摘要：This article describes a dataset on pop songs that charted on the Billboard Top 40 and/or at one or more of five radio stations, three in Chicago, Illinois, and two in Grand Rapids, Michigan, from the early 1960s through 1970. The dataset includes 5746 observations and 26 variables. In the body of the article, we describe how the cleaned version of the dataset can be used in an introductory or second-level statistics course to investigate questions of race and gender bias and the role of radio consultants in Top 40 radio airplay in the 1960s. The richness of the dataset requires students to think about relationships among multiple variables. In an appendix, we briefly describe how a raw, uncleaned version of the dataset can be used in an R programming course to illustrate data management and data entry error detection.
关键词：Data cleaning ; Data visualization ; Multivariable thinking ; R ; Top 40 Radio
