Get sample size updates by email

Receive educational sample size content

Get sample size updates by email

Receive great industry news once a week in your inbox

Get sample size updates by email

Receive educational sample size content

Get sample size updates by email

Receive great industry news once a week in your inbox

From fixed to flexible trial designs, the Summer 2020 nQuery release (v8.6) sees the continued strengthening of nQuery to help biostatisticians and clinical researchers save costs and reduce risk in their clinical trial designs.

New Adaptive/Pro Tables

New Base Tables

(Included in the* **Pro Package*)

The Summer 2020 (v8.6) release sees 5 new sample size tables added to nQuery Advanced PRO tier, covering various new adaptive designs.

**In this release, the following areas have been targeted for development:**

- Multi-Arm Multi-Stage Designs (MAMS) GSD for Means
- Generalized MCP-Mod (Multiple Comparisons Procedure - Modelling)
- Phase II Group Sequential Tests for Proportions (Fleming’s Design)

Adaptive designs, such as the group sequential design, have become widely used in clinical drug development. However, much of this development has been confined to the two-arm setting. A common situation in clinical trials is that in which an optimal treatment or dose has not been identified prior to the phase III trial. In this situation it may be desirable to begin a Phase II trial (or longer Phase III trial) with several treatment arms and conduct interim analyses that will allow the dropping of less promising arms and potentially seamlessly move those arms into Phase III. This type of design is commonly named a multi-arm multi-stage design.

The Multi Arm Multi Stage (MAMS) group sequential design extends the common two-arm group sequential design to a design in which multiple treatment arms can be compared to a common control arm and allows the trial to be stopped for efficacy or futility based on the best performing arm. In addition, it can be shown that less effective arms may be dropped at interim analyses without affecting the Type I error.

MAMS designs provide the ability to assess more treatments in less time than could be done with a series of two-arm trials and can offer significantly smaller sample size requirements when compared to that required for the equivalent number of two-arm trials.

In this release, a MAMS Group Sequential design has been implemented for a continuous endpoint under normality. This provides a familiar framework with which to conduct a MAMS design and explore the additional flexibility offered.

**The table added is as follows:**

- Multiple Arms Multiple Stage (MAMS) Group Sequential Design for Means

MCP-Mod (**M**ultiple **C**omparisons **P**rocedure - **Mod**elling) is an increasingly popular statistical methodology for dose-finding Phase IIb trials. Since its development at Novartis, MCP-Mod promises to devise proof-of-concept and dose-ranging trials with greater evidence and data that can prove critical for Phase III clinical trial design.

Combining the robustness of multiple comparisons procedures with the flexibility of modelling, MCP-mod combines these methods to provide superior statistical evidence from Phase II trials with regards to dose selection with the FDA & EMA approving MCP-Mod as fit-for-purpose (FFP).

The MCP-Mod methodology has been well developed for the case of normally distributed, homoscedastic data from a parallel group study design. In practice however many other types of endpoints are encountered and often in more complex settings like longitudinal studies for example. Generalized MCP-Mod extends the original MCP-Mod methodology to the context of general parametric models and for general study designs.

In this release, 3 tables will be added for generalized MCP-Mod. This extends the MCP-Mod methodology for a continuous endpoint (released in nQuery 8.5) to one for binary and count endpoints. Similar to the continuous MCP-Mod table, these new tables focus on the proof-of-concept stage of the study.

**The tables added are as follows:**

- Multiple Comparisons Procedure - Modelling for Poisson Rates (MCP-Mod)
- Multiple Comparisons Procedure - Modelling for Negative Binomial Rates (MCP-Mod)
- Multiple Comparisons Procedure - Modelling for Binary Outcome (MCP-Mod)

Typically, a phase II trial is designed to have a single stage in which a certain number of subjects are treated and the number of successes/responses are observed. However for ethical and economic reasons it may be of interest to stop the trial early, in particular for futility due to high failure rates at Phase II.

Based on the method described in Fleming (1982), the Phase II group sequential test is a one-sided multiple testing procedure that allows for early termination of the study if interim results are extreme. This is done by testing the accrued data at a number of interim stages and looking at the point estimate for the proportion of successes or responses observed at interim points.

Under this design, at each of the interim analyses, the trial may be stopped for futility if the interim cumulative number of successes is below an acceptance point and the trial may be stopped for efficacy if the interim number of successes is above a rejection point. In addition to the ethical benefit, this type of design allows for greater flexibility and cost savings while retaining operating characteristics similar to a fixed term trial.

In this release, a table will be added for a Phase II Group Sequential Tests for One Proportion. This is commonly referred to as Fleming’s Design.

**The table added is as follows:**

- Group Sequential Test of One Proportion (Fleming’s Design)

- Multiple Arms Multiple Stage (MAMS) Group Sequential Design for Means

- Multiple Comparisons Procedure - Modelling for Poisson Rates (MCP-Mod)
- Multiple Comparisons Procedure - Modelling for Negative Binomial Rates (MCP-Mod)
- Multiple Comparisons Procedure - Modelling for Binary Outcome (MCP-Mod)

- Group Sequential Test of One Proportion (Fleming’s Design)

To access the adaptive module you must have a **nQuery Advanced Pro** subscription. If you do, then nQuery should automatically prompt you to update.

You can manually update nQuery Advanced by clicking **Help>Check for updates.**

**CLICK HERE FOR FULL DETAILS ABOUT UPDATING**

(Included in all packages: *Base Plus & Pro Package*)

21 new sample size tables with additional endpoints and use cases have been added to the base nQuery module. This release summary provides an overview of which areas have been targeted, along with the full list of tables being added.**In this release, the four main areas targeted for development are:**

- Survival/Time-to-Event Trials
- Cluster Randomized Stepped-Wedge Designs
- Three Armed Trials Non-inferiority
- Confidence Intervals for Proportions

- Flexible Log-Rank Test Designs
- Tests for >2 Survival Curves
- Piecewise Weighted Log-Rank Test for Delayed Survival Effect
- One Sample Survival

In this release, two tables are added for flexible log-rank test designs. These provide many additional options to give more flexibility over the design and assumptions when designing a survival study. Some of the new areas covered included sample size determination that targets the study length given accrual rates. This moves beyond the fixed study length assumption in previous tables. Secondly, these tables allow piecewise accrual, hazard rates/survival curves and dropout under both the fixed length and accrual rate tables. This flexibility will allow users to test the effect of deviations from uniform accrual, exponential survival curves and other similar assumptions.

- Log-Rank Test, User-Specified Accrual Rates, Piecewise Survival and Dropout Rates
- Log-Rank Test, User-Specified Accrual, Piecewise Survival and Dropout Rates

In this release, two new tables were added that extend standard methods to this context. This release adds a table which uses an ANOVA-like log-rank omnibus test to test for the equality of a number of independent exponentially distributed log hazard rates. This release also adds a contrast test for exponential hazard rates and should be useful for dose-finding studies which have a survival endpoint.

- Omnibus Log-Rank Test of >2 Survival Curves
- Contrast Test for Equality of >2 Survival Curves

In this release, the Analytic Power Calculation Method based on the Piecewise Weighted Log-rank Test (APPLE) method approach for determining the sample size for a weighted log-rank test for a delayed effect is added. This method is useful in detecting a difference between two hazard functions when there is a delayed onset of the clinical effect. This results in a delayed separation of the survival curves for the experimental and control groups, so the proportional hazard assumption no longer holds. This type of design is often encountered in immunotherapy trials when the immune system takes time to respond to the treatment.

- Piecewise Weighted Log-rank Test for Delayed Effect Survival Model (APPLE Method)

In this release two one-sample tables for survival are included. The first of these builds upon prior one sample log-rank test tables by using an exact parametric approach for the one sample log-rank test which is more appropriate in trials with small to moderate sample sizes where the asymptotic assumptions of other methods may not hold. The second of these tables finds the number of events or confidence interval width for a one-sample confidence interval for a median survival time assuming an exponential survival curve and Type II censoring. The median survival is the time at which 50% of the population have the event.

- One Sample Testing using Exact Parametric Test
- One Sample Confidence Interval for Median Survival

Cluster-randomized designs are often adopted when there is a high risk of contamination if cluster members were randomized individually. Stepped-wedge designs are useful in cases where it is difficult to apply a particular treatment to half of the clusters at the same time.

In this release, three Stepped-Wedge CRT tables are added. The Cluster Randomized Stepped-Wedge design tables contained in this release will cater for both complete and incomplete designs. In a complete stepped-wedge design, all clusters are initially assigned to the control group and a fixed number of clusters switch to the treatment group at each step. In an incomplete design, the number of clusters switching at each step can vary. When a cluster has switched from the control to treatment group, it remains in the treatment group for the remainder of the study. At each point in time, different subjects are measured within each cluster and no subject is measured more than once. The types of incomplete designs available to users will be Balanced, Unbalanced, and Sequential designs. The option is also available for users to enter their own custom design pattern.

- CRT Stepped-Wedge design for Inequality of Two Means
- CRT Stepped-Wedge design for Inequality of Two Proportions
- CRT Stepped-Wedge design for Inequality of Two Poisson Rates

In this release, six new tables are added for three armed trials. These will cover this design type for continuous, incidence rate, proportion and survival endpoints using a common framework for the analysis of the trial type.

- Non-Inferiority Test for Means in a Three Armed Trial with Common Variance
- Non-Inferiority Test for Means in a Three Armed Trial with Uncommon Variance
- Non-Inferiority Test for Poisson Rates in a Three Armed Trial
- Non-Inferiority Test for Negative Binomial Rates in a Three Arm Trial
- Non-Inferiority Test for Proportions in a Three Armed Trial
- Non-Inferiority Test for Exponential Survival in a Three Armed Trial

Proportions are a common type of data where the most common endpoint of interest is a dichotomous variable. Examples in clinical trials include the proportion of patients who experience a tumour regression. There are a wide variety of confidence intervals proposed for binary proportions ranging from exact to maximum likelihood to normal approximations.

In this release, five new tables will be added to the binary proportion confidence intervals for the one sample, two sample and cluster randomized contexts. These tables include sample size determination for a variety of possible confidence intervals such as score intervals like the Farrington & Manning Score, Miettinen & Nurminen Score, Gart & Nam (Skewed) Score, Wilson Score; exact intervals such as the Clopper-Pearson and Cornfield; and asymptotic intervals such as the normal approximation and Log Ratio (Katz).

- Confidence Intervals for One Proportion
- Confidence Interval for the Difference between Two Proportions
- Confidence Interval for the Ratio of Two Proportions
- Confidence Interval for the Odds Ratio of Two Proportions
- CRT Confidence Interval for One Proportion

- Flexible Log-Rank Test Designs
- Tests for >2 Survival Curves
- Piecewise Weighted Log-Rank Test for Delayed Survival Effect
- One Sample Survival

- Log-Rank Test, User-Specified Accrual Rates, Piecewise Survival and Dropout Rates
- Log-Rank Test, User-Specified Accrual, Piecewise Survival and Dropout Rates

- Omnibus Log-Rank Test of >2 Survival Curves
- Contrast Test for Equality of >2 Survival Curves

- Piecewise Weighted Log-rank Test for Delayed Effect Survival Model (APPLE Method)

- One Sample Testing using Exact Parametric Test
- One Sample Confidence Interval for Median Survival

- CRT Stepped-Wedge design for Inequality of Two Means
- CRT Stepped-Wedge design for Inequality of Two Proportions
- CRT Stepped-Wedge design for Inequality of Two Poisson Rates

- Non-Inferiority Test for Means in a Three Armed Trial with Common Variance
- Non-Inferiority Test for Means in a Three Armed Trial with Uncommon Variance
- Non-Inferiority Test for Poisson Rates in a Three Armed Trial
- Non-Inferiority Test for Negative Binomial Rates in a Three Arm Trial
- Non-Inferiority Test for Proportions in a Three Armed Trial
- Non-Inferiority Test for Exponential Survival in a Three Armed Trial

- Confidence Intervals for One Proportion
- Confidence Interval for the Difference between Two Proportions
- Confidence Interval for the Ratio of Two Proportions
- Confidence Interval for the Odds Ratio of Two Proportions
- CRT Confidence Interval for One Proportion

If you have nQuery Advanced installed, nQuery should automatically prompt you to update.

You can manually update nQuery Advanced by clicking **Help>Check for updates.**

**CLICK HERE FOR FULL DETAILS ABOUT UPDATING**

**If your nQuery home screen is different, you are using an older version of nQuery.Please contact your Account Manager.**