USMLE Step 1 Biostatistics/Epidemiology Questions And Answers Graded A+

Adoption study - compares siblings raised by biological vs adoptive parents measures heritability and influence of environment Observer-expectancy effect - Occurs when a researcher's belief in the efficacy of a treatment changes the outcome of that treatment Chi square - tests the difference between 2 or more percentages or proportions of categorical outcomes (NOT THE MEAN VALUES) ANOVA - checks difference between the means of 3 or more groups Attributable Risk - (a / (a+b) ) - (c / (c+d) ) Case control study - compares a group of people with a disease to a group of people without a disease Asks, what happened? Measures odds ratio Cohort study - Compares a group wit ha given exposure or risk factor to a group without the exposure Asks who developed disease? Measures relative riskConfidence Interval - range from [mean - Z (SEM)] to [mean + Z (SEM)] Z = 1.96 for 95% CI Z = 2.58 for 99% CI On the test, it may be easier to remember the Z values as 2 and 2.5 for easier calculations and memorization Confounding Bias - Occurs when factor is related to both exposure and outcome, but is not the the causal pathway; factor distorts or confuses effect of the exposure on outcome Cross-sectional study - Collects data from a group of people to asses frequency of disease Asks what is happening? Measures disease prevalence Gaussian curve standard deviation %'s - +/- 1 SD = 68% +/- 2 SD = 95% +/- 3 SD = 99.7% Hawthorne effect - Occurs when the group being studied changes its behavior because they know they are being studied This looks at new incidences occurring during a time period Late-Look Bias - Information gathered at an inappropriate time (like surveying dead people) Lead-time Bias - Early detection confused with increased survival; seen with improved screening (the natural history of the disease is not changed but catching things earlier, like cervical cancer, makes it seem as though survival increased)Negative Predictive Value - TN / (FN + TN) Number needed to harm - 1 / attributable risk Number needed to treat - 1 / absolute risk reduction Odds Ratio - (a/c) / (b/d) OR ad / bc Phases of clinical trials - Phase 1: small number of healthy volunteers to measure safety, toxicity, and pharmacokinetics Phase 2: small number of sick volunteers with disease of interest to measure treatment efficacy, optimal dosing, and adverse effects Phase 3: large number of randomly assigned either to treatment under investigation of to the best available treatment (or to placebo group to compare the new treatment to the current standard of care or placebo Phase 4: Postmarketing surveillance trial of patients after approval to detect rare or long-term adverse effects Positive Predictive Value - TP / (TP + FP) Power - 1-beta or in other words, 1 - type 2 error (increasing sample size will increase power, there is POWER in numbers. Also, increasing Precision will increase power) Prevalence - # of existing cases / population at risk Looks at ALL current casesProcedure Bias - Subjects in different groups are not treated the same Recall Bias - Knowledge of presence of disorder alters recall by subjects