Dataxiom: Power and Precision



Demo		Power and Precision is a stand-alone program for determining the sample size and statistical power for a planned study. Power and Precision enables you to: Find optimal sample size Compute statistical power Estimate confidence intervals Create reports, tables, and graphs The program is an invaluable resource for market researchers, experimental psychologists, medical researchers, or anyone who is involved in the process of designing studies or preparing grant applications. Power and Precision Version 2 has many important additions such as Survival Analysis, Logistic Regression, Equivalence Tests and many more. See below for details. Take the Guesswork Out of Power and Precision Analysis Determining the appropriate sample size and statistical power for a study is essential in planning research. If you choose too small a sample, your study results may prove statistically insignificant. However, if you select too large a sample size, you may create unnecessary work, wasting time and money. Yet few researchers take this initial analysis step because of the complexity of calculating these values. Created by leading experts in the field of statistical power analysis -- Michael Borenstein, Jacob Cohen, Hannah Rothstein,David Schoenfield,Jesse Berlin, and Ed Lakatos-- Power and Precision provides a simple yet highly effective method for analyzing sample size and calculating a statistical test’s power. With Power and Precision, you can easily compute power and precision (confidence intervals) for many statistical procedures. The program allows you to work interactively and automatically apply Cohen’s effect size conventions for small, medium, and large effects. Easy-to-Use Features for Learning and Teaching The program’s intuitive interface makes high-level power and precision analysis easily accessible to students and new users. Many of the procedures are initiated by simple point-and-click interactions. You can generate tables and graphs with one simple click! To aid in the analysis, you can take advantage of the “Wizard” interactive guide and extensive help system. Program Features Clear, Intuitive Interface Manipulate effect size, alpha, sample size and see immediate impact on power Find required sample size automatically (user may specify allocation ratio) Take account of power and confidence interval width simultaneously Use interactive guide (“Wizard”) to learn program features Use continuous summary to understand the meaning of computed data Tables Print directly Copy to clipboard as data and insert into MS Excel or other spreadsheet New! Copy to clipboard as a bitmap and insert into MS Word or other word processing program Graphs Print directly Copy to clipboard as data an inset into MS Word or other word processing program Export as bitmap(BMP),Windows Metafile(WMF) or EMF and insert into MS Word, PowerPoint and other programs New! Reports Save as RTF file or copy to clipboard and inset into Word or other word processing programs. Stored Scenarios (Sensitivity Analysis) Print directly Copy to clipboard as data and inset into MS Excel or other spreadsheet New! Copy to clipboard as a bitmap and insert into MS Word or other word processing program Tables and graphs Pivot the tables interactively New! Display several graphs at once to assess the impact of factors in isolation of in combination with each other New! Graphs are linked to the tables-Drag and drop columns in table, and the graphs are updated as well. New! Graphs can be saved as BMP,WMF,EMF files and easily exported to Word, PowerPoint, and other programs. New! Tabulate and graph precision (confidence interval) and standard error as well as power for proportions and means Statistical Procedures t-tests and z-tests One group against a null of zero One group against a user-specified null Paired/change against a null of zero Paired/change against a user-specified null Two independent groups, enter difference score Two independent groups, enter mean for each group Proportions One group against a null of 50% One group against a user-specified null (Binomial) Two independent groups (Power options include Chi-square and Fisher Exact test. Indices include rate difference, relative risk and odds ratio) McNemar test of paired proportions KxC test of independent proportions (up to 8 rows by 8 columns) Sign test Correlations One group against a null of zero One group against a user-specified null Two groups Analysis of Variance/Covariance One-way analysis of variance/covariance Two-way fixed effects factorial analysis of variance/covariance Three-way fixed effects factorial analysis of variance/covariance Multiple Regression Includes templates for common designs including covariates followed by main effects; main effects followed by interactions; dummy-coded variables; and polynomial regression Allows the user to customize the study design with up to 10 sets of variables and 99 variables per set Computes power for the increment of R2 at each step and also for the cumulative R2 at each step Allows the user to compute power for sequential groups of sets General Case Computes power using the non-central t-distribution; includes assistants for one-sample and two-sample t-tests Computes power using the non-central F-distribution; includes assistants for ANOVA and for multiple regression Computes power using the non-central chi-square distribution; includes assistants for a KxC test of independence Logistic Regression *New!* One continuous covariate Two continuous convariates, one partialled Two continuous covariates combined One categorical covariate up to 5 levels Survival Analysis New! Accrual options-Prior to study, constant rate, or variates Hazard-Constant rate or varies Attrition (Drop-Outs)-None, constant rate, or varies Equivalence Tests *New!* Proportions Means Power, Confidence Intervals, Tolerance Intervals Power is available for all procedures Confidence intervals are available for t-tests and z-tests, one sample proportions, two independent sample proportions, and one sample correlation Tolerance intervals are available for t-tests Tools for Computing Power Find N required for specified power Allows unequal N’s Cohen’s effect size conventions Store scenarios to list List may be scrolled, copied, printed Save data to disk Tables and Graphs Power as a function of sample size Power as a function of effect size, alpha, and sample size Confidence intervals as a function of sample size for mean, mean difference, standard difference, single proportion, difference between proportions, relative risk, log relative risk, odds ratio, log odds ratio, correlation Standard error as a function of sample size for mean, mean difference, rate difference, correlation Reports Full-page text report for all procedures Report includes discussion of both power and confidence interval width Reports, tables and graphs may be copied to clipboard and pasted into word-processing program Help Interactive guide Interactive Summary Tip of the day Windows 95® Help system including Table of Contents, Index, Step-by-Step Help and worked examples System Requirements Windows 9x,2000® or NT® VGA or SVGA monitor 12 MB hard disk space
		[ Home \| Products \| Services \| FAQs \| Downloads \| Order Info \| About Dataxiom ] ©2002Dataxiom Software, Inc.. All rights reserved. e-Mail comments and questions to support@dataxiom.com.