15  Confirmatory Factor Analysis

Outliers: values outside the typical range of scores Skewness: measure of the asymmetry of a distribution Skewed distributions are common and violate statistical assumptions Lopsided distribution of values or scores influenced by outliers Negatively (left) skewed (e.g., job satisfaction ratings) Positively (right) skewed (e.g., income) Kurtosis: measures flatness/peakedness of the distribution

Skewness is important for many reasons, mostly to understand the deviation from the normal curve. What is considered an outlier? That’s up for debate. Some say outliers are values that are up to 10 standard deviations from the mean. In business sciences, there’s something called the 68-95-99.7 rule where people will rule out values that are three standard deviations from the norm. 68–95–99.7 — The Three-Sigma Rule of Thumb Used in Power BI. | by Sebastian Zolg 🤝 | Towards Data Science In I-O psychology we typically leave these values in, cross our fingers, and pray to the gods of the Central Limit Theorem. There is usually not a good justification for leaving out data solely because it violates our statistical assumptions. Instead, we should use a different statistical test to account for this deviation from the norm. There are other tests that are robust to these violations. In economics they just transform the data to be normal… 🤷 This is a great review: https://www.frontiersin.org/articles/10.3389/fpsyg.2018.02104/full