Biostatistics Flashcards
What P value is considered statistically significant?
P < 0.05
Define accumulation effect
Exposture to risk factor/risk reducers may depend on duration and intensity of exposure
(Therefore there may be discrepancy between patients exposed for longer period of time than those exposed less)
In a positively skewed distribution, there is an increased number of observations with _____ (larger or smaller) than expected magnitudes that shift the mean toward the _____ and a longer slope (tail) of the curve to the _____
Larger
Right
Right (positive side of distribution)
A negatively skewed distribution has an increased number of observations with ____ (larger or smaller) than expected magnitudes that shifts the _____ toward the left, producing a longer slope of the curve (tail) on the negative side of distribution
Smaller
Mean
In general, in a positively skewed distribution the ___ is shifted the most in the positive direction, then the ____ and then the _____
(Mode, median, mean)
Mean
Median
Mode
In a positively skewed distribution, the mean is the most shifted in the positive direction. In such a situation, the ____ is often a better reflection of the central tendency than the mean.
Median
Case control study is an observational study in which potential participans are initially identified as cases or controls based on ____
Disease status
Are case control studies retrospective or prospective
Retrospective
Case control studies compare what between groups
Risk factor frequency
The anaylsis of variance (ANOVA) test compares the ____ of how many groups
Means
3 or more
The analysis of variance (ANOVA) test requires a ____ dependent variable
Quantitative
The analysis of variance (ANOVA) test requires a ______ independent variable
Categorical
What is an independent variable?
What is used to divide the study pool into groups
What is the dependent variable
The outcome
If a patient asks “what are the chances that I really do not have thyroid cancer?” After receiving results on a biopsy saying a nodule was benign, what diagnostic test parameter would be most helpful for answering their question
Negative predictive value
How is negative predictive value calculated
True negatives divided by total number of negative tests
Does negative predictive value vary with the prevalence of disease in the target population?
Yes
What is a type I error
Rejecting a true null hypothesis
Determining there is a correlation when one truly does not exist
What is a type II error
Fail to reject false null hypothesis
Determine there is no correlation when one truly exists
What is the power of a test?
The probability of making the correct decision of rejecting a false null hypothesis
What is the probability of a type II eror
The probability of failing to reject a false null hypothesis
How can the power of a test be calculated from the probability of a type II error
Power = 1 - (probability of a type II error)
What is the p-value
The probabililty of obtaining the observed result when the null hypothesis is assumed to be true
(Informally interpreted as the probability that the observed results are due to chance)
What is pretest probability
The probability of having the disease before testing
A t-test compares the ____ of how many groups
Mean
A t-test requires a ___ dependent variable and ___ independent variable
Quantitative
Categorical
How does a t-test differ from a paired t-test
T-test: 2 groups are independent
Paired: matched groups are formed (either same individuals being assessed twice or individuals are matched with indivduals in the other group based on certain attributes)
Does phase I testing in a clinical trial include healthy or ill patients
Healthy
Does phase II testing include healthy or affected subjects
Affected
What phase study asses the safety, pharmacokinetic profile, and metabolism of a drug in a smal number of healthy subjects
Phase I
What is the goal of phase III clinical trials
Assess safety and effectiveness of a new treatment compared to a standard treatment or a placebo
Expansive populations have ____ birth rates and ____ mortalilty rates
High
High
Expansive populations have ___ life expectancy and a _____ population
Short
Growing
Stationary popilations have a ___ in birth rates and ___ mortality rates
Decline
Low
Stationary populations have a ____ life expectancy and ____ population
Long
Stable
Constrictive populations have ____ birth rates and ___ mortality rates
Very low
Low
Constrictive populations have ___ life expectancy and a ___ population
Long
Shrinking
What type of population would be expected in a very advanced country with a high level of lilteracy, easy access to birth control mesures, and exceptional health and medical resources? (Constrictive, stationary, or expansive)
Constrictive
What population type is seen in many developed countries (stable, expansive, or constrictive)
Stable
what is the equation for positive predictive value
true positive / (true positive + false positive)
how can you calculate the true negatives with the sensitivity
true negatives = sensitivity x patients without disease
what is the attack rate?
number of people who contracted an illness divided by people who are at risk of contracting that illness
matching is a method often used in case control studies to control what bias?
confounding
according to, Hardy weinberg analysis, what variables represent disease frequency
q squared
according to Hardy weinberg analysis, how is carrier frequency represented for recessive disorders
2q
what is the purpose of randomization
to make experimental groups as similar as possible
what test is adequate for qualitative dependent variable and qualitative independent variable
chi-square
logistic regression
what test is adequate for qualitative dependent variable and quantitative independent variable
logistic regression
what test is adequate for a quantitative dependent variable and qualitative independent variable
t-test
ANOVA
linear regression
what test is adequate for a quantitative dependent variable and quantitative independent variable
correlation
linear regression
which would you likely calculate an odds ration: in a cohort study or case-control study
case-control
which would you likely calculate relative risk: in a cohort study or case control study?
cohort study
In a null hypothesis for a case control study, the odds ration will be equal to ___
1
what is the power of a study
power = 1 - (probability there is no difference in the two groups, or that the null hypothesis is correct)
what is health promotion
the process of enabling people to increase control over their health and its determinants, and thereby improve their health (it is a form of primary intervention)
how does a larger population affect negative and positive predictive values
increases positive predictive value
decreases negative predictive value
what is a statistical method commonly employed to compare the means of 2 groups of subjects
two-sample t test
what type of bias includes error due to loss to follow up
selection bias
what percentage of observations lie within 1, 2, and 3 standard deviations of the mean?
1: 68
2: 95
3: 99.7
what is effect modification
when the effect of the main exposure on the outcome is modified by the presence of another variable (not a bias, not the same as confounding)
what is alpha?
the significance level used to establish the statistical significance of s study result, a study is considered statistically significant when the p value is less than the significance level (alpha)
alpha is also the probability of making a type 1 error
what does “r” stand for in biostatistical analysis
correlation coefficient, the direction and strength of a linear relationship between 2 variables
what p value represents statistically significant data
less than the significance level
what is a descriptive observational study design in which a group of patients with a similar diagnosis or treatment is described at a point in time or followed over a certain perioed
case series
what phase trial assesses treatment efficacy, toxicity, adverse effects, and optimal dosing strategies in a small number of affected subjects
phase II
what is attributable risk percent
the excess risk in the exposed population that can be attributed to the risk factor
ARP = [(RR-1)/RR]
What is statistical power in a biostatistical study?
a study’s ability to detect a difference when on exists
1-beta
what statistical test evaluates association between 2 categorical variables
chi square test
how can absolute risk reduction be calculate
event rate in control - event rate in treatment group
how does a confidence interval determine if a relevant risk is significant or not
if a confidence interval contains the relative risk value, it is not statistically significant
ie. CI of .57-1.28 and RR =.87 indicates not statistically significant
define precision vs accuracy
precision: ability of test to reproduce identical or similar results with repeated measurements (ie. hitting the same spot on a dart board repeatidly)
accuracy: validity, ability of test to measure what it its actually supposed to measure (ie. getting a bulls eye)
How should non compliant test subject’s data be treated in a study that uses “intention-to-treat”
included regardless of their compliance
how is number needed to harm interpreted between 2 treatment options
NNH = 1/ absolute risk increase
if the parameter of interest is a difference between groups, what confidence interval will indicate statistically significant
if the confidence interval does not include the null hypothesis, which is 0 when testing for a difference between groups, the data is statistically significant
(if comparing relative risk or odds ration, the null value is 1)
how is the confidence interval of the mean calculated
confidence interval of mean = mean + [z-score for confidence leve] x (SD/square root of n)
which of the follow has the best indication of accuracy: sensitivity, specificity, area under the curve
area under the curve
closer to 1 = more accurate
what do you know about the p value if the 95% confidence interval does not include the null hypothesis
the p value is < .05
what is length time bias
subjects with a rapidly progressive form of disease are less likely to be detected by screening compared to those with slowly progressive disease
what phase of a drug trial includes post marketing surveillance that assesses rare or delayed adverse effects of newly approved treatments on the market
phase IV
The unit of analysis in ____ studies is populations rather than individuals
ecological
what is the equation to determine relative risk reduction
RRR= (Risk in control- risk in treatment)/risk in control
or
RRR= 1-relative risk