STAT-2300 Lecture Notes - Lecture 5: Asteroid Family, Unimodality, Skewness

• School: Clemson University
• Department: Statistics
• Course: STAT-2300
• Professor: Erwin Walker

Document Summary

The shape of a distribution is described by mentioning symmetry or skewness, number of peaks, any clusters or gaps, and any unusually high or low observations called outliers. A distribution is unimodal if a graph contains a single peak. A distribution is bimodal if a graph contains two distinct peaks. A distribution is uniform if the frequency of each class is relatively the same. A distribution is multimodal if a graph contains a number of distinct peaks. A distribution that is both symmetric and unimodal is described as bell shaped. There are a couple of main features that can help to determine the shape of any distribution, and these are: Look for any kind of general symmetry or clear skewness. (skewness can be very minor or (cid:448)er(cid:455) o(cid:271)(cid:448)ious, a(cid:374)d gi(cid:448)e(cid:374) that, s(cid:455)(cid:373)(cid:373)etr(cid:455) does(cid:374)"t al(cid:449)a(cid:455)s (cid:373)ea(cid:374) a perfe(cid:272)t (cid:271)ell shape. ) Look for major peaks or gaps, not just for minor ups and downs in the bars of a histogra(cid:373).