question

Observational Studies

answer

1. Cross-sectional 2. Case-control 3. Cohort 4. Twin concordance 5. Adoption

question

Observational Studies, Temporality 1. Cross-sectional 2. Case-control 3. Cohort 4. Twin concordance 5. Adoption

answer

1. Cross-sectional: Prospective 2. Case-control: Retrospective 3. Cohort: Prospective, Retrospective 4. Twin concordance: Prospective, Retrospective 5. Adoption: Prospective, Retrospective

question

Observational Studies, Measures 1. Cross-sectional 2. Case-control 3. Cohort 4. Twin concordance 5. Adoption

answer

1. Cross-sectional: Prevalence 2. Case-control: Odds Ratio (OR) 3. Cohort: Relative Risk (RR) 4. Twin concordance: Heritability and influence of environmental factors 5. Adoption: Heritability and influence of environmantal factors

question

Observational Studies, Examples 1. Cross-sectional 2. Case-control 3. Cohort

answer

1. Cross-sectional: What is happening? 2. Case-control: Patients w/ COPD had higher odds of a history of smoking than those without COPD. 3. Cohort: Smokers had a higher risk of developing COPD than nonsmokers.

question

Observational Studies, Stable Factor 1. Cross-sectional 2. Case-control 3. Cohort

answer

1. Cross-sectional: One group, Point in time 2. Case-control: Risk factor 3. Cohort: Disease or no disease

question

Observational Studies, Variable Factor 1. Case-control 2. Cohort 3. Twin concordance 4. Adoption

answer

1. Case-control: Diseased/Non-diseased 2. Cohort: Exposed/Non-exposed 3. Twin concordance: Disease and Risk factor 4. Adoption: Disease and Risk factor

question

Observational Studies, Design 1. Cross-sectional 2. Case-control 3. Cohort 4. Twin concordance 5. Adaption

answer

1. Cross-sectional: Assesses frequency of disease (and related risk factor), Shows risk factor association but does not establish causality. 2. Case-control: Looks for prior exposure or risk factor. 3. Cohort: Looks to see if exposure incr. the likelihood of disease. 4. Twin concordance: Compares frequency with which both mono- and dizygotic twins develop the same disease 5. Adaption: Compares siblings raised by biological vs. adoptive parents

question

Clinical trial

answer

Compares therapeutic benefit of 2 or more treatments, or of treatment and placebo

question

Clinical trial, Study quality

answer

Improves when study is: - randomizes - controlled - double-blinded

question

Clinical trial, Study Sample

answer

Humans

question

Triple-blind Clinical trial

answer

Double-blinded plus additional blinding of the researchers analyzing the data.

question

Clinical trial, Phase I, Typical Study Sample

answer

Small Healthy

question

Clinical trial, Phase I, Purpose

answer

Assesses: - Safety - Toxicity - Pharmacodynamics - Pharmacokinetics

question

Clinical trial, Phase II, Typical Study Sample

answer

Small Disease of interest

question

Clinical trial, Phase II, Purpose

answer

Assesses: - Treatment efficiacy - Optimal dosing - Adverse effects

question

Clinical trial, Phase III, Typical Study Sample

answer

Large, Diseased Randomly assigned to treatment or control group

question

Clinical trial, Phase III, Purpose

answer

Compares new treatment to current standard of care.

question

Clinical trial, Phase IV, Typical Study Sample

answer

Postmarketing surveillance of patients after treatment is approved

question

Clinical trial, Phase IV, Purpose

answer

Detects: - Rare adverse effects - Long-term adverse effects Can result in treatment being withdrawn from market.

question

Double-blind Clinical trial

answer

Neither Patient nor Doctor knows whether patient is in the treatment or control group.

question

Sensitivity

answer

True-positive rate Proportion of all people with disease who test positive. Probability that test detects disease when disease is present.

question

High Sensitivity Test, Use

answer

Screening in disease with low prevalence.

question

Sensitivity approaching 100%

answer

Desirable for ruling out disease. Indicates low false-negative rate.

question

Sensitivity, Equation

answer

True-positive rate = TP / (TP + FN) = 1 - FN If Sensitivity = 100% = TP / (TP + FN) = 1, FN = 0 and all negatives must be TNs

question

Specificity

answer

True-negative rate Proportion of all people without disease who test neg. Probability that test indicates no disease when disease is absent.

question

High Specificity Test, Use

answer

Used for confimation after positive screening test

question

Specificity approaching 100%

answer

Desirable for ruling in disease. Indicates low false-positive rate.

question

Specificity, Equation

answer

True-negative rate = TN / (TN + FP) = 1 - FP If Specificity = 100% = TN / (TN + FP) = 1, FP = 0 and all positives must be TPs

question

Positive predictive value (PPV)

answer

Proportion of positive test results that are true positive. Probability that a person actually has a disease given a positive test result.

question

Positive predictive value (PPV), Equation

answer

PPV = TP / (TP + FP)

question

Positive predictive value (PPV) : Prevalence or pretest probability

answer

PPV varies directly with prevalence or pretest probability: High pretest probability -> high PPV

question

Negative predictive value (NPV)

answer

Proportion of negative test results that are true negative. Probability that person actually is disease free given a negative test result.

question

Negative predictive value (NPV), Equation

answer

NPV = TN / (TN + FN)

question

Negative predictive value (NPV) : Prevalence or pretest probability

answer

NPV varies inversely with prevalence or pretest probability: High pretest probability -> low NPV

question

Incidence Rate

answer

= # of new cases / # of cases at risk

question

Prevalence Rate

answer

= # of existing cases / # of cases at risk

question

Incidence Rate, Temporality

answer

During a time period

question

Prevalence Rate, Temporality

answer

At a point of time

question

When is Prevalence ≈ Incidence

answer

When Incidence for short duration disease (e.g. common cold)

question

Prevalence ≈

answer

Pretest probability

question

Odds ratio (OR)

answer

Odds that the group with disease (cases) was exposed to a risk factor (a/c) divided by the odds that the group without the disease (controls) was exposed (b/d).

question

Odds ratio (OR), Equation

answer

OR = (a/c)/(b/d) = ad/bc

question

Relative risk (RR)

answer

Risk of developing a disease in the exposed group divided by risk of developing a disease in the unexposed group. If prevalence is low, OR ≈ RR.

question

Relative risk (RR), Equation

answer

RR= a (a + b) / c (c + d) [exposed% / unexposed%]

question

Relative risk (RR), Example

answer

If 21% of smokers develop lung cancer vs. 1% of nonsmokers, RR = 21 / 1 = 21

question

Attributable risk (AR)

answer

Difference in risk between exposed and unexposed groups. The proportion of disease occurrences that are attributable to the exposure.

question

Attributable risk (AR), Equation

answer

AR = a / (a + b) - c / (c + d) [exposed% - unexposed%]

question

Attributable risk (AR), Example

answer

If risk of lung cancer in smokers is 21% and risk in nonsmokers is 1%, then 20% of the lung cancer risk in smokers is attributable to smoking.

question

Relative risk reduction (RRR)

answer

The proportion of risk reduction attributable to the intervention as compared to a control

question

Relative risk reduction (RRR), Equation

answer

RRR = 1 - RR

question

Relative risk reduction (RRR), Example

answer

If 2% of patients who receive a flu shot develop the flu, while 8% of unvaccinated patients develop the flu, then RR = 2/8 = 0.25, and RRR = 0.75

question

Absolute risk reduction (ARR)

answer

The difference in risk (not the proportion) attributable to the intervention as compared to a control.

question

Absolute risk reduction (ARR), Equation

answer

If 8% of people who receive a placebo vaccine develop the flu vs. 2% of people who receive a flu vaccine, then ARR = 8% − 2% = 6% = .06

question

Absolute risk reduction (ARR), Example

answer

ARR = (c /c + d) - (a / a + b)

question

Number needed to treat (NNT)

answer

Number of patients who need to be treated for 1 patient to benefit.

question

Number needed to treat (NNT), Equation

answer

NNT = 1 / ARR

question

Number needed to harm (NNH)

answer

Number of patients who need to be exposed to a risk factor for 1 patient to be harmed.

question

Number needed to harm (NNH), Equation

answer

NNH = 1 / AR

question

Precision

answer

The consistency and reproducibility of a test (reliability). The absence of random variation in a test.

question

Accuracy

answer

The trueness of test measurements (validity). The absence of systematic error or bias in a test.

question

Precision, Error

answer

Random error decr. precision in a test. Incr. precision -> decr. standard deviation. Incr. precision -> incr. statistical power (1 − β)

question

Accuracy, Error

answer

Systematic error decr. accuracy in a test.

question

Bias and study errors, Recruiting

answer

Selection bias

question

Bias and study errors, Performing

answer

Recall bias Measurement bias Procedure bias Observer-expectancy bias

question

Bias and study errors, Interpreting

answer

Confounding bias Lead-time bias

question

Selection bias

answer

Error in assigning subjects to a subject group resulting in an unrepresentative sample. Most commonly a sampling bias.

question

Selection bias, Examples

answer

Berkson bias Healthy worker effect Non-response bias

question

Selection bias, Strategy to reduce bias

answer

Randomization Ensure the choice of the right comparison/reference group.

question

Berkson bias

answer

Study population selected from hospital -> less healthy than general population

question

Healthy worker effect

answer

Study population is healthier than the general population.

question

Non-response bias

answer

Participating subjects differ from nonrespondents in meaningful ways.

question

Recall bias, Definition

answer

Awareness of disorder alters recall by subjects

question

Recall bias, Example

answer

Patients with disease recall exposure after learning of similar cases.

question

Recall bias, Strategy to reduce bias

answer

Decrease time from exposure to follow-up.

question

Measurement bias, Definition

answer

Information is gathered in a way that distorts it.

question

Measurement bias, Example

answer

Miscalibrated scale consistently overstates weights of subjects.

question

Measurement bias, Strategy to reduce bias

answer

Use standardized method of data collection.

question

Procedure bias, Definition

answer

Subjects in different groups are not treated the same.

question

Procedure bias, Example

answer

Patients in treatment group spend more time in highly specialized hospital units.

question

Procedure bias, Strategy to reduce bias

answer

Blinding Use of placebo -> reduce influence of participants and researchers on procedures and interpretation of outcomes as neither are aware of group allocation

question

Observer-expectancy bias, Definition

answer

Researcher's belief in the efficacy of a treatment changes the outcome of that treatment

question

Observer-expectancy bias, Example

answer

If observer expects treatment group to show signs of recovery, then he is more likely to document positive outcomes

question

Observer-expectancy bias, Strategy to reduce bias

answer

Blinding Use of placebo -> reduce influence of participants and researchers on procedures and interpretation of outcomes as neither are aware of group allocation

question

Recall bias Common in:

answer

Common in retrospective studies.

question

Observer-expectancy bias, aka

answer

Pygmalion effect: self-fulfilling prophecy

question

Confounding bias, Definition

answer

When a factor is related to both the exposure and outcome, but not on the causal pathway -> factor distorts or confuses effect of exposure on outcome.

question

Confounding bias, Example

answer

Pulmonary disease is more common in coal workers than the general population; however, people who work in coal mines also smoke more frequently than the general population

question

Confounding bias, Strategy to reduce bias

answer

Multiple/repeated studies Crossover studies (subjects act as their own controls) Matching (patients with similar characteristics in both treatment and control groups)

question

Lead-time bias, Definition

answer

Early detection is confused with incr. survival.

question

Lead-time bias, Example

answer

Early detection makes it seem as though survival has increased, but the natural history of the disease has not changed.

question

Lead-time bias, Strategy to reduce bias

answer

Measure "back-end" survival (adjust survival according to the severity of disease at the time of diagnosis)

question

Measures of central tendency

answer

Mean Median Mode

question

Mean

answer

Sum of values / total number of values. Most affected by outliers (extreme values).

question

Median

answer

Middle value of a list of data sorted from least to greatest. If there is an even number of values, the median will be the average of the middle two values.

question

Mode

answer

Most common value. Least affected by outliers.

question

Standard deviation (SD)

answer

How much variability exists from the mean in a set of values.

question

Standard error of mean (SEM)

answer

An estimate of how much variability exists between the sample mean and the true population mean.

question

Standard error of mean (SEM), Equation

answer

SEM = σ/√n σ = SD; n = sample size SEM decr. as n incr.

question

Normal distribution

answer

Gaussian, also called bell-shaped. Mean = median = mode.

question

Bimodal

answer

Suggests two different populations

question

Positive skew

answer

Typically, mean > median > mode. Asymmetry with longer tail on right.

question

Negative skew

answer

Typically, mean < median < mode. Asymmetry with longer tail on left.

question

Bimodal, Examples

answer

Metabolic polymorphism such as fast vs. slow acetylators Age at onset of Hodgkin lymphoma Suicide rate by age

question

Statistical Hypothesis, Null (H0)

answer

Hypothesis of no difference or relationship.

question

Statistical Hypothesis, Null (H0), Example

answer

There is no association between the disease and the risk factor in the population.

question

Statistical Hypothesis, Alternative (H1)

answer

Hypothesis of some difference or relationship.

question

Statistical Hypothesis, Alternative (H1), Example

answer

There is some association between the disease and the risk factor in the population.

question

Outcomes of statistical hypothesis testing, Correct result

answer

1. Stating that there is an effect or difference when one exists (null hypothesis rejected in favor of alternative hypothesis). 2. Stating that there is not an effect or difference when none exists (null hypothesis not rejected).

question

Type I error (α)

answer

Also known as false-positive error. Stating that there is an effect or difference when none exists (null hypothesis incorrectly rejected in favor of alternative hypothesis).

question

Type I error (α), α

answer

α is the probability of making a type I error.

question

Type I error (α), p

answer

p is judged against a preset α level of significance (usually < .05).

question

Type I error (α), p < 0.05

answer

There is less than a 5% chance that the data will show something that is not really there.

question

Type II error (β)

answer

Also known as false-negative error. Stating that there is not an effect or difference when one exists (null hypothesis is not rejected when it is in fact false).

question

Type II error (β), β

answer

β is the probability of making a type II error. β is related to statistical power (1 - β), which is the probability of rejecting the null hypothesis when it is false.

question

Type II error (β), incr. power and decr. β by:

answer

incr. sample size incr. expected effect size incr. precision of measurement

question

Confidence interval

answer

Range of values in which a specified probability of the means of repeated samples would be expected to fall.

question

Confidence interval, Equation

answer

CI = mean ± Z(SEM).

question

For the 95% CI

answer

Z = 1.96

question

For the 99% CI

answer

Z = 2.58

question

If the 95% CI for a mean difference between 2 variables includes 0...

answer

then there is no significant difference and H0 is not rejected.

question

If the 95% CI for odds ratio or relative risk includes 1...

answer

H0 is not rejected.

question

If the CIs between 2 groups do not overlap...

answer

-> statistically significant difference exists.

question

If the CIs between 2 groups overlap...

answer

-> usually no significant difference exists.

question

t-test

answer

Checks differences between MEANS of 2 groups.

question

t-test, Example

answer

Comparing the mean blood pressure between men and women.

question

ANOVA

answer

Checks differences between MEANS of 3 or more groups.

question

ANOVA, Example

answer

Comparing the mean blood pressure between members of 3 different ethnic groups.

question

Chi-square (χ2)

answer

Checks differences between 2 or more PERCENTAGES or PROPORTIONS of categorical outcomes (not mean values).

question

Chi-square (χ2), Example

answer

Comparing the percentage of members of 3 different ethnic groups who have essential hypertension.

question

Pearson correlation coefficient (r)

answer

r is always between −1 and +1. The closer the absolute value of r is to 1, the stronger the linear correlation between the 2 variables.

question

Pearson correlation coefficient (r), Positive r value

answer

Positive correlation -> as one variable INCR., the other variable INCR.)

question

Pearson correlation coefficient (r), Negative r value

answer

Negative correlation -> as one variable INCR., the other variable DECR.)

question

Pearson correlation coefficient (r), Coefficient of determination

answer

r2 (value that is usually reported).

question

Disease prevention, Primary

answer

Prevent disease occurrence (e.g., HPV vaccination)

question

Disease prevention, Secondary

answer

Screening early for disease (e.g., Pap smear)

question

Disease prevention, Tertiary

answer

Treatment to reduce disability from disease (e.g., chemotherapy)

question

Medicare

answer

Available to patients: - ≥ 65 years old - < 65 with certain disabilities - patients with end-stage renal disease

question

Medicare and Medicaid

answer

Federal programs that originated from amendments to the Social Security Act.

question

The 4 parts of Medicare:

answer

- Part A: Hospital insurance - Part B: Basic medical bills (e.g., doctor's fees, diagnostic testing) - Part C: (Parts A+B) delivered by approved private companies - Part D: Prescription drugs

question

Medicaid

answer

Medicaid is joint federal and state health assistance for people with very low income.

USMLE Step 1 First Aid 2015 Behavioral Science Epidemiology/Biostatistics – Flashcards

Unlock all answers in this set

Haven't found what you were looking for?

Search for samples, answers to your questions and flashcards