Statistical Inference (part 1): Basic Concepts

In the most common research situations, the investigator cannot directly assess the whole population of interest. For this reason, a sample is often studied to infer the actual population measures or parameters. Statistical inference comprises the application of methods to analyze the sample data in order to estimate the population parameters. The basic assumption in statistical inference is that each individual within the population of interest has the same probability of being included in a specific sample. When the sample is not randomly selected. the study findings can still be generalized if the sample can be considered representative of the whole population of interest. A set of statistical methods used to infer the population parameters is performed under the assumption that the sample estimates follow a bell-shaped distribution, called normal distribution. This article presents with the help of examples, the logic used in the sampling distribution theory. The concept of normal (also called gaussian) sampling distribution has an important role in statistical inference, even when the population values are not normally distributed. In fact, in the statistical inference process, the form of the distribution of the sample estimates is more important than the distribution of the individual values.