USMLE Step 1 Epidemiology
Number Needed to Harm
1/Attributable Risk =
1/[(Ppl w/ Intervention & Disease/Total Ppl w/ Intervention)-(Ppl w/o Intervention &
Disease/Total Ppll w/o Intervention)]
Factorial Study
Study design where different combination of treatments are given to different patient groups
Advantages include that researchers evaluate multiple independent variables at the same time
Internal Validity
The extent to which we can draw cause-and-effect inferences from a study
Affected by:
-Lack of Blinding
-Observer Bias
-Hawthorne Effect
Limited # of Participants
Parameter which limits Statistical Power
Regression Analysis
Study of 2+ independent variables which may be qualitative or quantitive and 1 dependent
variable while adjusting for others variables fo interest
Convenience Sampling
Survey method which uses a sample of people who are readily available to participate
I.e.
-Email surveys
-Standing in a public place + recruiting participants
Number Needed to Harm
1/Attributable Risk =
1/[(Ppl w/ Intervention & Disease/Total Ppl w/ Intervention)-(Ppl w/o Intervention &
Disease/Total Ppll w/o Intervention)]
Factorial Study
Study design where different combination of treatments are given to different patient groups
Advantages include that researchers evaluate multiple independent variables at the same time
Internal Validity
The extent to which we can draw cause-and-effect inferences from a study
Affected by:
-Lack of Blinding
-Observer Bias
-Hawthorne Effect
Limited # of Participants
Parameter which limits Statistical Power
Regression Analysis
Study of 2+ independent variables which may be qualitative or quantitive and 1 dependent
variable while adjusting for others variables fo interest
Convenience Sampling
Survey method which uses a sample of people who are readily available to participate
I.e.
-Email surveys
-Standing in a public place + recruiting participants
