AMS 5 Lecture Notes - Lecture 3: Categorical Variable, Histogram

• School: UCSC
• Department: Applied Math and Statistics
• Course: AMS 5
• Professor: Jonathan Katznelson

Document Summary

Cross-sectional : collected from different subjects during the same time period. Longitudinal : collected from the same subjects over time. Variables: head of household, household size, monthly income, birth year, occupation, Relevant data is summarized by the frequency or relative frequency. To summarize quantitative data in a table the typical approach is to transform it into categorical data. Range of values divided into lass intervals = bins (category) Histogram is graphical form of a distribution table for quantitative data. Histogram for data are usually drawn as bar charts. Frequency is the observed divided by the total number observed. Density is the area of the bar over a given area. Relative frequency divided by the width of their intervals. The average of the distribution is bigger than the median. The histogram reports the info accurately but is misleading, the bins for the higher income appear larger than the bins for the lower income because they are wider.