Epidemiology is a section of medical science that covers the spread of diseases and the causal factors within a group of people and the steps taken to curb and contain the disease by identification of possible predisposing sources for the illness (Robins, Hernan, & Brumback, 2000). The study targets masses of people. In conducting research, the data collection process is not always accurate because only the samples of the population are used, which affects the understanding and outcome of the study. Chance normally creates room for multiple errors in the study process, which can lead to different conclusions. The sample size is the number of people that are involved in research. Essentially, it determines the outcome. Sample power controls and assists in the interpretation of the outcome and effectiveness of the study (Hoeffding, 1952).
Central tendencies refer to how often a particular measure keeps appearing in a study such that it offers a reference point for analysis (Glick, 1988). They issue directions for making conclusions and near accurate reporting. Random errors affect the study, and because of a large number of participants, the sources are not always clear because they occur in almost all researches carried out regardless of the size. However, they are easy to manage. Random errors are normally close, and the variances are relatively similar. Comparisons done on random errors would lead to accurate estimations, for instance, one can choose several errors and come up with an average measure for the study.
Statistical testing is the actual ascertaining of the data sampled and making a comparison with different data. For example, a statistical test can be done on the average life expectancy of a country using the actual population ( Tajima 1989).
Reference
Glick, W. H. (1988). Response: Organizations are not central tendencies: Shadowboxing in the dark, round 2. Academy of Management Review, 13(1), 133-137.
Hoeffding, W. (1952). The large-sample power of tests based on permutations of observations. The Annals of Mathematical Statistics, 169-192.
Robins, J. M., Hernan, M. A., & Brumback, B. (2000). Marginal structural models and causal inference in epidemiology.
Tajima, F. (1989). Statistical method for testing the neutral mutation hypothesis by DNA polymorphism. Genetics, 123(3), 585-595.