Release Notes
Discover what's new
in nQuery

Version 9.5
From fixed to flexible trial designs, nQuery 9.5 is a major update to help biostatisticians and clinical researchers save costs and reduce risk.
Highlights include:
- Simulation for Survival Group Sequential Designs
- Two-Stage Bioequivalence via Maurer Method
- Bayesian Equivalence using Bayes Factor
- Expanded Bioequivalence Tables
- Innovative Vaccine Trial Designs
- Mixed Models for Hierarchical Designs
- Enhanced Non-Parametric Tests
- Redesigned Table Select Tool

Jump to Section
nQuery Pro Tier
What's new in the PRO tier of nQuery?
2 new major features added to the Pro tier of nQuery 9.5 in the following areas:
- Simulation for Survival Group Sequential Designs
- Two-Stage Bioequivalence using Maurer Method
1. Simulation For Group Sequential Designs
What is it?
Group Sequential Design is the most common adaptive design used in confirmatory clinical trials. This design allows trialists to stop a trial early at pre-specified interim analyses if there is sufficient evidence that treatment is effective (efficacy) or ineffective (futility).
Group sequential designs capacity to stop trials early can lead to significant cost savings while also getting vital treatments into the hands of patients faster. Simulation is considered a key aspect of evaluating the statistical and practical performance of adaptive designs.
By using simulation you can flexibly evaluate a design over a wide variety of scenarios and gain valuable insights into the pros and cons of your complex design.
nQuery 9.5 adds a tool for evaluating the operating characteristics of group sequential designs for survival analysis. It provides flexible inputs covering piecewise, complex accrual, hazard and dropout patterns and designs which include fixed term censoring, additional linear rank tests such as the Fleming-Harrington test and basing interim analysis on events or interim timing targets.
The simulation tool can also quickly take design choices from our group sequential survival table (GST3) for quick evaluation of your survival sequential design.
The simulation tool outputs the expected power, sample size, events, dropout and study length for your trial while also providing a summary of the timing of each look, the number of trials that stopped for efficacy and futility at each look plus the sample size recruited, events, dropout and average follow-up time at each look.
Group Sequential Survival Simulation Tool Features
-
Piecewise Poisson Accrual Model
-
Piecewise Exponential Model for Events and Dropout
-
Event-Based and Fixed Follow-up Time Designs
-
Interim Timing Based on Event or Analysis Time Targets
-
Log-Rank, Wilcoxon, Fleming-Harrington Test Statistics
-
Z-statistic and p-value scale boundaries for 1 and 2-sided Designs
- Simulation Report Covering:
-
Average Sample Size, Events, Dropout, Study Length, Accrual Period Length
-
Number Stopping for Efficacy and Futility at each Look
-
Timing of each look
-
Average Events, Sample Size, Dropout and Follow-up Time at each Look
-
-
Per-Simulation Summary + Individual Simulation Results Optional Outputs
2. Two-Stage Bioequivalence using Maurer Method
What is it?
Bioequivalence testing is the most common route for the approval of new generic medicines. This testing consists of evaluating if the pharmacokinetics (PK) parameters Area under the Curve (AUC) and maximum concentration (Cmax) are equivalent using the two one-sided tests (TOST) or (equivalent) confidence interval approach.
Crossover designs are designs where each subject is given multiple treatments in a pre-specified sequence. The most common crossover design is a 2x2 design where each subject is given treatment with half given treatment then control and other half given control and then treatment. Most bioequivalence testing is done via fixed term crossover designs where analysis is conducted after all followup is complete.
However, two-stage bioequivalence designs have been proposed by researchers to deal with design-stage uncertainty about key bioequivalence parameters. These two-stage designs allow for both the early evaluation of bioequivalence and to also adjust the sample size appropriately if the variance was misspecified for the initial sample size determination.
In nQuery 9.4, a table is added for the calculation of the overall power or required stage 1 sample size for a two-stage bioequivalence design using the Maurer Method which extends the Potvin 2-stage design (added by nQuery in 9.2 update) by providing strong Type I error control via the inverse-normal test while also including additional refinements to improve the design’s operating characteristics.
Table Added:
- Two-Stage Equivalence Test for Two Means in a Crossover Design using Inverse-Normal Combination Tests (Maurer's Design)
How to update?
If you have a subscription for the Query Pro Tier nQuery should automatically prompt you to update. You can manually update nQuery Advanced by clicking Help>Check for updates.
To discuss any aspect of your subscription, click here.
nQuery Plus Tier
What's new in the Plus tier of nQuery?
1 new sample size table has been added to the Plus tier of nQuery 9.5:
- Bayesian Equivalence (1 New Table)
3. Bayesian Equivalence
What is it?
Equivalence testing, where a researcher wants to establish if two treatments give equivalent results, is a common objective in areas such as generics development and medical devices. At present, most equivalence testing is conducted using frequentist methods such as the two one-sided tests (TOST) or checking if a confidence interval falls within the lower and upper equivalence limits.
Bayesian alternatives have been proposed for the testing of equivalence. This includes proposals such as the “Region of Practical Equivalence” (also known as ROPE) (added in nQuery 9.3 update) and using Bayes Factors. nQuery 9.3 implements a table which provides the required sample size for two-arm study assessing equivalence using Bayes Factors where a critical Bayes Factor in favour of equivalence is required to find in favour of bioequivalence.
Tables/Features added:
- Bayesian Equivalence using Bayes Factor
nQuery Base Tier
What's new in the Base tier of nQuery?
25 new sample size tables have been added to the Base tier in nQuery 9.5 in the following areas:
- Bioequivalence (8 Tables)
- Vaccine Studies (8 Tables)
- Mixed Models (6 Tables)
- Non-Parametric (3 Tables)
4. Bioequivalence
What is it?
Bioequivalence testing is the most common route for the approval of new generic medicines. This testing consists of evaluating if the pharmacokinetics (PK) parameters Area under the Curve (AUC) and maximum concentration (Cmax) are equivalent using the two one-sided tests (TOST) or (equivalent) confidence interval approach.
Crossover designs are designs where each subject is given multiple treatments in a pre-specified sequence. The most common crossover design is a 2x2 design where each subject is given treatment with half given treatment, then control and other half given control and then treatment.
However, there are many higher-order cross-over designs which are also commonly used where issues such as multiple treatments/doses, highly variable drugs and/or interest in carryover or interaction effects. nQuery 9.5 extends our bioequivalence offering by providing tools for common higher-order cross-over designs such as the partial replicate and Williams designs while also covering additional scenarios for crossover, parallel and multi-arm trials plus additional equivalent non-inferiority scenarios.
In nQuery 9.5, sample size tables are added in the following areas for the design of trials involving bioequivalence, alongside the 2-Stage Crossover Maurer table in Pro tier and Bayesian Bioequivalence using Bayes Factor in Plus tier described above.
Table(s) Added:
- Equivalence Test for Crossover Designs for Log-Scale Ratio (2x2x2, 2x2x3, 2x3x3 (Partial Replicate), 2x2x4, 2x4x2 (Balaam's), 2x4x4, 3x3x3, 3x6x3, 4x4x4, 2x2x2r (Liu))
- Two One-Sided Equivalence Tests (TOST) for Two Group Design with Unequal Variances
- Two One-Sided Equivalence Tests (TOST) for Two Group Design with Unequal n's
- Two One-Sided Equivalence Tests (TOST) for Ratio of Two Log-Normal Means with Unequal n's
- Equivalence Test for One-Way Analysis of Variance (ANOVA) with Equal Variances
- Equivalence Test for One-Way Analysis of Variance (ANOVA) with Unequal Variances
- Studentized Range Tests for Equivalence of Multiple Groups
- Non-Inferiority t-test for Two Means with Unequal Variances
5. Vaccine Studies
What is it?
Vaccines are one of the most successful medical innovations in clinical history. However the unique nature of vaccines where they are provided to entire populations rather than just patients with the disease of interest provides unique challenges when designing clinical trials. Therefore, trial design considerations such as sample size need to integrate these challenges to ensure optimal trial outcomes.
Vaccine efficacy is the primary target in clinical trials and the basis for most new vaccine approvals. While sample size based on parallel trial calculations can be used when the underlying disease's incidence rate is low it is often preferred to use an exact conditional approach where vaccine efficacy is calculated based on the symptomatic subjects only as a one proportion problem.
nQuery 9.5 adds a table to make this conditional approach more accessible for vaccine efficacy sample size calculations. Additionally, a complex vaccine efficacy endpoint based on a burden-of-illness composite measure is included in nQuery 9.5.
However, trials may be of interest for other vaccine characteristics such as vaccine safety, vaccine durability and impact vaccine boosters. Innovative design approaches are required to study these aspects of vaccine performance and some of these are now covered in nQuery 9.5
Tables Added :
- Non-Inferiority/Supersuperiority Test for Vaccine Efficacy with Extremely Low Incidence from Disease Rates (Conditional Method)
- Tests for Vaccine Efficacy with Composite Efficacy Measure (Burden-of-Illness) using the Ratio of Two Means (Fixed Time Design)
- Tests for Vaccine Efficacy with Composite Efficacy Measure (Burden-of-Illness) using the Ratio of Two Means (Fixed Event Design)
- Tests for Vaccine Efficacy with Composite Efficacy Measure (Burden-of-Illness) using the Difference of Two Means (Fixed Time Design)
- Tests for Vaccine Efficacy with Composite Efficacy Measure (Burden-of-Illness) using the Difference of Two Means (Fixed Event Design)
- Deferred Vaccine Tests for Durability and Harm in a Crossover Trial
- Test for Relative Incidence of Adverse Events using Self-Controlled Case Series (SCCS) Method without Age Effects
- Test for Relative Incidence of Adverse Events using Self-Controlled Case Series (SCCS) Method with Age Effects
6. Mixed Models
What is it?
Mixed models are models used when data is nested within multiple levels such as hierarchical and repeated measures designs. For example, when students (level 1) are nested within a class (level 2) which are nested within a school (level 3) which are nested within a school district (level 4). These are also known as multi-level or mixed-effects models.
For example, a common type of hierarchical trial design would be a 2-Level longitudinal hierarchical design in which subjects (level 2) are randomized to one of two treatments and then multiple observations (level 1) are made on each subject over time. In determining the sample sizes for such a design, the hierarchical data structure must be considered since both the first and second level units contribute to the total variation in the observed outcomes. In addition, level 1 data units (i.e. repeated measurements) from the same level 2 unit 9 (i.e. subject) tend to be positively correlated.
In nQuery 9.5, 6 new Mixed Model tables for factorial 2x2 designs based on Ahn, Heo, and Zhang (2015) were added.
Tables added:
- Mixed Models Tests for Slope-Interaction in a 2x2 Factorial 2-Level Hierarchical Design with Fixed Slopes (Level-2 Randomization)
- Mixed Models Tests for Slope-Interaction in a 2x2 Factorial 2-Level Hierarchical Design with Random Slopes (Level-2 Randomization)
- Mixed Models Tests for Slope-Interaction in a 2x2 Factorial 3-Level Hierarchical Design with Fixed Slopes (Level-2 Randomization)
- Mixed Models Tests for Slope-Interaction in a 2x2 Factorial 3-Level Hierarchical Design with Fixed Slopes (Level-3 Randomization)
- Mixed Models Tests for Slope-Interaction in a 2x2 Factorial 3-Level Hierarchical Design with Random Slopes (Level-2 Randomization)
- Mixed Models Tests for Slope-Interaction in a 2x2 Factorial 3-Level Hierarchical Design with Random Slopes (Level-3 Randomization)
7. Non-Parametric Analysis
What is it?
Non-parametric analysis are statistical tools which have far fewer assumptions than the commonly used parametric tests such as t-tests or ANOVA. These can be useful for complex scenarios where there is continuous data with extreme outliers or when dealing with ordinal data.
The most commonly used non-parametric tests are rank tests where the statistical analysis is applied to the sorted ranks of the underlying data rather than the data itself. Many common parametric tests have a non-parametric rank test analogue such as the Wilcoxon-Mann-Whitney U test for the two sample t-test, the Wilcoxon test signed-rank test for the one sample t-test and the Kruskal-Wallis test for one-way ANOVA.
In nQuery 9.5, our non-parametric test options are extended to the Kruskal-Wallis test for continuous or ordinal data (with multiple methods to calculate pairwise probabilities for both including parametric models and pilot data) while also providing the improved Lehmann algorithm for the Mann-Whitney U test with additional options to find the test moments based on parametric assumptions or pilot data.
In nQuery 9.5, sample size tables are added in the following areas for the design of trials involving non-parametric tests:
- Kruskal-Wallis Tests for Continuous Outcome
- Kruskal-Wallis Tests for Ordered Categories (Ordinal)
- Wilcoxon-Mann-Whitney U-test for Two Means (Lehmann Method)
What is it?
Since its initial launch nQuery Advanced has doubled the number of clinical trial design scenarios in adaptive design, Bayesian sample size and power + sample size calculations. However, based on user feedback this rapidly increasing number of options has sometimes made it difficult to find the specific table right for your specific trial scenario.
To address this, nQuery 9.5 features a comprehensive redesign of the Table Select tool, streamlining the process of identifying the most appropriate option for your clinical trial, regardless of your initial design framework
The overhaul uses an extensive tree-view with 12 high-level categories (see below) which cover various design types, endpoints, types of hypothesis and specific focus areas. Each category has sub-levels which can go up to three levels deep which can help further refine the ideal design table candidates for your clinical trial.
We have also ordered tables within each node to highlight the most likely preferred option based on our internal expertise and user feedback. In addition, we have added a dynamic search tool and the options to quickly view recently opened and recently added tables (such as those described elsewhere here) within our table select tool.
This tool will make finding the right design table for your trial easier than ever, as we continue to expand our trial design scenario options in the years ahead.
The 12 main categories are:
- Fixed Term Trials
- Adaptive Designs
- Bayesian Sample Size
- Means
- Proportions
- Survival Analysis
- Counts
- Regression
- Non-inferiority
- Equivalence
- Focus Areas
- Recently Added Design Tables
- Group Sequential Design
- Probability of Success (Assurance)
- Early Stage Designs (Phase I/II)
- Post-Marketing Surveillance (Phase IV)
- Pilot Study Sample Size
- Correlation/Agreement Measures
- Cluster Randomized/Mixed Models
- Vaccines
- Non-parametric
- Composite Endpoints
- Assistant Tools
Under each main category, there are multiple sub-categories with up to three levels available for further search refinement.
The overhauled table select also offers the following improvements:
- Recently Used Tables
- Dynamic Search Bar
- Table Select as tab for improved UX
- Table Category and Per-Table Icons
- List or Tile View options
- Open table via double-click
- Legacy Table Select available from the options menu
How to update?
nQuery should automatically prompt you to update. You can manually update nQuery Advanced by clicking Help>Check for updates.
To discuss any aspect of your subscription, click here.
nQuery Predict
Accurately predict your key trial milestones. Identify roadblocks and take action to keep your trial on schedule.
nQuery Predict is the most recent module to be added to the nQuery platform for clinical trial design.
Only available in the expert tier, nQuery Predict is a suite of tools that uses current data to project the likely trajectory of future enrollment or event milestones. With the nQuery Predict module, you can make more informed decisions based on real trial data as it becomes available.
Play this short video below for more information about milestone prediction
Get started with nQuery today
Start for free and upgrade as your team grows