Vassar Stats is a collection of useful statistical tools that allow import and export of data and which have (untypical for on-line materials) EXCELLENT documentation available at the click of a button. From another vantage point Vassar Stats is a full textbook for a course in statistics. This type of material is exactly the kind of merge of old methods (books, narrative) with new methods (interactive applets) that make on-line tools a great opportunity.
Type of Material:
Simulation, Tutorial, Reference material
Identify Major Learning Goals:
Like a well-done textbook, Vassar Stats touches upon many standard topics in statistics and provides tools for their analysis.
Target Student Population:
Anyone taking a statistics course or using statistics could benefit from using this site.
Prerequisite Knowledge or Skills:
Basic knowledge of statistics is required to select the appropriate tests and interpret the results. The companion text may be used to acquire that knowledge. Basic algebra and knowledge of functions are needed to understand the companion text.
Generally speaking, Vassar Stats gives thorough coverage of statistics and the applets generally have good layout of the numerical outputs. More specific features follow.One feature of Vassar Stats is its graphic and numerical results for binomial, Poisson, chi-square, and normal distributions, among others. The labeled sketch for the binomial distribution is particularly informative with its accompanying probability table and table of critical values for various probabilities. Included under frequency data are the Poisson approximation of binomial probabilities and the exact binomial probability calculator, as well as the chi-square goodness of fit. Correlation and regression, various t-tests, and nonparametric tests are available along with ANOVA and ANOCVA. Conditional probabilities are calculated using Bayes' Theorem.
Control charts for range, variation and mean would be a nice addition. In some cases graphical instead of numerical output would be nice.
Potential Effectiveness as a Teaching Tool
Each statistical test is prefaced by an explanation of the information that the user will be asked to input. Once the test is selected, that information is sequentially requested. Following input of all data by the user, the data is restated along with the results. The chance for error is almost zero. The independent learner will find everything needed to master statistical concepts and perform statistical tests.The student or researcher who has an idea of the test he/she wishes to perform will find the site very easy to use. Topics highly recommended by the reviewers for lecture/demo include Bayes Theorem, normal distributions, and linear correlation and regression.
There are no exercises in the accompanying on-line text. This limits the usability of the text,
as most faculty will not generate their own exercise sets. If the text is viewed as (excellent) documentation for the applets this is not of much consequence.
Ease of Use for Both Students and Faculty
Documentation is superb. The online textbook, Concepts and Applications of Inferential Statistics, is available for instruction or reference. An index of topics is included. Specific topics are grouped into categories that remain visible while the user selects one to use. Returning to the menu is as simple as clicking on a category. Explanations of nuts-and-bolts (such as data entry) can be found through "Click here"s.
Search by ISBN?
It looks like you have entered an ISBN number. Would you like to search using what you have
entered as an ISBN number?
Searching for Members?
You entered an email address. Would you like to search for members? Click Yes to continue. If no, materials will be displayed first. You can refine your search with the options on the left of the results page.