a sample of a population. Statistical tests are used in order to establish the probability that a conclusion obtained from a sample is applicable to the population from which it was obtained. However, choosing the appropriate statistical test in general poses a challenge for novice researchers. To choose the statistical test it is necessary to take into account three aspects: the research design, the number of measurements and the scale of measurement of the variables. Statistical tests are divided into two sets, parametric and nonparametric. Parametric tests can only be used if the data show a normal distribution. Choosing the right statistical test will make it easier for readers to understand and apply the results.

Systematic reviews are secondary investigations that compile published results that have been obtained from studies involving human subjects. Meta-analysis is the term used to describe the carrying out of statistical analysis of the combination of the results of two or more original studies, which had to be selected from a systematic review. In this way, a meta-analysis cannot exist without a systematic review. Systematic reviews arise due to the exponential increase in the information; to provide all health personnel with a study that critically analyzes the results and discriminates those that may be useful in clinical practice. Systematic reviews are one of the fundamental tools in evidence-based medicine, in which two of the main steps refer to both the search and the critical analysis of the studies, which shall support medical decisions on aspects that are mainly related to diagnosis, treatment, or prognosis. On the other hand, systematic reviews have been essential for some time now when developing evidence-based clinical practice guidelines and they can be used to make decisions on health policies. The methodology for performing and interpreting systematic reviews and meta-analysis is described in this article.

Informar en los estudios sobre el tamaño del efecto de una intervención o del impacto de factor(es) sobre un desenlace, permite tomar mejores decisiones para la aplicación de los resultados a la práctica clínica. En este artículo se presenta la manera de analizar el tamaño del efecto, lo cual puede ser mediante métodos estadísticos directos o indirectos. Dentro de los métodos directos, se encuentra la diferencia de promedios entre grupos y la diferencia de frecuencias absolutas o relativas. Dentro de los métodos indirectos se muestran los índices de la familia de “d” de Cohen (que se basan en valores de desviación estándar), la familia de “r y R2”, medidas de asociación (RM, RR, HR) e impacto (NNT). La decisión del uso de cualquiera de los métodos descritos, depende de los objetivos del estudio, la escala de medición usada para evaluar los resultados y la distribución de los datos. Para facilitar la comprensión, se incluyen ejemplos y se resalta la necesidad de incluir los diferentes estadísticos con su nivel de precisión (ej. intervalos de confianza), junto con los umbrales clínicos de decisión, a fin de mejorar su interpretación.

Research on human subjects cannot occur if it does not comply with these ethical principles: autonomy, beneficence and justice. The historical antecedents that emphasized the need to have documents to guide the researchers’ behavior point to regrettable events for humanity. Even though the first recommendations were published more than 50 years ago in the Declaration of Helsinki, it is possible to find examples of investigations that have been conducted without complying with the aforementioned ethical principles. Approval by an ethics committee is required by law for all the research projects that involve human subjects. At present, virtually all scientific journals require the proof of approval and they assess whether the risks which participants were subjected to in the studies were necessary, and they also assess whether the benefits that were obtained from the research justify its conduction. Meeting the criteria that are required in order to conduct a study in an ethical manner should not be seen as an imposition; but as a moral commitment that has been established between the researcher and the participants of the study.

The concept of validity in research refers to what is true or what is close to the truth. It is considered that the results of an investigation will be valid when the study is free of errors. The errors or biases appear in the development of research, are due to methodological problems and, in general, can be grouped into three: selection bias, measurement bias and confusion bias. In this article, measurement biases will be addressed; this type of error has three axes: 1) the research subject, 2) the instrument for the measurement of the variable (s), and 3) those who make the evaluation of the measurement (s). To improve the obtaining of data and to prevent errors, some strategies can be followed: in every study protocol, it is necessary to include the operational definition of the variables; the subjects that will carry out the measurements or surveys must be trained. If measuring instruments are used, their proper functioning must be verified; when questionnaires are included, they must be validated in the language in which they will be applied, they have had a process of adaptation to the language of the participants in the study, and self-applicable ones are preferred. It is necessary to quantify the variability of the measurements from the statistical point of view to increase the validity of a study.

Experimental studies are used to assess the efficacy and effectiveness of therapeutic (pharmacological or surgical), preventive (such as vaccination or lifestyle changes) or educational interventions (e.g., workshops to improve quality and healthcare). There are different experimental studies but, currently, randomized controlled trial (RCT) is recognized as the type of study that provides the highest level of evidence. When this type of research cannot be carried out, there are quasi-experimental studies, where there may be no randomization or a control group; however, this type of studies has a lower degree of validity. This article describes the way different types of RCT and quasi-experimental studies are performed; their advantages and disadvantages are also explained.