Differentiate Experimental and Observational Studies
Experimental: Includes RCT. They evaluate efficacy of therapeutic. educational, and administrative intervention. The Investigators control the allocation of the intervention
Observational:include Cohort, Case Control, and Cross Sectionals. They observe natural occurrences =. They examine causes, etiologies, predictors, better diagnoses
Identify the different types of primary literature
letter to the editor
a letter sent to the editor and reviewed only by the editor
opinion piece written by the editor or selected expert scholar in the field
short summaries of research projects to be presented as posters at a conference
generall a separate additional issue dedicated to conference abstracts/ proceedingsor specific drug/disease states
process of collecting, reviewing and presenting all available evidence
Statistical technique involved in extracting and combining data to produce a summary estimate. It is useful in providing trends
statements that were developed based on evidence and provide recommendations for patient care
-Developed by a panel of experts in the field
Best type of study for therapy/prvention?
best type of study for diagnosis?
blind comparison to a gold standard
best type of study for prognosis
Best type of study for Harm/Etiology?
best type of study for Cost benefit?
predictor variable. It is the variable which preceedes and is presumed to cause or be associated with the outcome
Outcome variable. It is the response to the independent variable.
Variables whose effects on the response variable may be indistinguishable
The degree to which the investigator draws the correct conclusions about what actually happened in the study
-Within the confines of the study, results appear to be accurate and the interpretation of the investigator is supported
External Validitty or Generalizability
-the degree to which theses conclusions can be appropriately applies to people and events outside of the study.
Importance of Intention to Treat
-compares outcomes betwen the study groups with every participants analyzed. It is real life. large numbers, and less bias
Advantage of RCT
Strongest design- demonstrates causality
Disadvantages of RCT?
Expensive, Time Consuming, not practical for rare disease, informed consen, compliance, loss to follow up, generalizability
What is a prospective cohort?
-Defines sample and measures predictor variables before outcome occurs.
-Measure characteristics in each subject which may predict a subsequent outcomes.
What are the strengths of a Prospective cohort?
-Good way to investigate a potential cause of a condition
- potential cause factors are established before the outcomes
-allows the investigator the opportunity for complete and accurate measurement of variables
-not a problem with inaccurate, incomplete, or missing records
-decrease potential bias of already knowing the outcomes
-No Recall bias- dont have to remember past events
What are the weakness of Prospective cohort?
- Expensive and inefficient method for rare outcomes
-Potential for subclinical forms of outcomes being evaluated
-Loss to follow up: Can bias results
-Change of habits
What is a Retrospective Cohort
-Defines the sample and collects the data about the predictor after the outcome has occurred
- Relies on adequate record keeping
What are the Strength of a Retrospective Cohort?
-Same as prospective
-Less time consuming
What are the weakness of a Retrospective Cohort?
-Limited control of sampling population
-limited control over type and frequency of measurement of predictor values
-Incomplete, inaccurate, or missing data necessary to answer each research question
What are the characteristics of a Case Control study?
-goal is to define the cause of disease or specific outcome
-identify group of subjects with the outcome of interest and a group without the outcome of interest
-Does not yield Incidence or Prevalence data
-provides estimate of strength of association between each predictor value and the presence of absence of disease
What are the strengths of a Case Control?
-efficiency for rare outcomes
-usefulness for generating hypotheses
-Dont need to wait years for disease to develop or track down
What are the weakness of a Case Control?
-Limits to information
-Selection of controls: need to be from same general population as cases but do not exhibit outcome
-differential measurement bias
What is Outcomes research?
-Seeks to understand the end results of particular health care practices and interventions
-Includes ECHO MOdel, PROs, and Survey
Why are Outcomes research important for pharmacy students?
1. Evidence based medicine is the standard for making decisions about patient care
2. Evaluating your service
3. Evaluating your patients
What can a survey measure?
What is the difference between a survey and a experiement?
experiment: if you measure dependent variables and manipulate independent variables.
Survey: is if you measure both independent and dependent variables.
How can you have independent variables that you do not manipulate?
-in experiments independent variables are causal, in surveys they are variables beleieved to be causal
What is reliability?
it is the repeatability, consistency, and dependability of a measure
Why cant me calculate reliability?
-bc we cant measure the true score component of an observation
What can we estimate the true score component of reliability as?
-the covariance between 2 observations of the same measure, and therefore we can estimate the reliability as the correlation between two observatins of the same measure.
what is inter-rater or inter-oberserver reliability?
-used to assess the degree to which diff. obervers give consistent estimates of the same phenomenon
What is Test-Retest reliability
measure intrument at 2 times for multiple persons. I.E. administered twice over a period of time. Compute the correlation between the 2 measures and assume no change in the underlying trait between time 1 and 2
What is Parallel Forms Reliability?
-Administer both forms to the same people and get a correlation between the two forms
- Problem: many items that reflect the same construct must be generated. The assumption is that the randomly divided halves are parallel or equivalent
What is internal consistency reliability:
-Items measuring the same phenom should correlate, therefore higher the correlation greater the internal consistency and thereby higher the reliability of the instrument
What is validity
A set of standards by which research can be judged. in general, validity relates to weather the concept being investigated are actually the ones being tested
- its an index of how well a test or procedure in fact measures what it is intended to measure
What is conclusion validity?
-relationship between what you did and what you saw
What is internal validity?
-is the relationship causal
what is external validity?
-Can it be generalized to other people places times
What is construct validity?
-generalized to constructs
What is Face Validity?
-a judgement call
-probs the weakest and easiest form of measurement validity
what is content validity?
- check the measure against the relevant content domain. also a judgement call. Can make this relatively rigorous with a systematic check.
What are the different types of Criterion related Validity?
-Predictive Validity: looks at measures ability to predict something it should be able to predict
-Concurrent Validity: does the measure distinguish betwen groups that it should distinguish against
What are the different types of Construct Validity?
-Factor Analysis: Whether the constructs empirically identified through factor analysis, correspond to the theoretical constructs which test developers hypothesized in developing the survey.
-Convergent Validity: Measures of constructs that related to each other should be strongly related
-Discriminant Principle: Measures of DIFFERENT constructs should NOT correlate highly with each other