EPIB 301 Midterm: Quiz Two Review
Premium

4 Pages
82 Views
Unlock Document

Department
Epidemiology and Biostatistics
Course
EPIB 301
Professor
Dyer
Semester
Spring

Description
EPIB301 Test 3 Review Ecological vs. Cohort Studies: • Ecological: studies of populations, not individual o Uses things like census data, etc. o Group-level data o Comparison studies & correlation o FALLACY: findings cannot be applied to an individual level ▪ Forces at individual level different than group-level o ADVANTAGES: context of health, can happen when no individualized data, rapid & minimal resources ▪ DISADVANTAGES: fallacy & imprecise measures of exposure • Cohort: population group (with certain characteristic) followed over time: birth, age, work, etc. o Prospective, retrospective & historical perspective cohort studies ▪ Prospective: classified by exposure and observed over time for incidence of disease • Originally no subjects have disease ▪ Retrospective: study is made AFTER some people get disease/outcome, begin identifying/enrolling subjects AFTER outcome occurs • Historical/pre-existing data at baseline used • Not always reliable if based on subject’s memory o ADVANTAGES: direct observation of risk, exposure is well defined, exposures may be uncommon, temporal factor is known o DISADVANTAGES: expensive & time consuming, complicated, subjects may be lost, exposures can be misclassified o Relative Risk used ▪ Incident rate in exposed/incident rate in unexposed ▪ THOSE WHO HAD X had RR TIMES THE RISK COMPARED TO THOSE WHO DID NOT HAVE X o Attributable risk ▪ Difference between incidence rate in exposed vs unexposed • Incidence exposed – incident not exposed ▪ Percent is divided by incidence exposed and multiplied by 100 o Population risk ▪ Incidence in total population – incidence in non-exposed Case Control Studies • Alternative to cohort but much more efficient • Measures association between exposure & outcome • SUBJECTS DEFINED ON BASIS OF PRESENCE OR ABSENCE OF DISEASE OR OUTCOME OF INTEREST o Cases are people with the disease, controls are those who do not have disease • Uses past data from medical records, personal interviews, etc to work backwards and differentiate between cases and controls and differing factors Odds Ratio used in CASE CONTROL • AD/BC o OR > 1 suggests positive association o OR or 2 means association is 2 times higher among exposed o OR < 1 suggests exposure might be a protective factor o OR = 1 suggests no association or not statistically significant • Odds: A/C, B/D Randomized Control Trial • Randomly allocated into study and control groups to receive treatment/prevention • Gold standard Quasi-Experimental Study • Manipulates study factor but does not assign individual subjects randomly to exposed/non exposed groups Threats to Internal Validity of a Study • History o Events occurring with treatment may have impact o Reduced by selecting patients from same location and give same schedule for testing • Maturation o Naturally occurring changes over time may have impact o Reduce by all subjects same age • Testing o Exposure to test can affect scores on later exposures to that same test, may have impact o Different tests to yield different variables o Less threat when time between pre and post-test is large • Instrumentation o Changes in equipment (calibration, adjustment, etc) can have impact o
More Less

Related notes for EPIB 301

Log In


OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


OR

By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.


Submit