Because we often do not work with data or information population from the entire population, we must make inferences from the information we have (i.e., data included from a sample) to what is actually happening in the entire population. While analytics and statistical processes do a good job of guiding us toward better know the reality of what is happening in the population, we will sometimes make inferential errors.
The following will discuss the two types of Inferential errors that can be made and help better illustrate how we can determine the extent to which we "found an effect" if is present in the population.
Before you do an experiment, you should perform a power analysis to estimate the number of observations you need to have a good chance of detecting the effect for which you are looking.