| PASS
11 Upgrade
We are pleased to announce the release of PASS 11. PASS 11 adds
17 new power and sample size procedures and features
to PASS, including procedures for analysis of covariance,
group-sequential testing, sensitivity and specificity,
Poisson means testing, tests for two ordered categorical
variables, Williams test for the minimum effective dose,
Control Charts, an enhanced user interface, increased
computation speed, and an improved graphics system.
New Procedures
Analysis of Covariance (ANCOVA)
Group-Sequential Tests for Two Means using Simulation
Group-Sequential Non-Inferiority Tests for Two Means using Simulation
Group-Sequential Tests for Two Proportions using Simulation
Group-Sequential Non-Inferiority Tests for Two Proportions using Simulation
Group-Sequential Logrank Tests using Simulation
Sensitivity and Specificity Tests for One Group
Tests for Independent Sensitivities of Two Groups
Tests for Paired Sensitivities
Tests for One Poisson Mean
Tests for Two Poisson Means
Tests for Two Ordered Categorical Variables
Williams Test for the Minimum Effective Dose
Control Charts for Process Means
Control Charts for Process Variation
New Features
Enhanced User Interfaces
Improved Graphics System
Known Problems Fixed by PASS 11
Mouse scrolling now works on all PASS windows
Compatible with all computer language settings
Compatibility
PASS 11 is fully compatible with Windows
7, Vista, and XP on both 32-bit and 64-bit operating systems.
Click here
to view the complete system requirements.
Prices
Upgrade from PASS 2008:
$349 (academic/government)
$395 (commercial)
Upgrade from Earlier Versions:
$449 (academic/government)
$495 (commercial)
Click here to view complete price lists.
Ordering
To order your upgrade, call us at 1-800-898-6109 (US only) or (801) 546-0445, fax us at (801)
546-3907, email us at
sales@ncss.com, or order
from our secure
online order form.
Documentation
PDF versions of the documentation are available directly
from each procedure window. These may be displayed or printed. The
documentation is also available in the help system. You can purchase a
printed copy of the three manuals for $200.
Analysis of Covariance
(ANCOVA)
The new ANCOVA procedure computes power and sample size for comparing means when equal-slope covariates are included.
Group-Sequential Tests using Simulation
These procedures can be used to determine power, sample size and/or boundaries for group sequential tests comparing two groups. For one-sided tests, significance and futility boundaries can be produced. Boundaries can be computed based on popular alpha- and beta-spending functions (O’Brien-Fleming, Pocock, Hwang-Shih-DeCani Gamma family, linear) or custom spending functions. Boundaries can also be input directly to verify alpha- and/or beta-spending properties. Futility boundaries can be binding or non-binding.
Group-Sequential Difference and Non-Inferiority Tests for Two Means
The common two-sample T-Test and the Mann-Whitney U test for group sequential tests can be simulated in these procedures. The distributions of each of the groups under the null and alternative hypotheses can be specified directly using over ten distributions including normal, exponential, Gamma, Uniform, Beta, and Cauchy.
Complex Group-Sequential Difference and Non-Inferiority
Tests for Two Proportions
Simulated group-sequential tests in this procedure include the common two-sample Z-test with or without pooled standard error and with or without continuity correction, the Mantel-Haenszel test, the T-test, and Fisher’s Exact test. The available non-inferiority tests are the common two-sample Z-test with or without pooled standard error and with or without continuity correction, the T-test, and three score tests.
Complex Group-Sequential Logrank Tests
This procedure can be used to determine power, sample size and/or boundaries for group sequential tests comparing two survival curves. Available tests are the common logrank test, the Gehan-Wilcoxon test, the Tarone-Ware test, the Peto-Peto and Modified Peto-Peto tests, and the Fleming-Harrington tests. Survival rates can be piece-wise customized to specify proportional hazard scenarios or non-proportional hazard scenarios. Loss-to-follow-up and noncompliance proportions can be entered with piece-wise flexibility. Accrual times and accrual patterns are completely flexible. Maximum and average (expected) sample sizes are reported as well as the alpha and/or beta spent and incremental power at each look.
Sensitivity and Specificity Tests for One, Two, and
Paired Groups
These three procedures give power or required sample size for a single diagnostic test when sensitivity and specificity are both of interest, for comparing two diagnostic tests for sensitivity, and for tests of paired sensitivity where the sensitivities of two diagnostic tests are each performed on the same subject.
Tests for One and Two Poisson Means
These procedures calculate the power or sample size for testing whether the Poisson parameter λ is less than or greater than a specified value, and for testing whether the ratio of two Poisson means is different from a specified value (usually one).
Tests for Two Ordered Categorical Variables
This module computes power and sample size for tests comparing two ordered categorical variables. A common example of such variables are those with a Likert scale response.
Williams Test for the Minimum Effective Dose
This procedure can be used to calculate the power and sample size for experiments in which the treatments are a series of monotonically increasing (or decreasing) doses of a substance, where the minimum effective dose is of interest.
Control Charts for Process Means and Process Variation
Using simulation, these two new procedures allow you to study the run length distribution of Shewhart (Xbar), Cusum, FIR Cusum, and EWMA process control charts for means, and R, S, and S with probability limits process control charts for variation. The in-control distribution can be input directly or a specified number of in-control preliminary samples can be simulated based on a user-determined in-control distribution. The out-of-control distribution is flexible in terms of distribution type and distribution parameters. This procedure can also be used to determine the necessary sample size to obtain a given run length.
Simplified Interface
The interface has been redesigned to make the user input easier to complete and the output easier to navigate. The output now has a navigation tree that allows the user to quickly jump to any portion of the output. The graphics system has been separated from the primary input, resulting in fewer tabs and more straightforward parameter input. The flow of the input options is now top to bottom with sensible option groupings. The PASS home window now offers easier options for finding the procedures by allowing for quick category views and procedure searches as well as the menus.
Improved Graphics System
The graphics system has been separated from the primary input options. The graphics system now has a final-look preview and a full array of color, style, and size options for all aspects of the graphs. |
