This applet simulates and plots the sampling distribution of various statistics (i.e. mean, standard deviation, variance). The applet allows the user to specify the population distribution, sample size, and statistic. An animated sample from the population is shown and the statistic is plotted. This can be repeated to produce the sampling distribution of the statistic. After the sampling distribution is plotted it can be compared to a normal distribution by overlaying a normal curve. These features make it useful for introducing students in a first course to the idea of a sampling distribution. The site also includes instructions and exercises. Also available at: http://www.stat.ucla.edu/~dinov/courses_students.dir/Applets.dir/SamplingDistributionApplet.html
Java enabled browser
Content Quality Concerns:
On some machines the sample statistics drop down rather quickly, even in animation mode. Students may not see these and need specific instructions to make this clear. The applet allows calculation of two separate statistics (such as mean and median), but repeats the sampling animation when these are calculated. This may be confusing to the student.
Content Quality Strengths:
This applet allows students to see sampling distributions in action. The applet shows, in a clear visual way, how sampling distributions are built up from samples. One of the strongest parts of the applet is that you can change the population distribution.
Ease of Use Concerns:
One area of confusion might arise from the labeling of the parameters in the simulation. As with any simulation of sampling, keeping clear what are the number of samples simulated or the number of observations within a sample is sometimes difficult and instructors should be prepared for student questions on these issues.
Ease of Use Strengths:
The applet is easy to use and quite intuitive.
Potential Effectiveness Concerns:
A small limitation of this simulation is that the user cannot hold some of the previous results while changing sample sizes. An instructor could easily work around these issues by giving students clear instructions such as having students record distribution on a worksheet. Another minor limitation is that the user cannot build the sampling distributions in increments between 5 or 1000, such as 20 or 50.
Potential Effectiveness Strengths:
The user can control many aspects of the simulations. Although the sample mean is the statistic most commonly of interest, the applet lets one study sampling distributions of other statistics as well, such as the sample standard deviation. One interesting use is to create a custom bimodal distribution and see how the sampling distribution of the mean is normal, but not that of the median. Additionally, underlined words take you to a definitions of these terms from the Rice Virtual Lab in Statistics.
Potential Effectiveness Rating:
Source Code Available:
Source Code Available
Intended User Role:
Free for All