Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Behavioral Science > Epidemiology/Biostatistics > Flashcards

Epidemiology/Biostatistics Flashcards

You may prefer our related Brainscape-certified flashcards:
Biology 101 flashcards
1
Q

Case-control study

A

Compares a group of people with disease to a group without disease. Looks for prior exposure to risk factor
Asks, “What happened?”
Measures: OR
Example: patients with COPD had higher OR of a history of smoking than those without COPD

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Cohort Study

A

Compares a group with a give exposure or risk factor to a group without such exposure. Looks to see if exposure affects the likelihood of a disease.
Prospective: Who will develop disease?
Historical: Who developed disease?
Measures: Relative Risk
Example: smokers had a higher risk of developing COPD than non-smokers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Twin concordance study

A

Compares the frequency with which both monozygotic or both dizygotic twins develop the same disease.
Measures: heritability and influence of environmental factors

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Adoption Study

A

Compares siblings raised by biological vs. adoptive parents

Measures: heritability and influence of environmental factors

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Clinical Trial

A

Experimental study involving humans. Compares therapeutic benefits of 2 or more treatments, or of treatment and placebo. Study quality improves when the study is randomized, controlled and double-blinded (triple blinded - researchers blinded as well)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Drug Trial: Phase I

A

Small number of healthy volunteers

Purpose: is it safe? Assess safety, toxicity, PK & PD

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Drug Trial: Phase II

A

Small number of pts with disease of interest

Purpose: does it work? Assesses treatment efficacy, optimal dosing, adverse effects

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Drug Trial: Phase III

A

Large number of pts, randomly assigned either to the treatment under investigation or to the best available treatment currently (or placebo)
Purpose: is it as good or better? Compares the new treatment to the current standard of care

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Drug Trial: Phase IV

A

Post marketing surveillance of pts after treatment has been approved
Purpose: Can it stay? Detects rare or long-term adverse effects. An result in treatment being withdrawn from the market

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Evaluation of diagnostic tests

A

2x2 table comparing test results with the actual presence of disease.
TP, FP, TN, FN
Sensitivity and specificity are fixed properties of a test
PPV and NPV vary depending on disease prevalence

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Sensitivity (TP rate)

A

Proportion of all people with disease who test positive, or the probability that when the disease is present, the test is positive
Value approaching 100% is desirable for RULING OUT disease and indicates a low FN rate. High sensitivity is used for screening in diseases with low prevalence.
Sensitivity = TP/ (TP+FN)
SNOUT - highly sensitivity test, when negative, rules out disease

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Specificity (TN rate)

A

Proportion of all people without disease who test negative, or probability that when the disease is absent the test is negative.
Value approaching 100% is desirable for ruling in disease and indicates a low FP rate. High specificity used for confirmation after a positive screening test.
Specificity = TN/ (TN + FP)
SPIN - highly specific test, when positive, rules in disease

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Positive Predictive Value

A

Proportion of positive test results that are true positive.
Probability that a person who has a positive test result actually has the disease
PPV = TP/(TP+FP)
PPV varies directly with pretest probability (High PP = High PPV)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Negative Predictive Value

A

Proportion of negative test results that are true negative.
Probability that a person with a negative test result actually does not have the disease
NPV=TN/(TN+FN)
NPV varies inversely with prevalence or pretest probability

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Incidence Rate

A

IR = # of new cases/# of people at risk
During a specified time period
Incidence looks at new cases (incidents)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Prevalence

A

Prevalence = # of existing cases/total # of people in a population
At a point in time
Prevalence looks at all current cases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Prevalence vs. Incidence

A

Prevalence = Incidence for a short duration disease (e.g. Cold)
Prevalence > incidence for chronic diseases, due to large # of existing cases (e.g. Diabetes)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Odds Ratio (OR)

A

Typically used in case control study
Odds that the group with disease was exposed to a risk factor divided by the odds that the group without the disease was exposed
OR = AD/BC

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Relative Risk

A

Typically used in cohort studies
Risk of developing disease in the exposed group divided by risk in the unexposed group.
E.g. If 21% of smokers develop lung cancer vs. 1% of non-smokers RR=21/1=21
RR= a/(a+b) / c/(c+d)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Attributable Risk

A

The difference in risk between exposed and unexposed groups, or the proportion of disease occurrences that are attributable to the exposure
E.g. If risk of lung cancer in smokers is 21% and risk in non-smokers is 1%, then 20% of lung cancer risk in smokers is attributable to smoking
AR = a/a+b - c/c+d

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Relative Risk Reduction

A

The proportion of risk reduction attributable to the intervention as compared to the control
E.g. 2% of pts who receive a flu shot develop the flu, while 8% of the unvaccinated pts develop the flu, RR=2/8=.25 and RRR=.75
RRR=1-RR

22
Q

Absolute Risk Reduction

A

The difference in risk attributable to the intervention as compared to a control
E.g. If 8% of people who receive a placebo vaccine develop the flu vs. 2% of people who receive a flu vaccine, the ARR=8-2=6%
ARR=c/c+d - a/a+b

23
Q

Number Needed to Treat (NNT)

A

Number of pts who need to be treated for 1 pt to benefit

NNT = 1/ARR

24
Q

Number Needed to Harm (NNH)

A

Number of pts who need to be exposed to a risk factor for 1 pt to be harmed
NNH=1/AR

25
Q

Precision

A

The consistency and reproducibility of a test (reliability)
Random error low precision in a test
Increase precision –> decreased standard deviation
Increase precision –> increase statistical power (1-Beta)

26
Q

Accuracy

A

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

27
Q

Selection Bias

A

Error in assigning subjects to a study group resulting in an unrepresentative sample. Most commonly sampling bias.
Reduce bias: randomization, ensure choice of the right comparison/reference group

28
Q

Selection Bias: Berkson bias

A

Study population selected from hospital is less healthy than general population

29
Q

Selection Bias: Healthy worker effect

A

Study population is healthier than the general population

30
Q

Selection Bias: Non-response bias

A

Participating subjects differ from no respondents in meaningful ways

31
Q

Recall Bias

A

Awareness of disorder alters recall by subjects, common in retrospective studies.
E.g. Pts with disease recall exposure after learning of similar cases
Reduce: decrease time from exposure to follow-up

32
Q

Measurement Bias

A

Information is gathered in a systemically distorted manner
E.g. Association between HPV and cervical cancer not observed when using non-standardized classifications
Reduce: use objective standardized and previously tested methods of data collection that are planned ahead of time

33
Q

Procedure Bias

A

Subjects in different groups are not treated the same
E.g. Pts. In treatment group spend more time in highly specialized hospital units
Reduce: blinding and use of placebo to reduce influence of participants and researchers on procedures and interpretation of outcomes as neither are aware of group allocation

34
Q

Observer expectancy bias

A

Researcher’s belief in the efficacy of a treatment changes the outcome of that treatment (self-fulfilling prophecy).
E.g. If observer expects treatment group to show signs of recover then he is more likely to document positive outcomes.
Reduce: blinding and use of placebo to reduce influence of participants and researchers on procedures and interpretation of outcomes as neither are aware of group allocation

35
Q

Measures of central tendency

A 
Mean = sum of values/total number of values (average) - most effected by outliers
Median = middle value of 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
Mode = most common value - least effected by outliers
36
Q

Measures of dispersion

A

Standard deviation - how much variability exit is from the mean in a set of values
Standard Error of the Mean - an estimate of how much variability exist between the sample mean and the true population mean
SEM = SD/square root of n

37
Q

Normal Distribution

A 
Gaussian, bell shaped curve
Mean=median=mode
1 SD = 68%
2 SD = 95%
3SD = 99.7%
38
Q

Bimodal distribution

A

Suggests two different populations

E.g. Metabolic polymorphism such as fast vs. slow acetylators

39
Q

Positive skew distribution

A

Typically - mean>median>mode

Asymmetry with longer tail on the right

40
Q

Negative Skew distribution

A

Typically, mean

41
Q

Null hypothesis

A

Hypothesis of no difference or relationship

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

42
Q

Alternative hypothesis

A

Hypothesis of some difference or relationship

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

43
Q

Type I Error (alpha)

A

Stating that there is an effect or difference when none exists (null hypothesis incorrectly rejected in favor of alternative hypothesis)
Alpha - probability of making a type I error (you “Abserved” a relationship that was not there)
p - judged against a preset alpha level of significance (0.05), if p

44
Q

Type II error (beta)

A

Stating that there is not an effect or difference when one exists (null hypothesis is not rejected when it is in fact false)
Beta - probability of making a type II error. Beta related to statistical power (1-beta) which is the probability of rejecting the null hypothesis when it is false (Blinded by the truth)
Increase power and decrease beta: increased sample size, expected effect size, precision of measurement

45
Q

Confidence interval

A

Range of values within which the true mean of the population is excepted to fall with a specified probability
CI = me a +/- Z(SEM)
The 95% CI is often used (p

46
Q

T-test

A

Check differences between means of 2 groups.

Tea is MEANt for 2

47
Q

ANOVA

A

Checks differences between means of 3 or more groups

An Analysis of Variance

48
Q

Chi-square

A

Checks differences between 2 or more percentages or proportions of categorical outcomes (not mean values)

49
Q

Pearson correlation coefficient

A

The r is always between -1 and +1. The closer the absolute value of r is to 1, the stronger the linear correlation between the two variables.
Positive r = positive correlation (as one variable increases so does the other)
Negative r = negative correlation (as one variable increases the other decreases)
Coefficient of determination = r2

50
Q

Cross-sectional study

A

Collects data from a group of people to assess the frequency of disease (and related risk factors) at a particular point in time.
Asks “What is happening?”
Measures: disease prevalence
Example: can show risk factor association with disease but does not establish causality

Behavioral Science (4 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions