ACRP CP FINAL STUDY PAPER 2026
QUESTIONS WITH ANSWERS GRADED A+
●● When and how should statistical plans be outlined? Answer: All
details for the design and conduct of the statistical plan should be
outlined in the protocol prior to beginning the trial.
●● Robustness Answer: Sensitivity of the overall conclusions to various
limitations of the data, assumptions, and analytical approaches to data
analysis.
●● How to select a patient population. Answer: In early phases of trials,
it may be beneficial to select groups of patients who have a greater
chance of observing specific effects of interest. In later confirmatory
studies, it is helpful to loosen the I/Es in order to have a population that
is reflective of the target population. Make sure to still maintain
homogeneity.
●● Primary Variable Answer: Primary endpoint. The variable capable of
providing the most clinically relevant and convincing evidence directly
related to the primary objective of the trial. SHOULD ONLY BE ONE.
●● Secondary Variables Answer: Supportive measurements related to
the primary variable or measurements of effects related to the secondary
objectives. These should also be defined prior to initiation of the trial.
,●● Composite Variables Answer: When multiple clinical measurements
are combined using a pre-defined algorithm. The algorithm would need
to be defined prior to initiation of the trial. (Arthritis scales, psychiatric
scales)
●● Global Assessment Variables Answer: Integration of objective
variables as well as the investigator's overall impression of the state or
change in state of the subject. Not advisable to use global assessments as
a primary variable.
●● Type I Error Answer: False Positive
●● What is the downfall to having multiple primary variables? Answer:
Increased risk of type I error due to multiplicity. If using more than one
primary variable, the effect on the type I variable should be explained
prior to study start.
●● Surrogate Variables Answer: Indirect criteria used to look at patient
outcomes. There is a risk that it is not a true indicator. They also may not
yield a quantitative measure of clinical benefit that can be weighed
against adverse events.
●● Categorized Variables Answer: Categorization of continuous or
ordinal variables. (Ex: minimum percentage improvement). This can
, result in the loss of power of the analysis. A higher sample size would
need to be utilized.
●● How to Avoid Bias Answer: Blinding and randomization.
●● Blind Review Answer: Checking of data during the period of time
between trial completion and the breaking of the blind.
●● Unrestricted Randomization Answer: a randomization method in
which all subjects have the same chance to receive each treatment
●● Randomization in Blocks Answer: Increases the comparability of
treatment groups, especially if characteristics may change over time.
Also makes sure that the treatment groups will be of relatively equal
size. Need to select block lengths that are sufficiently short to limit
imbalance but long enough to avoid predictability.
●● Dynamic Allocation Answer: The allocation of treatment to a subject
is influenced by the current balance of allocated treatments, and in a
stratified trial, the strata to which a subject belongs and the balance
within the stratum.
●● Parallel Group Design Answer: Subejcts are randomized to one of
two or more study arms, each arm being allocated to a different
treatment. The most commonly used design for confirmatory trials.
QUESTIONS WITH ANSWERS GRADED A+
●● When and how should statistical plans be outlined? Answer: All
details for the design and conduct of the statistical plan should be
outlined in the protocol prior to beginning the trial.
●● Robustness Answer: Sensitivity of the overall conclusions to various
limitations of the data, assumptions, and analytical approaches to data
analysis.
●● How to select a patient population. Answer: In early phases of trials,
it may be beneficial to select groups of patients who have a greater
chance of observing specific effects of interest. In later confirmatory
studies, it is helpful to loosen the I/Es in order to have a population that
is reflective of the target population. Make sure to still maintain
homogeneity.
●● Primary Variable Answer: Primary endpoint. The variable capable of
providing the most clinically relevant and convincing evidence directly
related to the primary objective of the trial. SHOULD ONLY BE ONE.
●● Secondary Variables Answer: Supportive measurements related to
the primary variable or measurements of effects related to the secondary
objectives. These should also be defined prior to initiation of the trial.
,●● Composite Variables Answer: When multiple clinical measurements
are combined using a pre-defined algorithm. The algorithm would need
to be defined prior to initiation of the trial. (Arthritis scales, psychiatric
scales)
●● Global Assessment Variables Answer: Integration of objective
variables as well as the investigator's overall impression of the state or
change in state of the subject. Not advisable to use global assessments as
a primary variable.
●● Type I Error Answer: False Positive
●● What is the downfall to having multiple primary variables? Answer:
Increased risk of type I error due to multiplicity. If using more than one
primary variable, the effect on the type I variable should be explained
prior to study start.
●● Surrogate Variables Answer: Indirect criteria used to look at patient
outcomes. There is a risk that it is not a true indicator. They also may not
yield a quantitative measure of clinical benefit that can be weighed
against adverse events.
●● Categorized Variables Answer: Categorization of continuous or
ordinal variables. (Ex: minimum percentage improvement). This can
, result in the loss of power of the analysis. A higher sample size would
need to be utilized.
●● How to Avoid Bias Answer: Blinding and randomization.
●● Blind Review Answer: Checking of data during the period of time
between trial completion and the breaking of the blind.
●● Unrestricted Randomization Answer: a randomization method in
which all subjects have the same chance to receive each treatment
●● Randomization in Blocks Answer: Increases the comparability of
treatment groups, especially if characteristics may change over time.
Also makes sure that the treatment groups will be of relatively equal
size. Need to select block lengths that are sufficiently short to limit
imbalance but long enough to avoid predictability.
●● Dynamic Allocation Answer: The allocation of treatment to a subject
is influenced by the current balance of allocated treatments, and in a
stratified trial, the strata to which a subject belongs and the balance
within the stratum.
●● Parallel Group Design Answer: Subejcts are randomized to one of
two or more study arms, each arm being allocated to a different
treatment. The most commonly used design for confirmatory trials.
