Experimental Designs Flashcards
What involves numerical data that result from taking measurements on subjects, is objective, and involves deductive reasoning?
Quantitative Research
With quantitative research the researcher is an?
Objective Observer
What involves data derived from words such as questionnaires or interviews, is subjective and involves inductive reasoning?
Qualitative Research
With qualitative research the reseacher is what
Actively involved at times
What type of research employs the scientific method and is usually regarded at a higher level?
Quantitative
Qualitative research often leads to what?
Quantitative Studies
What is used to verify the effectiveness of treatments?
Pragmatic Research
Pragmatic research does not determine what?
How or Why the treatment work
What is used to establish the efficacy of treatments?
Explanatory Research
Explanatory research is capable of answering questions about?
How and Why treatment works
Patient selection is more strict in what type of research because patients are excluded due to co-morbid condtions?
Explanatory
What research observes and records various aspects of participants in a study?
Descriptive (Observational) Research
Descriptive research involves what?
Descriptive Statistics
What considers the relationships that may exist between variables and involves correlation and regression?
Relational Research
What explores whether an intervention causes or affects one or more outcome variable and is the most demanding type of research that involves detailed methods?
Causal Research
Casual Research looks for what?
Statistically significant difference between groups
What type of research has a random assignment to groups and is capable of determining cause and effect relationships?
Experimental Research
What type of research has no random assignment and provides much less evidence about cause and effect relationships?
Quasi-Experimental Research
What type of research does not involve random assignment or even a comparison group and merely involves the observation of one group before and after an intervention?
Non-Experimental Research
What is the research design notation?
R- random assignment
O- observation or measure
X- treatment or intervention
N- non-equivalent groups
A quasi-experiment has 2 groups but no?
Randomization
A non-experiment research design has only what?
1 group
Population parameters that are estimated from random samples are known as?
Unbiased Estimates
When patients are obtained using sequentially presenting patients or recruiting though advertisements this is referred to as?
Convenience Sampling
When subjects are separated into homogeneous subgroups based on factors such as age or disease severity this is known as?
Blocking
Blocking enhances comparison because the subgroups are more alike than?
The intact groups
What is it called when the intact groups are separated into subgroups based on prognostic factors?
Stratified Randomization
What is assignment that is often concealed from researches to avoid the temptation of allotting patients with certain traits to groups that will receive special treatment?
Concealment
What concealment is inadequate the apparent effects of the treatment may be distorted as much as or more than the size of what?
Effect being investigated
How do you determine sample size?
Ethically Important
Economical
If the sample size is to small it reduces the power of a study so that a treatment effect may not be noticeable when it is actually?
Present
What is regarded as the ultimate research design in health care also known as the classic experiment?
Randomized Controlled Trial (RCT)
RCT is best for what?
Treatment Effects (efficacy) Comparative Effects (effectiveness)
What are the downsides for an RCT?
Sample size prevents extensive safety or risk/benefit ratio
Applicability to practice setting
Demographics external validity
What is an inert substance or treatment?
Placebo
What are compared to determine if the drug resulted in a statistically significant treatment effect?
Drug and Placebo Groups
What is a non-therapeutic intervention that imitates the real treatment?
Sham
A sham is similar to what?
Placebo
What is the result that a treatment has on outcomes that is attributable specifically to the effect of the intervention?
Treatment Effect
What do patients improve?
Natural History
Actual Effect of Treatment
Nonspecific Effects of Treatment
The treatment is considered effective if the mean outcome of the treatment groups is what
Significantly better than placebo group
What is it called when people react differently when participating in experiments?
Hawthorne Effect
What is a factor in a clinical study?
Hawthorne Effect
What are systematic errors in a study that are caused by problems with selection or assignment of patients to groups or the measurements involved in the study?
Bias
Bias can render a study?
Invalid
What are the types of bias?
Sampling Bias
Experimenter (researcher) Bias
Exclusion Bias
A sampling bias means that during the selection process each person doesn’t have an equal change of being selected from what?
Source Population
What is the best safeguard against selection bias in RCT’s?
Random Assignment with Concealment
When examining or treating doctors influence a study’s results because of their expectancies or desires for a certain outcome this is known as?
Experimenter Bias
How do you dimish experimenter bias?
Blinding (masking) of researchers and participants
Experimenter bias can be divided into what 2 categories?
- Detection Bias
2. Performance Bias
What bias occurs when patients drop out of a study and are systemically different from subject who remain?
Exclusion Bias
What is the ability of an experiment to show that the explanatory variables actually caused the observed changes in the outcome variables?
Internal Validity
What are uncontrolled factors that can influence the relationship between variables in an experiment?
Extraneous Variables
Extraneous variables are unwanted because they do what?
Create error
What is a type of extraneous variable that affects the explanatory variables differently?
Confounding Variable
A confounding variable introduces what into the sutyd?
Systemic Error
The effects of a confounding variable cannot be separated from the what?
Outcome Variable
What research designs are particularly susceptible to confounding variables because the individual differences of subjects may act as confounding variables?
Quasi-Experimental Designs