Topic: Miscellaneous

Methods: Distribution, Histogram,
Topics: Miscellaneous,
Datafile Name: Militiamen Chests

These data summarize the chest sizes of Scottish militiamen in the early 19th century. Chest sizes are measured in inches, and each observation reports the number of soldiers with that chest size. A histogram of chest sizes shows an approximately normal curve. Notice that the histogram must be dr...

Methods: Paired T-Test, T-test,
Topics: Famous Datasets, Miscellaneous,
Datafile Name: Difference Tests

Four sets of data are presented. The first is measures of tire wear by two methods, the so-called weight method and the groove method. The second is Gosset's famous example of corn yield from split plots of regular and kiln dried seed. The third set is waiting times between eruptions of Old F...

Methods: Outlier, Summary Statistics, Mean, Median, Histogram, Boxplot,
Topics: Miscellaneous,
Datafile Name: Distribution Patterns

This "story" illustrates some of the different distribution patterns that variables may take on. The distribution of Tobin's Q-ratios for firms shows high positive skewness. Sometimes this can be 'remedied' by taking the logarithms of the data. Try this for the Q-ratios. Oth...

Methods: Regression, Dummy Variable, Confidence Interval,
Topics: Government, Miscellaneous,
Datafile Name: Parking Meter Theft

The variable CON in the datafile Parking Meter Theft represents monthly parking meter collections by the principle contractor in New York City from May 1977 to March 1981. In addition to contractor collections, the city made collections from a number of "control" meters close to City Ha...

Methods: Regression, T-test, Time Series,
Topics: Government, Medical, Miscellaneous, Sports,
Datafile Name: Time Series

The datafile includes four series which can be described as time series exper- iments. At some point in the time series, new conditions are introduced. The question then is raised whether the sample of observations after the change comes from a population with a different mean than the sample of ...

Methods: Transformation, Regression, Assumptions, Regression,
Topics: Miscellaneous,
Datafile Name: Transformations

Four sets of data are presented in which the relation between X and Y is not best described as linear in the original numbers. Therefore, some transformation of X, Y, or both is appropriate. Suggestions are log Y, log X, log Y and log X, 1/Y, and 1/X. Two of the sets can be described as learning ...

Contact Us

© 2017 Data Description, inc. All rights reserved.