Biostatistics Flashcards
Statistical test: two qualitative variables
chi square test
Statistical test: two quanitative variables
linear regression analysis
Statistical test: Qualitative –> Quantitative > 30 population
Z test
Statistical test: Qualitative –> Quantitative < 30 population
T-test
Statistical test: Qualitative –> Quantitative > 3 groups
ANOVA
Statistical test: Quantitative –> Qualitative
Regression analysis
Statistical tet: reliability
Kappa statistic test
Percentage: 1 standard deviation
68%
Percentage: 2 standard deviations
95%
Percentage: 3 standard deviations
99.5%
Skewed to the left:
Mean is ___ than median
smaller
Skewed to the right:
Mean is ___ than median
larger
Scale: value of zero is arbitrary
Interval scale
Scale: highest form, (+) clear zero point
Ratio scale
Scale: lowest form, no intrinsic order
Nominal scale
Scale: intrinsically ordered, but not quantitatively
Ordinal scale
Proportion of true negative to those who tested negative
Negative predictive value
Proportion of true positive to those who tested positive
Positive predictive value
Proportion of true negative to those without disease
Specificity
Proportion of true positive to those with disease
Sensitivity
Screening test
Sensitivity
Confirmatory test
Specificty
TRUE OR FALSE
Sampling frame is necessary in simple random sampling
True
TRUE OR FALSE
Sampling frame is necessary in stratified random sampling
False
TRUE OR FALSE
Sampling frame is necessary in cluster sampling
False
Denominator in incidence rate
Person-years of observation
Causes distortion of results because the factor is distributed unevenly in exposed and unexposed individuals
The association between two variables is distorted by the fact that both are associated with a third
Difference in crude and adjustment risks
Confounding
Magnitude of the effect of a particular exposure on the outcome will vary according to the presence of a third factor
Effect modification
Control for confounding: case-control studies
Matching
Control for confounding: clinical trials
Randomization
Control for confounding: large cohort studies
Analysis
As prevalence decreases, the positive predictive value
Decreases
As prevalence decreases, the negative predictive value
Increases
Bias: when the screening test advances the time of diagnosis, but no true prolongation of life occurs because survival for persons who are screened and those who are not is the same from the time the cancer occurs
Lead bias
Bias: screening test less likely will detect a rapidly progressive disease if symptoms rapidly develop because the window period between the time the cancer can be detected when it is asymptomatic by a screening test and the time it will become clinically significant is short
Length bias
MIsclassification of exposure is not random
Result in overestimate of an association
Differential misclassification
When memory of exposure is unrelated to the fact that a person has a disease or not
Consequence of an imprecise measurement of eitther exposure or outcome
Causes the results to move towards the null (no association)
Nondifferential misclassification
Ratio of the observed number to the expected number of deaths or cases of the disease
Standardized mortality or morbidity ratio
Persons followed for variable lengths of time are counted according to the length of time they were followed
Survival anaylsis