Definitions Chapter 9 & 19 Flashcards
Categorical Variable
variable the represents counts of the number of obsevations falling int o each of several caterogies
- frequency of something
Interaction
the situation where the effect of one variable, depends on or is conditional on, another
Chi square test
a statistic test often used for categorical data
goodness of fit “
a test for comparing observed frequencies with theoretical frequences (o-e)2/e
Observed frequencies:
the frequencies you observe ??? weird eh
Expected frequencie
the expected value for the number of observations in a cell if null is true
Contingency table:
two dimensional table in which each observation is classified on the basis of two variables simutaneously
Prospective study
a study in which a tx is administrered and we look for the effects in the future
retrospective study
when partcipants on the basis of some condition and then look retrospectivley at their behavior
Risk:
the number of ppl or objects experiencing an event divided by the total number of people or objects
Odds:
the frequency of occurance of one event divided by the frequency of occurance of another event
PHI:
the correlation coefficient when both the varaibles are measured as dichotomies
Point biserial correlation:
the correlation coefficient when one of the variables is dichotomous
Dichotomous variables:
variables that can only take on two different values
boys girls
dead alive
population correlation coefficient (rho)
the correlation coefficient for the population
heterogeneous samples
data in which the sample of observations could be subdivided into two distinct sets on the basis of some other variable
Range restrictions
cases where in the range over which x or y varies is artificiallly limited
Monotonic Relationships
a relationship presented by a line that is contiually increasing or decreasing but not really a straight line
ranked data:
data for which the oberrvation have been replaced by highest to lowest
spearmens correlation coeffeficient for ranked data
a correlation for ranked data
covariance
a stat representing the degree to which two variables vary together
linear relationship
situation in which best fittign regression line is straight
negative relatonship
relationship in which increases in one variable and decreaes in aother
predictor vs criterion variable
the variable which the perdiction is made vs the variable to predidcted
Correlation:
the measure of relationship between variables
