Back to Explorer

E9 Statistical Principles for Clinical Trials

FinalCenter for Drug Evaluation and Research Center for Biologics Evaluation and Research09/16/1998
Good Clinical Practiceintention-to-treat principleblind reviewintention-to-treatBlind breakingDouble-blindbiasstandard operating proceduresType I error

Description

The efficacy and safety of medicinal products should be demonstrated by clinical trials that follow the guidance in E6 Good Clinical Practice: Consolidated Guidance adopted by the ICH, May 1, 1996. The role of statistics in clinical trial design and analysis is acknowledged as essential in that ICH guidance. The proliferation of statistical research in the area of clinical trials coupled with the critical role of clinical research in the drug approval process and health care in general necessitate a succinct document on statistical issues related to clinical trials. This guidance is written primarily to attempt to harmonize the principles of statistical methodology applied toclinical trials for marketing applications submitted in Europe, Japan and the United States.

Key Topics

Terms and concepts identified from this document

Scope & Applicability

Product Classes

3
Investigational product

Product being tested in clinical trials

medical product

Subject of safety and tolerability assessments

investigational drug

The drug being tested in clinical trials for MDS.

Stakeholders

5
sponsor

responsible for justifying omission of studies

statistician

Appropriately qualified and experienced individual responsible for statistical work; decisions made after the statistician has had access to the treatment codes

Independent Data Monitoring Committee

Body that may propose protocol amendments or maintain trial integrity

trial statistician

responsible for ensuring the protocol covers statistical issues; member of the team responsible for the clinical study report; Person responsible for the statistical aspects of the trial

Investigator

Responsible for qualifications, training, and trial conduct; Individual responsible for trial conduct and data governance at a site.; May delegate tasks but retains overall responsibility; Person responsible for the conduct of the clinical trial at a trial site; Responsible for trial conduct and participant safety; Responsible for trial conduct, data integrity, and investigational product management.; Individual responsible for trial conduct at a site and informing the institution.; maintaining

Regulatory Context

Regulatory Activities

7
New Drug Application

Rule does not apply to products marketed under an NDA

Bioequivalence trials

Trials falling into the category of equivalence trials.

Noninferiority trial

Justification for noninferiority margin for early Lyme disease using doxycycline as active control.

Equivalence trial

Trial designed to show that two treatments do not differ by more than a specified margin.; In an equivalence or noninferiority trial, use of the full analysis set is generally not conservative.; showing response to treatments differs by clinically unimportant amount

Superiority trial

The clinical trial design context for the instrument.

Confirmatory trials

Trials designed to provide evidence for claims

marketing application

sponsors should obtain advice from FDA prior to initiating trials for marketing applications; Clinical trials designed to support a marketing application

Document Types

10
Integrated Summary

Summary of safety and tolerability

gaiyou

required for marketing applications in Japan

expert report

required for marketing applications in the EU

integrated summary reports

required for marketing applications in the United States

clinical study reports

structure and content of clinical study reports is the subject of ICH E3

analysis plan

details of any adjustment procedure should be set out in the analysis plan

statistical analysis plan

Basic statistical principle for clinical trials

clinical study report

Source of cumulative clinical trial exposure data

protocol amendment

changes should always be described by a protocol amendment

case record forms

media for data transfer

Attributes

10
Sample Size

statistically justified calculation required in the plan

Per protocol set

Subset of subjects who complied with the protocol sufficiently

toxicity grading scale

Use of a toxicity grading scale should be prespecified

outliers

A similar approach should be adopted to exploring the influence of outliers.

confidence intervals

reporting of results that appropriately account for the adaptive design

Type II error

statistical property of hypothesis tests that should be accurate

Power

A parameter required for sample size calculation.

Inter-rater Reliability

Property of assessment variables for detecting changes.

robustness

feature of acceptable assay performance

Type I error

Study-wise control recommended for hypothesis testing in subgroups

Technical Details

Substances

1
Placebo

Accountability procedures for the investigational product including placebo; used as a reference in a clinical trial

Testing Methods

10
Interim Analysis

Whether an interim analysis is planned.; Rationale for any interim analysis planned with respect to its purpose and timing.; Analyses conducted while the trial is ongoing for stopping or adapting

electrocardiograms

Special safety test used in clinical trials

laboratory tests

Includes clinical chemistry and hematology used to assess safety

frequentist methods

significance tests and confidence intervals

survival analysis methods

used to exploit relationship of adverse events to duration of exposure

descriptive statistical methods

safety and tolerability implications are best addressed by applying descriptive statistical methods

survival analysis

survival analysis methods should be considered for long-term treatment

frequentist approach

usual frequentist approach to the analysis of clinical trial data

analysis of covariance

Data are usually analyzed using analysis of covariance (ANCOVA)

Imputation techniques

Imputation techniques may also be used in an attempt to compensate for missing data.

Processes

10
Data Capture and Processing

Trial design considerations

unblinded analysis

analysis where new questions may emerge from observed data

meta-analysis

formal evaluation of quantitative evidence from two or more trials

interim analyses

multiplicity may arise from interim analyses

exploratory analysis

subgroup or interaction analyses are exploratory

Data Transformation

selection of the data transformation method(s) can be driven by the type of data

blind review

plan should be reviewed and updated as a result of the blind review; Possible amendments to the way in which the analysis will deal with protocol violations should be identified during the blind review.; carry out the blind review of the planned analysis

Data Capture

The collection of data and transfer of data from the investigator to the sponsor

Interim analysis

Group sequential designs are used to facilitate the conduct of interim analysis.; breaking the blind to make treatment comparisons; analysis intended to compare treatment arms prior to formal completion

Stratification

Grouping defined by important prognostic factors measured at baseline.; Purpose of performing certain screening assessments.

Clinical Concepts

7
Adverse events

Safety findings including deaths and post-mortem examinations

toxicity

Signs requiring immediate cessation of drug use

serious adverse events

Committee should complete real-time review of these events.

Bioequivalence

Studies needed if comparative dissolution similarity is not achieved

Adverse Effects

Potential risks like low blood pressure or irregular heartbeat from ingredient interactions.

adverse event

Reason a patient may be unable to complete a PRO measure; Treatment discontinuation due to AE.; Reason for treatment discontinuation or PRO non-completion.

patient population

The group for which the device is intended

Identified Hazards

Hazards

1
Carryover

Impact during study sample analysis should be assessed and reported

Standards & References

External Standards

1
WHO-Art

Hierarchical medical dictionary for coding adverse reactions

Specifications

5
primary variable

variable providing the most clinically relevant evidence for the primary objective

reference ranges

Definitions of measurement units and reference ranges of laboratory variables

Equivalence margin

Maximum acceptable difference in population means for quantitative attributes; Criteria used to conclude equivalence if the confidence interval is within this range

secondary variables

supportive measurements related to primary or secondary objectives

composite variable

integration of multiple measurements into a single variable

ICH References (10)

ICH E9

Statistical Principles for Clinical Trials; Discourages deterministic procedures due to high risk of bias; Notes that the use of Bayesian methods in clinical trials may be considered.

ICH E7

Studies in Support of Special Populations: Geriatrics

ICH E2B

Data standard for electronic transmission of individual case safety reports

ICH M1

MedDRA is also known as ICH M1

ICH E2A

Provides definitions for seriousness criteria; ICH E2A recommends blinded therapy should not be reported

ICH E3

document remedial actions in the clinical trial report; Structure and Content of Clinical Study Reports standards.

ICH E1A

The Extent of Population Exposure to Assess Clinical Safety: For Drugs Intended for Long-term Treatment of Non-Life-Threatening Conditions

ICH E6

Referenced for safety data collection and adverse event reporting plans.

ICH E4

Dose-Response Information to Support Drug Registration

ICH E8

General Considerations for Clinical Studies

Related MFDS Guidelines

Korean regulatory guidelines covering similar topics

See Also (8)

E9 Statistical Principles for Clinical Trials | Guideline Explorer | BioRegHub