- Peer Review: “Java Applets for Power and Sample Size”
Java Applets for Power and Sample Size
- Feb 22, 2007 by Statistics
- This collection of free, interactive Java applets provides a graphical interface for studying the power of the most commonly encountered experimental designs. Intended to be useful in planning statistical studies, these applets cover confidence intervals for means or proportions, one and two sample hypothesis tests for means or proportions, linear regression, balanced ANOVA designs, and tests of multiple correlation, Chi-square, and Poisson. Each applet opens in its own window with sliders, which are convertible to number-entry fields, for manipulating associated parameters. Controlling for the other parameters, users can change sample size, standard deviation, type I error (alpha) and effect size one at a time to see how each affects power. Conversely, users can manipulate the power for the test to determine the necessary sample size or margin of error. Additional features include a graph option by which the program plots a dependent variable (i.e. power) over a range of parameter values; the graph is automatically updated as the parameters are changed. Each dialog window also offers a Help menu which provides instructions for using the applet. The applets can be used over the Internet or downloaded onto the users own computer.
- Type of Material:
- Java Applet
- Recommended Uses:
- These applets provide a free power calculator. They can be used to plan research projects or statistical studies or to complete homework that requires power calculations. Instructors can use the applets in lectures, class demonstrations, or activities designed to introduce power, display power functions, or assist students in investigating the interplay between power, sample size, and margin of error.
- Technical Requirements:
- To run the applets over the web, users need a Java-enabled browser. To run the software locally, users need the Java Runtime Environment (JRE) or the Java Development Kit (JDK), which are available through the links provided.
- Identify Major Learning Goals:
- While this material does not appear to have been designed with the goal of teaching a particular concept, it is useful for investigating how power changes as sample size, effect size, type I error, variance, and hypotheses change.
- Target Student Population:
- Although intended for those planning statistical studies such as researchers or advanced students, some of these applets could also be used by students in an introductory statistics course.
- Prerequisite Knowledge or Skills:
- Students need to understand the design used in the applet (confidence intervals, hypothesis testing, regression, etc.) and need an introduction to power analysis as well.
- The applets produce accurate calculations and useful graphical tools with the quality of many commercial software packages, and the menu of tests is large enough to satisfy many standard research needs. The documentation provided encourages good statistical practice with high quality explanations, good vocabulary, and good notation, although the Greek letters are spelled out with Roman ones. The Advice section gives ideas on how and how not to use the applets as well as practical issues associated with power and sample size, while the Accuracy section discusses the components of the software accuracy. The references and links to other resources given are useful.
- No underlying distributions are shown to illustrate how or why type I and type II errors and power move as other parameters change. Formulas are assumed to be known, so there are none given. The accuracy of the answers is set to 4 digits, which can result in rounding errors. This could be a stumbling block, as students struggle to get the right answer.
Potential Effectiveness as a Teaching Tool
- The applets demonstrate graphically and numerically how the components of a power analysis calculation move together, allowing teachers to quickly show many possible scenarios. They compute complicated calculations that take a long time to do by hand and have sliders that dynamically update the relevant parameters as the user investigates. The graphs show global relationships, such as how the sample size depends on the margin of error for a fixed level of confidence, and are useful for teaching students how to choose among competing tests based on graphical analysis of power functions or other functions. The graphing capabilities allow users to choose the dependent and independent variables and the plotting range. These applets can be readily implemented into statistics courses at almost any level and can be used with most statistics texts.
- These applets are not designed as teaching tools, and thus, are not conceptual in nature but are focused on calculations. They do not illustrate why the changes happen or describe what formulas are used, so students need a prior conceptual foundation to benefit from the applets. There are no pedagogical activities for teaching power analysis tied to the applets. Thus, teachers who want to use this resource in their class must create their own activities and assessments. Also, without an introduction to power, students may get misleading answers.
Ease of Use for Both Students and Faculty
- These applets are easy to use. The dialog boxes are straightforward with well-labeled sliders and drop-down menus. The help menus give good, easy to read explanations of how to use the applets. The site is not limited in terms of how it runs on standard machines, and the technical requirements are easily met. Installing this software on a personal computer is easy with clear instructions for how to handle the software. No technical support seems to be necessary.
- Instructors will have to prepare activities or lessons around these applets if they intend to use them in class to teach the concept of power. Students will also need some kind of introductory lesson on power before using the applets. There are many parameters and options associated with these applets, and this degree of flexibility may lead to situations where careless users could potentially get stuck. Reading the Help menus is vitally important to running these applets successfully and effectively. Some problems may occur when using a Mac to run these applets.
- Other Issues and Comments:
- This material is a great resource for doing power and sample size calculations. The combination of visual tools, such as dynamically updating sliders and fully customizable graphing capability, make this item a strong visual aid for teaching power. Unfortunately, because the applets are not intended for instructional use, teachers will have to create materials to accompany these applets for classroom and homework situations.
- Creative Commons: