Biostats definitions and equations

Question 1

Compares people with DISEASE to people without disease

Answer 1

Case-control study

Question 1

Patients serve as their own control

Answer 1

Crossover study (reduced confounding bias)

Question 2

CI between two groups overlaps

Answer 2

No difference, fail to reject H_O

Question 3

Hawthorne effect

Answer 3

Groups who know they’re being studied behave differently (measurement bias)

Question 4

PPV =

Answer 4

TP/TP+FP

Question 5

Measured by a cross-sectional study

Answer 5

Prevalence

Question 5

1 standard deviation = __%

Answer 5

68

Question 6

Attributable risk

Answer 6

Difference in risk between exposed and unexposed group

Question 6

Mean > median > mode

Answer 6

Positively skewed

(Tail to the right)

Question 7

Mean < median < mode

Answer 7

Negatively skewed

(Tail to the left)

Question 7

Incorrectly rejecting the null hypothesis

Answer 7

Type I error

(Saying there is a difference when there isn’t)

Question 8

Information is gathered in a way that distorts it

Answer 8

Measurement bias

Question 10

Collects data from a group of people to asses disease prevalence

Answer 10

Cross-sectional study

Question 11

Which bias? Patients in treatment group spend more time in in-patient treatment

Answer 11

Procedure bias

Question 11

Mean=median=mode

Answer 11

Normal distribution

Question 12

AR =

Answer 12

% risk in exposed group - % risk in unexposed group

Question 13

NNT =

Answer 13

1/risk difference

Question 14

Specificity =

Answer 14

TN/TN+FP

1 - false positive rate

Question 15

Increases with increasing prevalence

Answer 15

PPV

Question 16

3 standard deviations = ___%

Answer 16

99.7

Question 16

Coefficient of correlation =

Answer 16

r²

Question 18

Nonrandom assignment to participate in a study group

Answer 18

Selection bias

Question 18

95% CI includes 0

Answer 18

H_O not rejected

Question 19

RRR =

Answer 19

1 - RR

Question 20

Berkson bias

Answer 20

Study looking only at inpatients (a selection bias)

Question 21

Two means

Answer 21

T-test

Question 22

Ways to increase power and reduce ß

Answer 22

Increase sample size Increase expected effect size Increase precision of measurement

Question 23

Subjects in different groups are not treated the same

Answer 23

Procedure bias

Question 24

ß

Answer 24

Probability of making a type II error (Failing to reject the null hypothesis)

Question 25

Which bias? Study over effectiveness of CRC screening concludes that their screening method leads to increased survival

Answer 25

Lead-time bias

Question 26

Berkson bias Loss to follow-up Healthy worker and volunteer biases

Answer 26

Selection bias

Question 27

Power =

Answer 27

1 - ß (ß = type II error)

Question 28

Alpha

Answer 28

Probability of making a type I error (Falsely rejecting the null hypothesis)

Question 29

Failing to reject the null hypothesis

Answer 29

Type II error (Stating there isn't a difference when there is one)

Question 30

RR =

Answer 30

Incidence in exposed group/incidence in non-exposed a/(a+b) / c/(c+d)

Question 30

SEM =

Answer 30

σ/√n

Question 32

Which bias? Researcher expects those receiving drug to show more signs of improvement, so he documents those signs in the treatment group more frequently than the placebo group

Answer 32

Observer-expectancy bias

Question 33

Which bias? Coal miners more likely to have lung disease but also more likely to smoke

Answer 33

Confounding bias

Question 34

Z of 95% CI? 99% CI?

Answer 34

95% CI Z = 2 99% CI Z = 2.5

Question 35

Categorical differences

Answer 35

Chi-square ("Chi-tegorical")

Question 37

Early detection is confused with increased survival

Answer 37

Lead-time bias

Question 38

Relative risk reduction

Answer 38

Proportion of disease reduction attributable to intervention compared to control

Question 39

Decreases with increasing prevalence

Answer 39

NPV

Question 40

Hawthorne effect is an example of:

Answer 40

Measurement bias

Question 41

Bias reduced via randomization and ensuring the right comparison group

Answer 41

Selection bias

Question 42

3+ means

Answer 42

ANOVA (Remember: ANOVA = 3 words)

Question 43

Bias reduced via multiple studies, crossover studies, and matching

Answer 43

Confounding bias

Question 46

CI =

Answer 46

[mean - Z\*SEM] to [mean + Z\*SEM]

Question 47

CI between two groups doesn't overlap

Answer 47

Difference exists, reject H_O

Question 49

OR =

Answer 49

ad/bc

Question 51

Don't change if sample size increases

Answer 51

Specificity and sensitivity

Question 52

95% CI includes 1

Answer 52

Reject H₀

Question 53

Sensitivty =

Answer 53

TP/TP+FN 1 - false negative rate

Question 54

Measured by a cohort study

Answer 54

RR

Question 55

Bias reduced via "back-end" survival (measuring survival based on severity of disease at diagnosis)

Answer 55

Lead-time bias

Question 56

2 standard deviations = \_\_%

Answer 56

95

Question 57

Prevalence =

Answer 57

Incidence x disease duration (TP + FN)/(TP+TN+FP+FN) (a+c)/(a+b+c+d)

Question 58

NPV =

Answer 58

TN/TN+FN

Question 59

Bias reduced via placebo and blinding

Answer 59

Measurement bias (makes sure participants and researchers don't change their behavior)

Question 60

A factor is related to both exposure and outcome, but not on the causal pathway, so it distorts the effect of the exposure on the outcome

Answer 60

Confounding bias

Question 61

Compares people with an EXPOSURE to those without to see if exposure increases likelihood of a disease

Answer 61

Cohort study

Question 63

Increases with decreasing cut-off value of a test

Answer 63

Sensitivity NPV

Question 64

Measured by a case-control study

Answer 64

OR