What’s New in PASS 2021

What’s New in PASS 2021

 

We are pleased to announce the release of PASS 2021. PASS 2021 adds 68 new sample size procedures and includes a variety of enhancements. Among the new procedures are those for various Vaccine Efficacy Tests and Confidence Intervals, Group-Sequential Tests, Reference Limits, Ratio of Means, Agreement in Method Comparison, Equivalence Tests for ANOVA, Studentized Range Tests, Dose-Finding, ANCOVA Contrasts, Intraclass Correlation, Two Ordered Categorical Variables, Bayesian Approach, and the Ratio of Two Proportions.

 

New Procedures in PASS 2021

Vaccine Efficacy

• Confidence Intervals for Vaccine Efficacy using a Cohort Design
• Confidence Intervals for Vaccine Efficacy using an Unmatched Case-Control Design
• –
• Superiority by a Margin Tests for Vaccine Efficacy using the Ratio of Two Proportions
• Non-Inferiority Tests for Vaccine Efficacy using the Ratio of Two Proportions
• Superiority by a Margin Tests for Vaccine Efficacy using the Ratio of Two Proportions in a Cluster-Randomized Design
• Non-Inferiority Tests for Vaccine Efficacy using the Ratio of Two Proportions in a Cluster-Randomized Design
• –
• Superiority by a Margin Tests for Vaccine Efficacy using the Ratio of Two Poisson Rates
• Non-Inferiority Tests for Vaccine Efficacy using the Ratio of Two Poisson Rates
• Superiority by a Margin Tests for Vaccine Efficacy using the Ratio of Two Poisson Rates in a Cluster-Randomized Design
• Non-Inferiority Tests for Vaccine Efficacy using the Ratio of Two Poisson Rates in a Cluster-Randomized Design
• –
• Superiority by a Margin Tests for Vaccine Efficacy using the Ratio of Two Negative Binomial Rates
• Non-Inferiority Tests for Vaccine Efficacy using the Ratio of Two Negative Binomial Rates
• –
• Superiority by a Margin Tests for Vaccine Efficacy using the Hazard Ratio (Cox’s Proportional Hazards Model)
• Non-Inferiority Tests for Vaccine Efficacy using the Hazard Ratio (Cox’s Proportional Hazards Model)
• –
• Tests for Vaccine Efficacy with Extremely Low Incidence
• Superiority by a Margin Tests for Vaccine Efficacy with Extremely Low Incidence
• Non-Inferiority Tests for Vaccine Efficacy with Extremely Low Incidence
• –
• Tests for Vaccine Efficacy with Composite Efficacy Measure (Ratio)
• Tests for Vaccine Efficacy with Composite Efficacy Measure (Difference)

 

Group-Sequential Tests (with Efficacy & Futility Boundary Options)

For each of these group-sequential power and sample size procedures, there are corresponding group-sequential analysis and sample-size re-estimation procedures in NCSS 2021.

• Group-Sequential Non-Inferiority Tests for One Mean with Known Variance (Simulation)
• Group-Sequential Superiority by a Margin Tests for One Mean with Known Variance (Simulation)
• –
• Group-Sequential Non-Inferiority T-Tests for One Mean (Simulation)
• Group-Sequential Superiority by a Margin T-Tests for One Mean (Simulation)
• –
• Group-Sequential Tests for One Proportion (Simulation)
• Group-Sequential Non-Inferiority Tests for One Proportion (Simulation)
• Group-Sequential Superiority by a Margin Tests for One Proportion (Simulation)

 

Ratio of Two Means

• Tests for the Ratio of Two Means (Normal Data)
• Non-Inferiority Tests for the Ratio of Two Means (Normal Data)
• Superiority by a Margin Tests for the Ratio of Two Means (Normal Data)
• Equivalence Tests for the Ratio of Two Means in a 2×2 Cross-Over Design (Normal Data)

 

Two Poisson Rates in a Cluster-Randomized Design

• Superiority by a Margin Tests for the Difference Between Two Poisson Rates in a Cluster-Randomized Design
• Non-Inferiority Tests for the Difference Between Two Poisson Rates in a Cluster-Randomized Design
• –
• Superiority by a Margin Tests for the Ratio of Two Poisson Rates in a Cluster-Randomized Design
• Non-Inferiority Tests for the Ratio of Two Poisson Rates in a Cluster-Randomized Design

 

Method Comparison Studies

• Exact Method for Assessing Agreement in Method Comparison Studies

 

Confidence Intervals

• Confidence Intervals for a Percentile of a Normal Distribution using Assurance Probability
• Confidence Intervals for a Percentile of a Normal Distribution using Expected Width
• –
• Confidence Intervals for the Bland-Altman Range of Agreement using Assurance Probability
• Confidence Intervals for the Bland-Altman Range of Agreement using Expected Width
• –
• Confidence Intervals for Regression-Based Reference Limits using Assurance Probability
• Confidence Intervals for Regression-Based Reference Limits using Expected Relative Precision

 

Studentized Range

• Studentized Range Test
• Studentized Range Tests for Equivalence
• Non-Zero Null Studentized Range Tests

 

Analysis of Variance

• One-Way Analysis of Variance Contrasts Allowing Unequal Variances
• One-Way Analysis of Variance Contrasts Assuming Equal Variances
• –
• One-Way Analysis of Variance Allowing Unequal Variances错误!超链接引用无效。
• One-Way Analysis of Variance Assuming Equal Variances (F-Tests)
• One-Way Analysis of Variance F-Tests using Effect Size
• –
• Equivalence Tests for One-Way Analysis of Variance Assuming Equal Variances
• Equivalence Tests for One-Way Analysis of Variance Allowing Unequal Variances
• Non-Zero Null Tests for One-Way Analysis of Variance Assuming Equal Variances
• –
• 2×2 Factorial Analysis of Variance Allowing Unequal Variances

 

Analysis of Covariance

• Analysis of Covariance (ANCOVA)
• Analysis of Covariance Contrasts

 

Two Ordered Categorical Variables

• Tests for Two Ordered Categorical Variables (Non Proportional Odds, Wilcoxon-Mann-Whitney)

 

Logrank Tests

• Logrank Tests (Freedman)

 

Weibull

• One-Sample Tests of Weibull Hazard Rates
• Confidence Interval for Weibull Shape Parameter

 

Fisher’s Exact Test

• Fisher’s Exact Test

 

Intraclass Correlation

• Confidence Intervals for Intraclass Correlation with Assurance Probability (Lower One-Sided)
• Confidence Intervals for Intraclass Correlation with Assurance Probability (Two-Sided)

 

Two Proportions

• Confidence Intervals for Odds Ratio of Two Proportions using an Unmatched Case-Control Design
• Confidence Intervals for the Difference of Two Correlated Proportions

 

Phase II Selection Design

• Randomized Phase II Selection Design for Binary Data (Simon)

 

Dose-Finding

• Dose-Finding using the Bayesian Continual Reassessment Method (CRM)

 

Bayesian Approach

• Tests of Two Means Assuming Equal Variances using a Bayesian Approach

 

Three-Arm Mean Ratio

• Equivalence Tests for the Mean Ratio in a Three-Arm Trial (Normal Data)

 

Enhancements in PASS 2021

Report Auto-sizing

A program-wide auto-sizing of report columns was integrated, giving improved column spacing in reports.
 

Old Report Columns Display

 

 

New Report Columns Display

 

 

Random Seed

For all procedures that utilize random number generation, a Random Seed option was added, to obtain output reproducibility.

Decimals Display

A system-wide improvement was implemented to better determine the number of decimals to display in each column.

Access Improvements

The Report Options dropdown was added to the Procedure Window toolbar. The menu and toolbar of the Output and Gallery windows were updated.

Window Loading Time

Optimization techniques were employed to improve the loading time of various windows.

Operational Qualification (Validation) Processing Time

The time to execute the operational qualification (all-procedure validation) was significantly reduced.

 

Compatibility of PASS 2021

PASS 2021 is fully compatible with Windows 10, 8.1, 8, 7, and Vista SP2, on both 32-bit and 64-bit operating systems.