Evidence Based

Question 1

Ratio

Answer 1

Numerator does not need to be a subset of the denominator
ex. ratio of men to women

Question 2

Proportion

Answer 2

diving one number by another, where the numerator is a subset of the denominator
ex. the proportion of men in a population calculated as the number of men divided by the total population

Question 3

Rate

Answer 3

similar to ratios and proportions, rates are calculated by dividing one number by another, and additionally have a time component of the denominator
ex. the number of people who developed influenza in 2017, the birth rate per year in a population, the mortality rate per year in a population

Question 4

Observation bias

Answer 4

the bias arises from systematic differences in the way information on exposure or disease is obtained from the study groups
occurred only after the participants have entered the study

Question 5

Methods of controlling for confounding

Answer 5

randomization, restriction, matching, standardization, stratification, and conducting a multivariable analysis

Question 6

Reliability

Answer 6

aka repeatability
- repeated measures are close to one another but still misses the bull eye

Question 7

Validity

Answer 7

a screening test is the ability of a test to accurately identify diseases and non-diseases individuals

Question 8

Lead time bias

Answer 8

overestimation of survival duration attributable to earlier detection by screening than by clinical presentation

Question 9

Length bias

Answer 9

screening is more likely to detect cases that are progressing slowly compared with those with rapid progression of disease, who manifest clinically
- slow progressing cases are usually milder and more likely to survive, leading to an overestimation of survival as a result of screening

Question 10

Descriptive statistics

Answer 10

performed on a small subset of a population, known as a sample
- builds on descriptive statistics and allows researchers to draw conclusions on the population based on information collected from the sample

Question 11

nominal variables

Answer 11

data are collected on the category in which the participants falls. The categories have no inherent order (ie. race)

Question 12

Dichotomous variables

Answer 12

variables have only two possible values (i.e. exposure status: exposed or unexposed)

Question 13

ordinal variables

Answer 13

categories have an inherent order (i.e. level of education)

Question 14

Interval variable

Answer 14

• type of continuous variable
• have a distinct order
• lacks a true zero
  (i.e. pH)

Question 15

Ratio variable

Answer 15

• type of continuous variable
• true zero
• values of the variable act as true ratios of one another
  (i.e. temperatures in kelvin)

Question 16

Z scores table

Answer 16

Probabilities for the likelihood that a certain value or a more extreme value would be observed are tabulated through this table
- often uses inferential statistics analyses

Question 17

Poisson distribution

Answer 17

count data is the number of occurrences in a group
- distribution is right-skewed because higher counts are less likely to be observed

Question 18

Confidence interval

Answer 18

show the strength of association between the exposure and the outcome

Question 19

Pearson correlation of coefficient (r)

Answer 19

-1 to +1
reveals both the fit of the data to the regression line and the direction of association between the variables
- negative r = the values of independent variable increase, while dependent variable decrease
- positive r = independent variable increase, while the values of the dependent variable also increase
- 0 reveals the strength of the relationship
- +0.9 or -0.9 = strong positive and negative linear relationship
- +0.1 or -0.1 reveals a weak positive and negative linear relationship

Question 20

Coefficient of determination (r^2)

Answer 20

for simple linear regressions, this is the squared value of the pearson product moment correlations coefficient
- standardizes the value to be used as a metric of the fit of the linear regression model for both positively and negatively associated variables
- 0 to 1

Question 21

Case fatality ratio

Answer 21

of deaths / # of cases

Question 22

Distribution

Answer 22

describes who gets the disease, where people with the disease are located, and how these aspects of the disease change overtime

Question 23

When should sensitivity be increased

Answer 23

when the penalty associated with missing a case is high
- when the subsequent diagnostic evaluations are associated with minimal cost and risk

Question 24

When should specificity be increased

Answer 24

when the costs associated with further diagnostic techniques are substantial

Question 25

preclinical phase

Answer 25

period between the initial biological onset of a disease and the emergence of any noticeable symptoms or clinical signs.

Question 26

clinical phase

Answer 26

period during which a disease manifests noticeable symptoms and signs that are detectable through standard diagnostic methods or observable changes in a person’s health