Biostats Flashcards Preview

STEP1 > Biostats > Flashcards

Flashcards in Biostats Deck (14):

What percentage of the populations falls within 1, 2, and 3 standard deviations of the mean of a normal distribution?

1 - 68
2 - 95.5
3 - 99.7


What is a positively-skewed distribution?

One in which the mean is greater than the median, such that the distribution has a longer tail on the right (at greater values)


What is a negatively-skewed distribution?

One is which the mean is less than the median, such that the distribution has a longer tail on the left (at lower values).


What is the customary alpha-criteria for determining statistical significance?

P-values less than 0.05.

In this case, the null hypothesis that there is no difference is rejected, and the alternative is left: that there is a relationship.


What measure can be used to evaluate cohort studies?

Relative risk

This is found by dividing the incidence rate of the exposed group by the incidence rate of the control/unexposed group


What is incidence?

The number of new cases in a given period of time divided by the total susceptible population


What is prevalence?

The total number of cases in a slice in time divided by the total population


What is the crude mortality rate?

The number of deaths from all causes divided by the total population


What is the rate of increase of a disease?

The number of new cases of a disease minus the number of deaths (or cures) from the disease, divided by the total population.


How are incidence and prevalence related?

Prevalence = incidence * duration


How do you calculate a 95% confidence interval?

CI = sample mean +/- Z*(SD/n^-2)

the confidence interval reflects the probability that the confidence interval will contain the true parameter.


What is the difference between a confidence interval and "crude"/"simple" standard of deviation?

The (95%) confidence interval is an inferential statistic that can be used to decide where the true mean might be, whereas the standard deviation is a descriptive statistic, and cannot be used to make any assumptions about the true mean


What is the relationship between a test's sensitivity and specificity, and the positive and negative predictive values?

Tests with 100% sensitivity (no false negatives) will have a negative predictive value (NPV) of 100%; tests with 100%; tests with 100% specificity (no false positives) will have a positive predictive value (PPV) of 100%.


What are nominal data?

Things counted in groups or categories