Chapter 14: Biostatistics Flashcards
This kind of data has a logical order with values that continuously increase or decrease by the same amount (e.g., a HR of 120 BPM is twice as fast as a HR of 60 BPM)?
Continuous data
What is the difference between interval and ratio data?
Interval data has no meaningful zero (zero does not equal none) and ratio data has a meaningful zero (zero equals none)
What are the two types of discrete/categorical data?
Nominal and ordinal data
Which type of categorical data sorts subjects into arbitrary categories (names), such as male and female (0=male, 1=female or 0=female, 1=male)
Nominal data
Which type of categorical data is ranked and has a logical order, such as a pain scale?
Ordinal data
The mean is preferred for ____ data that is ____ distributed
Continuous; normally
The median is preferred for ____ data or ____ data that is skewed
Ordinal; continuous
The mode is preferred for ____ data
Nominal
Indicates how spread out the data is and to what degree the data is dispersed away from the mean
Standard deviation
Data that is highly dispersed has a ___ standard deviation
larger
Large sample sets of continuous data tend to form a ____ distribution
Gaussian or normal “bell-shaped”
When the distribution of data is normal, the curve is ____
Symmetrical (half of the values are on the left side and half of the values are on the right side)
When the distribution of data is normal, the mean, median and mode are ____ (the same or different)
The same
When the distribution of data is normal, __% of values fall within 1 SD of the mean and __% of the values fall within 2 SD of the mean
68%; 95%
Skewed distributions where 68% of the values do not fall within 1 SD of the mean and the mean, median and mode are not the same value usually occurs when the sample size is ___ and/or there are ____ in the data
Small; outliers
When there are a small number of values, an outlier has a ____ (small or large) impact on the mean and the data becomes skewed
Large
The distortion of the central tendency caused by outliers is ____ (increased or decreased) by collecting more values
Decreased
When there are more low values in a data set and the outliers are the high values, data is skewed to the ____ (left or right)
Right (positive skew)
When there are more high values in a data set and the outliers are the low values, data is skewed to the ____ (left or right)
Left (negative skew)
_____ states that there is no statistically significant difference between groups & is what the researcher hopes to disprove or reject
The null hypothesis
______ is what the researcher tries to prove or accept
The alternate hypothesis
When investigators design a study, they select a maximum permissible error margin, called ____, which is the threshold for rejecting the null hypothesis
Alpha
In medical research, alpha is usually set at ___
5% or 0.05
If the alpha is set at 0.05 and the p-value is less than alpha (p <0.05), is the null hypothesis rejected or accepted? Is the result termed statistically significant or insignificant
Rejected; statistically significant
A confidence interval provides the same information about significance as the p-value, plus the _____ of the result
precision
If alpha is 0.05, what would the confidence interval be?
If alpha is 0.01, what would the confidence interval be?
95%; 99%
When comparing means (difference data), when is a result statistically significant in regards to the confidence interval?
When the CI does not include zero
Example:
- The 95% CI for the difference in FEV1 between two drugs is 18-58 –> does not include zero, therefore the result is statistically significant
- The 95% CI for the difference in FEV1/FVC is -0.26-0.89 –> includes zero, therefore the result is not statistically significant
When comparing ratio data (relative risk, odds ratio, hazard ratio), the result is statistically significant if the CI range does not include ___
One
A narrow confidence interval range implies ____ (high or low) precision.
A wide confidence interval range implies ____ (high or low) precision.
High; low
Is a type I error a false-positive or false-negative?
False-positive
When alpha is 0.05 and a study result is reported with p <0.05, it is statistically significant and the probability of a type I error is ____
<5%
Is a type II error a false-positive or false-negative?
False-negative
Power is the probability that a test will ____ (accept or reject) the null hypothesis correctly
Reject
When is power used?
To avoid type II error
How can study power be increased?
Have a larger sample size
If beta is set at 0.2, what is the power?
80% - there is a 20% chance of missing a true difference and making a type II error
What is the relative risk formula?
RR = risk in treatment group/ risk in control group
What is the risk formula?
Risk = number of subjects in group with an unfavorable event/ total number of subjects in group
RR = 1 (or 100%) implies ___ (greater, lower, no difference) risk of the outcome between the groups
no difference
RR > 1 (or 100%) implies ___ (greater, lower, no difference) risk of the outcome in the treatment group
greater
RR < 1 (or 100%) implies ___ (greater, lower, no difference) risk of the outcome in the treatment group
lower
What does relative risk reduction indicate?
How much the risk is reduced in the treatment group compared to the control group
What is the relative risk reduction formula?
RRR = (% risk in control group - % risk in treatment group) / % risk in control group
-OR-
1-RR
What is absolute risk reduction?
Includes the reduction in risk and the incidence rate of the outcome
What is the formula for ARR?
ARR = (% risk in control group) - (% risk in treatment group)
What is number needed to treat?
The number of patients who need to be treated for a certain period of time in order for one patient to benefit
What is the NNT formula?
NNT = 1/ (risk in control group) - (risk in treatment group) OR 1/ARR
What is number needed to harm?
Number of patients who need to be treated for a certain period of time in order for one patient to experience harm
What is the formula for NNH?
NNH = 1/ARR (same formula as NNT)
What is the difference between the NNH and NNT formula?
NNT is rounded up and NNH is rounded down
Example: NNT of 52.1 is rounded to 53, NNH of 41.9 is rounded to 41
In order to estimate the risks associated with a treatment of some type of intervention in a CASE-CONTROL study, one should calculate ____
Odds ratio (or odds of unfavorable events)
What kind of patients are enrolled in a case-control study?
Patients who have a clinical outcome or disease that has already occurred (e.g. lung cancer)
In a case-control study, are medical charts reviewed prospectively or retrospectively?
Retrospectively
What does odds-ratio tell us?
The odds of an outcome occurring with an exposure compared to the odds of the outcome occurring without the exposure
What is the formula for odds ratio
OR = (# with outcome with exposure) x (# without outcome without exposure) / (# without outcome with exposure) x (# with outcome without exposure)
What is a hazard rate?
Rate at which an unfavorable event occurs within a short period of time
What is the hazard rate formula?
HR = hazard rate in treatment group/ hazard rate in control group
How do you interpret an OR or HR = 1
The event rate is the same in the treatment and control arms. There is no advantage to the treatment
How do you interpret an OR or HR > 1
The event rate in the treatment group is HIGHER than the event rate in the control group. For example, a HR of 2 for an outcome of death indicates that there are twice as many deaths in the treatment group
How do you interpret an OR or HR < 1
The event rate in the treatment group is LOWER than the event rate in the control group. For example, a HR of 0.5 for an outcome of death indicates that there are half as many deaths in the treatment group
What is a composite endpoint?
Combines multiple individual endpoints into one measurement
T or F: All endpoints in a composite endpoint must be similar in magnitude and have similar, meaningful importance to the patient
True
If continuous data is normally distributed, what test is appropriate to use to analyze the data?
Parametric methods
If continuous data is NOT normally distributed, what test is appropriate to use to analyze the data?
Non-parametric methods
Is a T-test a parametric or non-parametric method?
Parametric
What is a one-sample t-test?
When data from a single sample group is compared with known data from the general population
What is a paired t-test?
When a single-sample group is used for a pre- or post-measurement (i.e. the patient serves as their own control)
When is a student t-test used?
When the study has TWO independent samples: the treatment and the control groups
____ is used to test for statistical significance when using continuous data with 3 or more samples or groups
Analysis of variance (ANOVA) or F-test
What type of test would you use for nominal or ordinal data (categorical data)?
Chi-square
A statistical technique that is used to determine if one variable (such as number of days in hospital) changes or is related to another variable (such as incidence of hospital-acquired infection)
Correlation
Describes the relationship between a dependent variable and one or more independent variables, or how much the value of the dependent variable changes when the independent variables changes.
Regression
Which types of studies is regression common in?
Observational studies where researchers need to assess multiple independent variables or need to control for many confounding factors
____ describes how effectively a test identifies patients WITH the condition
Sensitivity
____ describes how effectively a test identifies patients WITHOUT the condition
Specificity
A test with 100% sensitivity will be _____ (+ or -) in all patients with the condition
Positive
A test with 100% specificity will be _____ (+ or -) in all patients without the condition
Negative
A(n) _____ analysis includes data for all patients originally allocated to each treatment group (active and control) even if the patient did not complete the trial according to the study protocol
Intention-to-treat
A(n) ____ analysis is conducted for the subset of the trial population who completed the study according to the protocol
Per protocol
___ trials attempt to demonstrate that the new treatment has roughly the same effect as the old treatment
Equivalence
___ trials attempt to demonstrate that the new treatment is no worse than the current standard based on the delta margin
Non-inferiority
What type(s) of studies use forest plots?
Meta-analysis
When interpreting statistical significance using a forest plot, what do the boxes represent?
Effect estimate. The size of the box correlates with the size of the effect from the single study shown
When interpreting statistical significance using a forest plot, what do the diamonds represent?
Pooled results from multiple studies
When interpreting statistical significance using a forest plot, what do the horizontal lines through the boxes represent?
The length of the CI for that particular endpoint (in a single study) or for the particular study (in a meta-analysis). The longer the line, the wider the interval, and the less reliable the study results. The width of the diamond in a meta-analysis serves the same purpose
When interpreting statistical significance using a forest plot, what does the vertical solid line represent?
The line of no effect
In a forest plot, what does it mean when data falls to the left of the solid line
A significant benefit has been reached
In a forest plot, what does it mean when data falls to the right of the solid line
Significant harm
The vertical line in a forest plot is set at __ for difference data and at __ for ratio data
0 ; 1
This type of study compares cases (patients with a disease) to controls (patients without a disease)
Case-control
This type of study compares patients with an exposure to those without an exposure
Cohort
This type of study compares patients who were randomly assigned to groups
Randomized controlled trials
This type of study analyzes the results of multiple studies
Meta-analysis
Is a case-control study prospective or retrospective?
Retrospective
Is a cohort study prospective or retrospective?
Prospective
What is a limitation of a cohort study?
Can be influenced by confounders, which are other factors that affect the outcome (i.e. smoking, lipid levels)
This type of study describes an adverse reaction or a unique condition that appears in a single patient
Case report
This type of study describes an adverse reaction or a unique condition that appears in a few patients
Case series
______ is used when 2 or more interventions have demonstrated equivalence in outcomes and the costs of each intervention are being compared
Cost-minimization analysis (CMAs)
A systematic process used for calculating and comparing benefits and costs of an intervention in terms of monetary units (dollars)
Cost-benefit analysis (CBA)
Used to compare the clinical effects of 2 or more interventions to the respective costs
Cost-effective analysis (CEA)
A specialized form of CEA that includes a quality-of-life component of morbidity assessments, using common health indices such as quality-adjusted life years (QALYs) and disability-adjusted life years (DALYs)
Cost-utility analysis (CUA)
