E9 Statistical Principles Flashcards
double blind
both experimenter and subjects are blinded
crossover study
Each study participant receives all treatments that are being investigated but at different times
Order of treatments is randomized
Washout often included between treatments
Pros of Crossover Study Design
Each patient serves as their own control.
Reduces between-subject variability.
Allows for detection of smaller effect sizes with reduced sample sizes.
Effect Size
Quantitative measure of the magnitude of a phenomenon (eg. the correlation between 2 variables).
Small effect size is one in which there is a real effect, i.e. something is really happening in the world - but which you can only see through careful study.
Parallel Study
Two groups of treatments: A & B
One group receives only A, other group receives only B
most common clinical trial design for confirmatory trials
Longitudinal Study
Repeated observations of the same variables over short or long periods of time.
Often observational but can be structured as longitudinal randomized experiments.
Large Effect Size
Can be seen by the naked eye, easily observed.
Small Effect Size
There is a real effect, i.e. something is really happening in the world - but which you can only see through careful study.
Confounders
Variable that influences both dependent and independent variables so that the results do not reflect the actual relationship
Why is the influence of confounders reduced in crossover studies?
Each patient is their own control.
Optimal crossover designs require ________ subjects.
fewer
Which patient population best aligns with crossover study design?
patients with chronic conditions.
May be infeasible or unethical for curative treatments or rapidly changing conditions.
What are two main issues with crossover studies?
- “Order” Effects. Order of treatment may effect outcome, eg. drug with many adverse effects given first, making patients taking a 2nd, less harmful medication, more sensitive to any adverse effects.
- “Carry-over”. Carry-over between treatments which confounds estimates of treatment effects. In practice “carry-over” effects can be avoided with a sufficiently long “wash-out” period between treatments. However, planning for sufficently long wash-out periods requires expert knowledge of the dynamics of the treatment, which is often unknown.
A trial with the primary objective of showing that the response to the investigational product is not clinically inferior to a comparative agent (active or placebo)
Non - inferiority trial
Trial where the treatment assignment is not known by the study participant - The investigator and staff are aware of the treatment but the subject is not
Single Blind study
The formal evaluation of the quantitative evidence from two or more trials bearing on the same question
Meta-analysis
Comparator (product)
An investigational or marketed product (i.e. active control) or placebo, used as reference in a clinical trial
Non-inferiority Trial
A trial with the primary objective of showing that the response to the investigational product is not clinically inferior to a comparative agent (active or placebo)
A variable that provides an indirect measurement of effect in situations where direct measurement of clinical effect is not feasible or practical
surrogate variable
Therapeutic Confirmatory Study
Phase III
-demonstrate or confirm efficacy/benefit** (the ability to produce a desired or intended result).
-confirm earlier clinical studies that drug is safe and effective to use. - -Provide bases of marketing approval
Phase I (Human Pharmacology Study)
-initial admin of IP to humans.
-Conducted in healthy volunteers or selected population of patients who have disease.
-Tests IP safety, tolerability, pharmacokinetics (what body does to drug), pharmacodynamics (what drug does to body)
investigational product
a pharmaceutical form of an active ingredient or placebo being tested or used as a reference in a clinical trial, including a product with a marketing authorization when used or assembled in a way different from the approved form, or when used for an unapproved indication, or when used to gain further information about an approved use
Exploratory Trial
-What Phase?
-Breifly describe
- Phase II
-Explore therapeutic efficacy - safety and efficacy of drug in selected population
Audit Trial
Documentation that allows reconstruction of the course of events
Pharmacokinetics study
- PK
- The study of how the body affects a drug after administration.
A trial with the primary objective of showing that the response to the investigational product is superior to a comparative agent (active or placebo)
Superiority Trial
composite variable
when a single primary variable can’t be selected from multiple measurements associated with primary variable. A useful strategy is to combine the multiple measurements into a single variable
Full analysis set
the set of subjects that is as close as possible to the ideal implied by the intention-to treat principle
Primary Variable
Capable of providing the most clinically relevant and convincing evidence related to primary objective of trial
Double dummy
Double dummy is a technique for retaining the blind when administering supplies in a clinical trial, when the two treatments cannot be made identical. Supplies are prepared for Treatment A (active and indistinguishable placebo) and for Treatment B (active and indistinguishable placebo). Subjects then take 2 sets of treatment: either A (active) and B (placebo) or A (placebo) and B (active)
biomedical studies not performed on human subjects
nonclincal studies
Equivalence trial
A trial where the primary objective of showing the response to 2 or more treatment differs by an amount which is NOT clinically important
content validity
Assesses whether a test/trial is representative of all aspects of the construct/ domain.
how study population changes in different phases of research
-In earlier phases of drug development the choice of subjects may be heavily influenced by the wish to maximize the chance of observing specific clinical effects of interest,
A. Study population may be very narrow.
-By the time the confirmatory trials are undertaken, the subjects should more closely mirror the target population.
B. helpful to relax the inclusion and exclusion criteria as much as possible within the target population, while maintaining sufficient homogeneity to permit precise estimation of treatment effects
How to avoid bias
blinding and randomization
Interim analysis
What does it require?
What if treatment is proven beneficial or harmful?
an analysis of data that is conducted before data collection has been completed.
-Requires unblinded access to treatment group assignments
-if a treatment can be proven to be clearly beneficial or harmful compared to the concurrent control, or to be obviously futile, based on a pre-defined analysis of an incomplete data set while the study is on-going, the investigators may stop the study early
What is a Notice of Claim Investigational Exemption for New Drug (IND)?
Involves 3 phases of clinical trials that require informed consent including approvals from FDA and organization sponsoring IND and institutional IRB of trial site; new drug application (NDA) that reports on preclinical and clinical data with FDA review; approval for marketing and post marketing surveillance
What is Investigation Exemption for New Drug - New Drug Application (NDA)
Full reports of all preclinical and clinical data; FDA review.
Phases of clinical trials
Phase I trials: Initial testing of experimental drug/treatment in 20–80 people to evaluate safety and side effects.
Phase II trials: Experimental drug/treatment is administered to 100–300 people for effectiveness and further safety evaluation
Phase III trials: Experimental drug/treatment is administered to 1,000–3,000 to confirm effectiveness, safety, monitor side effects, compare to standard treatments.
Phase IV trials: Post FDA approval and available to the public. Safety tracking for risks, benefits, and best use.
Primary Variable
Capable of providing the most clinically relevant and convincing evidence related to primary objective of trial
Secondary variables
either supportive measurements related to the primary objective or measurements of effects related to the secondary objectives
The most important design techniques for avoiding bias in clinical trials
are blinding and randomization
Multicenter trials benefits
a. Accepted way of evaluating a new medication more efficiently
b. Provides a better basis for the subsequent generalization of its findings
There are two distinct types of monitoring that generally characterize confirmatory clinical trials
i. Trial monitoring concerns the oversight of the quality of the trial
ii. Interim Analysis
The primary concern in a confirmatory trial is
a) Efficacy
b) Safety
c) Pharmacodynamics
d) Pharmacokinetics
The primary concern in a confirmatory trial is
a) Efficacy
Statistical principles are relevant to
a) Phase I trials
b) Phase Il trials
c) Phase Ill trials
d) All of the above
Statistical principles are relevant to
d) All of the above
a) Phase I trials
b) Phase Il trials
c) Phase Ill trials
Bias is defined as
a) Error in miscalculation of the final drug effect
b) Trend to extrapolation in missing values
c) Deviation in the estimation of a treatment effect from its true value
d) Failure to use a complete data set for analysis
Bias is defined as
c) Deviation in the estimation of a treatment effect from its true value
Factors associated with bias can include
a) Study design
b) Study conduct
c) Data analysis and interpretation
d) All of the above.
Factors associated with bias can include
d) All of the above
a) Study design
b) Study conduct
c) Data analysis and interpretation
Robustness refers to all of the following except
a) Sensitivity of the conclusions to various limitations of data
b) Sensitivity to the conclusions data to various limitations of assumptions
c) Lack of an effect of study conclusions to alternative analytic approaches
d) The health status of the subjects in the clinical trial
Robustness refers to all of the following except
d) The health status of the subjects in the clinical trial
A test is robust if it still provides insight into a problem despite having its assumptions altered or violated
A development plan purpose is to
a) Find a dose range that is simultaneously safe and effective
b) Prove that the risk benefit relationship is acceptable
c) Identify the subjects who would most benefit and indications for the use
d) All of the above.
A development plan purpose is to
d) All of the above
a) Find a dose range that is simultaneously safe and effective
b) Prove that the risk benefit relationship is acceptable
c) Identify the subjects who would most benefit and indications for the use
In a confirmatory trial the following apply
a) Phase 1 results are verified in phase 2 trials
b) Test the key hypothesis, effect size and clinical significance
c) Conduct the trial in a large sample of subjects
d) The design is that described for the use of an approved drug
In a confirmatory trial the following apply
b) Test the key hypothesis, effect size and clinical significance
Exploratory trials (select all that apply)
a) Explore a wide range of hypotheses
b) Provide formal proof of efficacy
c) Need flexible designs
d) Are designed to explore new uses for an approved drug
Exploratory trials (select all that apply)
a) Explore a wide range of hypotheses
c) Need flexible designs
The population of a clinical trial reflects all of the following except:
a) May be narrow in early trials to maximize effects
b) Tend to mirror the target disease population in later trials
c) Is always significantly large in Phase 1 trials to ensure reliable toxicology results
d) Must balance eligibility criteria and treatment effects
The population of a clinical trial reflects all of the following except:
c) Is always significantly large in Phase 1 trials to ensure reliable toxicology results
The primary variable reflects all of the following except
a) Must provide convincing evidence for the primary objective
b) Is usually the efficacy variable
c) Must provide significant support for secondary variables
d) May be restricted in some trials only to safety and tolerability
The primary variable reflects all of the following except
c) Must provide significant support for secondary variables
Secondary variables must
a) Be supportive measurements related to the primary objective
b) Need to have their role and importance defined carefully in a clinical trial
c) Should be limited to answering a limited number of questions in the trial.
d) All of the above.
Secondary variables must
d) All of the above
a) Be supportive measurements related to the primary objective
b) Need to have their role and importance defined carefully in a clinical trial
c) Should be limited to answering a limited number of questions in the trial.
Global assessment variables reflect all of the following except
a) They are developed to measure the overall usefulness of treatment
b) Require that a scale be developed and detailed in the protocol
c) Should define how to assign subjects to a unique category on a scale
d) Are never used as a primary variable in most clinical trials
Global assessment variables reflect all of the following except
d) Are never used as a primary variable in most clinical trials
Which of the following statements regarding surrogate variables is false?
a) They are used when direct observation of clinical efficacy is not practical
b) May show an effect in the absence of a clinical outcome
c) May not yield a quantitative measure of clinical benefit
d) Often allow for an assessment of benefits relative to adverse effects.
Which of the following statements regarding surrogate variables is false?
d) Often allow for an assessment of benefits relative to adverse effects.
For a surrogate variable to be reliable, they should
a) Have a plausible relationship to clinical outcome
b) Be supported by epidemiologic evidence
c) Reflect a treatment effect that corresponds to clinical outcome
d) All of the above
For a surrogate variable to be reliable, they should
d) All of the above
a) Have a plausible relationship to clinical outcome
b) Be supported by epidemiologic evidence
c) Reflect a treatment effect that corresponds to clinical outcome
A double blind trial is one in which the following are unaware of the treatment received
a) Sponsor
b) Investigator
c) Subject
d) All of the above
A double blind trial is one in which the following are unaware of the treatment received
d) All of the above
a) Sponsor
b) Investigator
c) Subject
In a single blind trial the person who is unaware of the treatment is
a) Subject
b) Investigator
c) Monitor
d) Clinical coordinator
In a single blind trial the person who is unaware of the treatment is
a) Subject
Breaking the blind for a single subject
a) Implies breaking the blind for the study group
b) May be done at the discretion of the monitor
c) Should be implemented when deemed essential for subject’s care
d) Always involves a serious adverse event
Breaking the blind for a single subject
c) Should be implemented when deemed essential for subject’s care
In a parallel group design the subjects
a) Randomized to two arms each with a different treatment
b) Are evaluated before and after drug administration
c) Are randomized to a sequence of two treatments
d) Are evaluated simultaneously for varying combinations of treatments
In a parallel group design the subjects
a) Randomized to two arms each with a different treatment
In a crossover design the subjects
a) Randomized to two arms each with a different treatment
b) Are evaluated before and after drug administration
c) Are randomized to a sequence of two treatments
d) Are evaluated simultaneously for varying combinations of treatments
In a crossover design the subjects
c) Are randomized to a sequence of two treatments
In a pre- post design the subjects
a) Randomized to two arms each with a different treatment
b) Are evaluated before and after drug administration
c) Are randomized to a sequence of two treatments
d) Are evaluated simultaneously for varying combinations of treatments
In a pre- post design the subjects
b) Are evaluated before and after drug administration
The most commonly used study design in clinical trials is:
a) Parallel design
b) Crossover design
c) Pre-Post design
d) Factorial design
The most commonly used study design in clinical trials is:
a) Parallel design
For a successful crossover design:
a) Carryover form a pervious treatment should be minimized
b) The disease should be chronic and stable
c) Drug effects should develop fully within the treatment period
d) All of the above
For a successful crossover design:
d) All of the above
a) Carryover form a pervious treatment should be minimized
b) The disease should be chronic and stable
c) Drug effects should develop fully within the treatment period
Multi center trials have the following features except
a) They are more efficient as they accrue sufficient subjects
b) May facilitate generalization of findings
c) May present the only method for accruing subjects in rare diseases
d) Are easily administered for uniform implementation of the protocol
Multi center trials have the following features except
d) Are easily administered for uniform implementation of the protocol
Drug efficacy is best established by
a) Demonstrating superiority to placebo in a placebo control trial
b) Demonstrating superiority in an active control trial
c) Demonstrating a dose -response relationship
d) All of the above
Drug efficacy is best established by
d) All of the above
a) Demonstrating superiority to placebo in a placebo control trial
b) Demonstrating superiority in an active control trial
c) Demonstrating a dose -response relationship
*investigational drug is compared with an established treatment that has a known degree of effectiveness, with the aim of either demonstrating that the test treatment is as good as or is superior to the active treatment
A placebo controlled trial would be considered unethical if
a) The drug has been shown to be efficacious in a superiority trial
b) The drug has been shown equivalent to active control in a non-inferiority trial
c) Drug has shown serious side effects in preclinical studies
d) All of the above
A placebo controlled trial would be considered unethical if
a) The drug has been shown to be efficacious in a superiority trial
An equivalence or non-inferiority trial is one in which
a) Efficacy of a test drug is no worse than an active comparator
b) Multiple doses of a test drug are compared to multiple doses of as standard drug
c) a only
d) a and b
An equivalence or non-inferiority trial is one in which
d) a and b
a) Efficacy of a test drug is no worse than an active comparator
b) Multiple doses of a test drug are compared to multiple doses of as standard drug
An active control is best represented by
a) Any drug that has shown activity against the disease
b) A drug that has been shown to be non-inferior in an equivalence trial
c) A drug that has shown efficacy in a superiority trial
d) All of the above
An active control is best represented by
c) A drug that has shown efficacy in a superiority trial
In assessing sample size, the items that need to be specified include all except
a) The primary variable and test statistic
b) The null and alternative hypothesis
c) The projected cost of the trial for the designated sample size
d) Type I and Type Il errors
In assessing sample size, the items that need to be specified include all except
c) The projected cost of the trial for the designated sample size
The type of monitoring in a confirmatory clinical trial may include
a) Oversight of the quality of the clinical trial
b) Breaking the blind for treatment comparison and interim analysis
c) a only
d) a and b
The type of monitoring in a confirmatory clinical trial may include
d) a and b
a) Oversight of the quality of the clinical trial
b) Breaking the blind for treatment comparison and interim analysis
Oversight of the quality of a trail involves review of all of the following except
a) Protocol adherence
b) Conflict of interest
c) Patient accrual and retention
d) Review of design assumptions
Oversight of the quality of a trail involves review of all of the following except
b) Conflict of interest
The ideal data analysis set is one in which
a) Procedures are followed perfectly
b) Data records are complete
c) There is no loss to patient follow up
d) All of the above
The ideal data analysis set is one in which
d) All of the above
a) Procedures are followed perfectly
b) Data records are complete
c) There is no loss to patient follow up
Irregularities in the data analysis set may arise from
a) Protocol violations
b) Patient withdrawals
c) Missing values
d) All of the above
Irregularities in the data analysis set may arise from
d) All of the above
a) Protocol violations
b) Patient withdrawals
c) Missing values
The intention to treat analysis set includes
a) All treated subjects
b) Only subjects with complete drug treatments
c) Subjects who have undergone the minimum number of acceptable trial visits
d) All randomized subjects
The intention to treat analysis set includes
d) All randomized subjects
Missing values in a data set
a) Are generally discounted in data analysis
b) Are eliminated by extrapolation
c) Contribute to bias
d) Have no effect on hypothesis testing
Missing values in a data set
c) Contribute to bias
Safety and tolerability of the drug are best assessed in
a) Phase I trials
b) Phase Il trials
c) Continuously during drug development
d) Phase Ill trials
Safety and tolerability of the drug are best assessed in
c) Continuously during drug development
Blind review occurs
a) At various stages of a clinical trial
b) After study close out visit for all sites has been completed
c) At pre-specified intervals
d) Between trial completion and breaking of the blind
Blind review occurs
d) Between trial completion and breaking of the blind
The term double dummy refers to
a) Double blinded trial
b) Placebo controlled trial
c) Technique to retain the blind when administering supplies to non-identical groups
d) All of the above
The term double dummy refers to
c) Technique to retain the blind when administering supplies to non-identical groups
The DSMB monitors
a) The safety data
b) Patient accrual
c) Data accuracy
d) Missing data
The DSMB monitors
a) The safety data
The DSMB can recommend
a) Continuation, modification or termination of a sponsor’s trial
b) The continued enrollment of patients in light of safety events
c) The submission of serious adverse safety events for regulatory review
d) The submission of serious adverse safety events to the IRB.
The DSMB can recommend
a) Continuation, modification or termination of a sponsor’s trial
Methods to avoid the bias in a clinical trial generally involve
a) Single-blind only
b) Double-blind only
c) Single or double blind
d) Open label
Methods to avoid the bias in a clinical trial generally involve
c) Single or double blind
A trial designed on the basis of some evidence of benefits is likely (to bring to completion) to be
a) Exploratory trial
b) Confirmatory trial
c) Phase IV trial
d) Open label trial
A trial designed on the basis of some evidence of benfits is leily to be
b) Confirmatory trial
Mutlicenter trials can be implemented for
a) Open label trials
b) Exploratory trials
c) Confirmatory trials
d) Any stage of clinical drug development
Mutlicenter trials can be implemented for
d) Any stage of clinical drug development
