Wie teste ich Residuen auf Normalverteilung (grafisch, analytisch)? - Daten analysieren in SPSS (19)

// How do I test residuals for normality (graphically, analytically)? // Normally distributed residuals are a prerequisite for hypothesis testing or the interpretation of confidence intervals. Initially, a graphical check can be performed by evaluating a histogram with a stylized normal distribution curve. Excessive skewness or kurtosis of the distribution already indicates that the residuals are not normal. For a more precise assessment, skewness and kurtosis can be used. Ideally, both values ​​should be 0. If the values ​​are only slightly different from 0, the assumption of normality or normal distribution of the data can still be considered fulfilled. A true analytical test for normality of the residuals is performed using the Kolmogorov-Smirnov test and the Shapiro-Wilk test. In both tests, the null hypothesis is that the data follow a normal distribution. Therefore, the goal is to be able to prove that the null hypothesis cannot be rejected if the data are to be shown to be normally distributed. The Shapiro-Wilk test is preferred, however, because it has higher statistical power, especially with smaller samples. Larger samples of several hundred are, by the way, approximately normally distributed anyway due to the central limit theorem. Both the Shapiro-Wilk and Kolmogorov-Smirnov tests sometimes indicate non-normality in large samples and are therefore best used with small samples (under 100). If you have any questions or suggestions about identifying normality or normal distribution of residuals in a regression in SPSS, please use the comment function. Let us know if you found the video helpful by giving it a thumbs up or down. ... #statistikampc ⭐Become a channel member⭐: =======================    / @statistikampc_bjoernwalther   Support the channel? 🙌🏼 =================== PayPal donation: https://www.paypal.com/paypalme/Bjoer... Amazon affiliate link: https://amzn.to/2iBFeG9 Thank you for your support! ♥ My website 💡 ================= https://www.bjoernwalther.com