Chapter 10 Flashcards
What is a clinical trial
an experimental study that examines the effect of interventions on patient or community populations
What is the difference between a therapeutic trial and a preventive trial
- A therapeutic trial examines the effect of a treatment or intervention on a particular disease
- A Preventive trial evaluates whether a procedure or agent reduces the risk of developing the disease
What is a between subjects design
Subjects are assigned to independent groups using a randomization procedure
What is a randomized block design
Subjects are first classified according to an attribute (blocking variable) and then randomized into treatment groups
What is a within subjects design (repeated measures)
A design in which subjects act as their own control
What is a pretest- posttest control group design
Used to compare two or more groups that are formed by random assignment. One group receives the experimental variable and the other acts as the control. Both groups are tested prior to and following treatment with the only difference between them being what happens between the measurements
What is a treatment arm of a study
The independent groups in a design. ie: the experimental group and the control group are each a treatment arm. If the study contained two experimental groups and one control, there would be 3 treatment arms
What is a two group pretest- posttest design
This design incorporates two experimental groups formed by random assignment without a “true control”. This is performed with a control condition is not feasible or ethical, often comparing a “new” treatment with an “old”.
What is a multi group pretest- posttest control group design
Like a pretest- posttest, compares a control group with an experimental group, but allows researchers to compare several treatment and control conditions. For instance 2 experimental groups and one control group.
How are pretest-posttest designs analyzed with Numeric Data
Change Scores; represent the difference between the posttest and pretest
How are pretest-posttest designs analyzed with Interval and Ratio Data
Difference scores are compared using an unpaired t test or if three or more groups, a one way analysis of variance (ANOVA)
How are pretest-posttest designs analyzed with Ordinal Data
Two groups: Mann Whitney U
Three or More: Kruskal-Wallis ANOVA
What is a posttest only control group design and when would you use it
Used to compare two or more groups that are formed by random assignment. One group receives the experimental variable and the other acts as the control. The groups are tested following treatment only, no pretest is performed. Used when a pretest is either impractical or potentially reactive
How are posttest only designs analyzed with Interval and Ratio Data
Two groups: unpaired t test
More than two groups: One way ANOVA
How are posttest only designs analyzed with Ordinal data
Two groups: Mann Whitney U
What is a factorial design
Incorporates two or more independent variables. Described according to their number of factors. Can also be described by number of levels within each factor. ie: 2x4 design includes two variables with 2 and 4 levels respectively
What is a two way factorial design
Incorporates two independent variables
What does it mean when independent variables are said to be “completely crossed” in a design
every level of one factor is represented at every level of the other factor and that each group represents a unique combination of the levels of these variables
What is the difference between the main effect and the interaction effect
In multifactorial studies, the main effect is concerned with examining each independent variable with scores collapsed across the other independent variable. Interaction effect is concerned with how one independent variable interacts with the other.
What is the purpose of using a randomized block design
When the investigator is concerned that an extraneous factor might influence differences between groups, one way to control for this is to build the variable into the design. Often an attribute variable such as gender. ie: To what degree does strength increase with an exercise program, may be different between the sexes, build this additional “blocking” variable into the design.
What analysis should be performed on a randomized block design
can be analyzed using a two way ANOVA, Multiple Regression, or Discriminant Analysis
What are some disadvantages of the repeated measures (within subjects) design
- potential for practice effects: the learning effect that can take place when one individual performs the same task over and over
- potential for carryover effects: when one subject is exposed to multiple treatment conditions
How can you limit the effects of Carryover in within subjects designs
By allotting sufficient time between successive treatment conditions to allow for complete dissipation of previous effects
When can a repeated measures (within subjects) design be considered “experiments”
When they incorporate randomization in the order of application of repeated conditions, and the comparison of one condition or intervention to another within one subject
Describe a one way repeated measures (within subjects) design
Involves a single factor experiment where one group of subjects is exposed to all levels of one independent variable
Describe how order effects should be considered when considering a repeated measures (within subjects) design
Because subjects are exposed to multiple treatment conditions in a repeated measures design, there must be a concern for potentially biasing effect of test sequence; This can be fixed by randomizing the order of presentation for each subject
What is a Latin Square
A matrix composed of equal numbers of rows and columns, designating permutations of sequence combinations; Used to decrease order effects in a repeated measures design
What data analysis should be performed on One way repeated measures designs
One Way ANOVA
Describe a crossover design
In a repeated measures design, when only two levels of an independent variable are repeated, a preferred method to control for order effects is to counterbalance the treatment conditions so that their order is systematically varied. In a crossover design, half the subjects receive treatment A and then B and half receive B then A. Two subgroups are created, one for each sequence, and subjects are randomly assigned to one of the sequences
When is the only time a crossover design should be used
Only in trials where a patients condition or disease will not change appreciably over time; not a reasonable approach when treatment effects are slow; especially useful when treatment conditions are immediately reversible
If a treatment in a crossover design has some cumulative effect, what is essential to allow for a common baseline for each treatment condition
A Washout period
What data analysis should be done for crossover designs
A paired t test can be used to compare change scores, or a two way ANOVA with two repeated measures can be used to compare pretest and posttest measures across both treatment conditions. The Wilcoxon signed ranks test should be used to look at change scores when ordinal data are used.
Describe a two way design with two repeated measures
Repeated measures studies involving more than one independent variable. Can be expanded to include three independent variables
What data analysis should be performed on two way repeated measures design
Two way ANOVA with two repeated measures is used to analyze differences across main effects and interaction effects
Describe a mixed design
When a study incorporates two independent variables, one repeated across all subjects, and the other randomized into independent groups
In a mixed design, what does it mean to have an independent factor and a repeated factor
- The variable whose levels have been randomly assigned is the independent factor
- The variable that is repeated and all subjects are exposed to all levels is the repeated factor
What data analysis should be performed on a two way design with one repeated factor
- Two way ANOVA is used to analyze main effects and interaction effects
What is a sequential clinical trial
A special approach to the randomized clinical trial. Allows for continuous analysis of data as they become available, instead of waiting until the end to compare data. Results are accumulated as each subject is tested so that the experiment can be stopped as soon as the evidence is strong enough to determine a significant difference between treatments
In a sequential clinical trial, what is meant by preference between groups
Specific criteria is set beforehand as a decision making factor for when to stop the experiment. Once this criteria is met, we can say that one group is “preferred” over the other
What is a sequential chart
For each outcome or measurement in the study, the result is charted as being favorable toward one group or the other group. It is set up in a certain way so that with enough favorable results for one study, the “boundary” in the chart is crossed and a terminal decision is made that that group is considered to be preferable to the other group.
What are the stopping rules when using a sequential chart
- If upper boundary is crossed, a terminal decision is made and we can recommend A
- If lower boundary is crossed, a terminal decision is made and we can recommend B
- If the middle boundary is crossed, there is no preference
What is the difference between a conditional decision and a terminal decision is a sequential trial
- Terminal decision is made when a boundary in the sequential chart is crossed
- Conditional decision is rendered without crossing a boundary, but is based on practical considerations and observation of the plotted path.
What is the difference between Efficacy and Effectiveness
- Efficacy is defined as the benefit of an intervention as compared to a control or standard program, provides information about the behavior or clinical variables under controlled, randomized conditions
- Effectiveness refers to the benefits and use of the procedure under “real world” conditions
