Biostats Quiz 2

Front 1

a computed disease rate that takes into acount the characteristics of the population so that rates in diff locales can be compred despite characteristics like age and gender

Back 1

adjusted rate

Front 2

the incidence of disease occurring during a limited period of risk (e.g the time span of a food borne outbreak of gastroenteritis)

Back 2

attack rate

Front 3

the proportion (percent) of people with disease who die w/in a specified time after disease onset

Back 3

case-fatality

Front 4

a disease rate that include all persons in a population w/o distinction with regard to age, gender, race, etc

Back 4

crude rate

Front 5

a databasse of information regarding all cases of certain disease that occur in a aspecficied population during a specified time period

Back 5

disease register

Front 6

infant mortality rate =

Back 6

# of deaths children under 12 months / number of live births X 1,000 (per 1,000)

Front 7

the number of deaths related to pregnancy of pregnant women in a year divided by the number of live births in that year (per 100,000)

Back 7

maternal mortality rate

Front 8

mortality =

Back 8

the incidence rate of death

Front 9

neonatal mortality rate

Back 9

number of deaths of children under 28 days in a given year divided by the total number of live births in that year, times 1000

Front 10

a disease for which notification of local health authorities is required

Back 10

notifiable disease

Front 11

the incidence of disease among contacts or household members following the occurrence of a primary case - the period observation is specified and usually brief

Back 11

secondary attack rate

Front 12

in survival analysis, when survival time for an individual is not observed because the individual was still alie at the end of the study or the subject is lost in follow up

Back 12

censored data

Front 13

a test for evalluating assocation between two variables in a contingency tabe. in the 2x2 tabel this test is equivalent to comparing proportions in two groups of patients

Back 13

chi-squared test

chi-squared statistic would help you reject or accept the null

Front 14

a rectangular array of numbers, typically croos classification of subjects into categries of two measurements

Back 14

contignency table

comparing expected to observed then you would want to do a chi-squared test to see if this difference is due to chance or not

Front 15

a statistical test for comparing the means on a continuous measurement for two separate groups of individuals. for example this test can be used to compare mean SBP in males versus females

Back 15

independent samples T-test

Front 16

Kaplan-Meier method (or Product-limit method

Back 16

a procedure for estimating a survival function form survival data in presence of censoring

Front 17

a tabulation showing the survival experience of a group of subjects over time. specifically showing the survival function estimated from data

Back 17

lifetable

1. divide follow up times into intervals
2. probability of dying during given interval is hazard (h = those who died / n entering interval)
3. prob of surviving that interval is 1-h
4. prob of surviving interval 2 is (1-h1)x (1-h2) ....

Front 18

a statistical test for comparing two survival curves

Back 18

log-rank test

Front 19

the time at which 50% of the individuals have experienced the event of interest. the timepoint at which the survival fucntion crosses 50%

Back 19

median survival

Front 20

a statistical test for comparing the means of paired continuous measurements. this test is usually applied to the case where a single indivdidual is observed on 2 occasions (before and after)

Back 20

paired-samples T-test

1. compute difference score for each observed pair (y1-y2 = d)
2. calculate mean of that (d)and the SD of difference scores
3. do a test statistic test
t=(mean d / SE)

Front 21

statistical evaluation of time to event data. examples include time to death, time to disease progression, and time until onset to the disease

Back 21

survival analysis

Front 22

describes the probability that an individual will survive beyond a specific point in time

Back 22

survival function

Front 23

R squared

Back 23

coefficient of determination
= 1 - (variation in Y not explained by X / total
variation in Y about mean)

describes proportion of total variation of dependent variable explained by its linear relationship w/ independent variable
e.g if it is .518 then the independent variable explains 51% of the variation in dependent

Front 24

linear regression analysis, this is the proportion of total variation in the dependent variable explained by the independent variable

Back 24

coefficient of determination (R squared)

Front 25

how is the dependent variable different in a linear regression versus a logistic regression

Back 25

in the linear regression the dependent variable is continuous. in the logistic regression it is dichotomous.

Front 26

what is the dependent variable in a proportional hazards regression

Back 26

survival time

Front 27

explanatory variable is also called

Back 27

the independent variable

Front 28

an independent variable that takes on the values of 0 or 1 e.g to describe Male or F

Back 28

indicator variable

Front 29

a procedure based on minimizing the squared error, for estimating the intercept and slopes in a linear regression

Back 29

least squares

Front 30

a statistical analysis that predicts a continuous dependent variable using one or more independent variables

Back 30

linear regression

Front 31

a regression analysis procedure used to predict the value of a dichotomous variable. the effects of independent variables are usually presented as odds ratios

Back 31

logistic regression

if the regression is higher than one than the variable is positively associated with the risk.

Front 32

a linear regression analysis using two more more independent variables

Back 32

multiple linear regression

y = a + (b1x1) + (b2x2) ....

Front 33

a regression analysis using (linear, logistic, or proportional hazards) using two or more independent variables

Back 33

multivariate regression analysis

Front 34

a relationshiop in which the scatterplot of a dependent variable and an independent variable is not well approximated by a straight line

Back 34

non-linear

Front 35

a regression analysis procedure used in survival analysis with censored data. the effects of the independent variables are usually presented as risk ratios

Back 35

proportional hazards regression

Front 36

an estimate of the intercept or slope in a regression analysis

Back 36

regression coefficeint

Front 37

a linear regression analysis using one independent variable

Back 37

simple linear regression

Front 38

the amount of change in the dependent variable when the independent variable increases by 1 unit

Back 38

slope

Front 39

a regression analysis (any of the three) using one independent variable

Back 39

univariate regression analysis

Front 40

the difference between the riskds of the exposed group and the unexposed group

Back 40

attributable risk

Front 41

an analysis in which statistical account is made for potential confounding factors, so that an estimate of the independent effect of a risk factor can be made

Back 41

adjusted analysis

could be via statistical modeling (regression techniques) or stratified analysis (breaking up confounding variables into narrow stratum or by doing separate analysis)

Front 42

events that prevent the observation of a possible endpoint

Back 42

competing risks

Front 43

an indirect association of an exposreu with disease.

Back 43

confounding

Front 44

choosing exposed and unexposed subjects to have the same or similar values of some trait or exposreu - to control for confounding

Back 44

matched analysis

Front 45

a groupoing of subjects, typically formed for the purpose of adjustment (e.g age groups)

Back 45

stratum

Front 46

the error that resuts when one rejects the null when it is true or when one concludes there is a difference when there is not

Back 46

type 1 error

Front 47

the error that results when one does not reject the null and it is false or when one does not detect a diff when there is one

Back 47

type II error

Front 48

confining the analysis to one group of subjects to minimize confounding

Back 48

restricted analysis

Front 49

the probability that an evne will occur in a defined period of time

Back 49

risk

Front 50

the probability of event in the exposed group / the probability of an event in the unexposed group

Back 50

risk ratio

Front 51

test statistic =

Back 51

the effect / SE

Front 52

the difference between the sample mean and the hypothesized mean

Back 52

effect

Front 53

restricted activity day, work loss day and bed disability day are estimates of

Back 53

disability

Front 54

the standard erroe =

Back 54

SD over square root of n

Front 55

the probability of a type I error is also called

Back 55

statistical significance level
Prob that you reject null when it is true

Front 56

confidence interval =

Back 56

mean plus or minus 2 x SE

Front 57

which risk (relative or atributable) indicateds best the causal relationship

Back 57

relative risk

Front 58

which risk (relative or attributable) is usually linked to indicating a clincal significance

Back 58

attributable