Jarrod Moore posted Apr 18, 2025 8:37 PM Subscribe Hello All, In the future, I hope to work in business or organizational leadership, and one key variable I expect to deal with is salary data. Salaries are usually collected through HR systems, surveys, or anonymous data pools for comparing compensation. Salary is a continuous variable and often skewed to the right because a small group of high earners raises the average, while most people earn closer to a lower central range. Since salary data isn't normally distributed, the Central Limit Theorem (CLT) is super helpful. Gravetter and Wallnau (2021) explain that the CLT says when you take random samples of a large enough size, the sampling distribution of the sample mean will be close to normal, even if the population distribution isn't. This is super important for making good statistical guesses. Why does this matter? Organizations don't usually collect data from every employee or job market participant. Instead, they use samples. Thanks to the CLT, they can make accurate predictions about average salaries or wage gaps if the sample is random and big enough. This makes it easier for companies to use statistics to make decisions. For example, a sample could include anywhere from 100 to 300 employees, depending on the organization's size. This is usually enough to meet the CLT's guideline for a "large sample" (typically n ≥ 30). So even if salary data is skewed, organizations can still create confidence intervals or test hypotheses about average salaries. Thanks! PEER REPLY 2: Review another classmate's Main Post. Assume that the restrictions of using the central limit are met for the classmate's situation. 1. Create a scenario that you are interested in the statistic being above a particular value, below a particular value, or between values. 2. What percent chance do you want for success in being above, below, or between those values based upon your scenario? 3. What would it mean for a sample to not be in the desired area in your scenario?