Survival analysis

Question 1

what is the dependent variable in survival analysis?

Answer 1

The time until a well defined event occurs

Question 2

what kind of analysis is survival?

Answer 2

time-to-event analysis

Question 3

What is time in survival analysis?:

Answer 3

the time interval between the beginning of a study and the occurrence of the event.

Question 4

what is the duration of being at risk of the event?

Answer 4

time between the start of measuring and the event

Question 5

what is the main goal of survival analysis?

Answer 5

to estimate the survival probability from survival time and assess the effect of predictors (wealth, local conditions, etc.) on survival

Question 6

what is censoring?

Answer 6

when you don’t know what happened, if the event happened to the subject or not.

Question 7

what is right censoring?

Answer 7

the event happening after the measuring ended, or if it’s unknown excactly when it happened

Question 8

what is left censoring?

Answer 8

when the event happened before you started measuring

Question 9

what is not censored data called?

Answer 9

complete

Question 10

how is censored data represented in a graph?

Answer 10

with a plus.

Question 11

how do you account for censoring?

Answer 11

a survival analysis

Question 12

S(t)=

Answer 12

survival function. The probability that a subject survives from the starting time to beyond a specific time t.

Question 13

H(t)=

Answer 13

hazard function. The instantaneous probability for the event to occur, if the subject survived to time t.

Question 14

what does a constant hazard function mean for survival function?

Answer 14

exponential decrease

Question 15

how can you know if hazard function is constant over time?

Answer 15

Ln(survival function). if the line is straight the hazard function is constant over time.

Question 16

whats the probability of the event happening?

Answer 16

1- survival probability

Question 17

what is on the y-axis in survival probability graph?

Answer 17

probability of survival

Question 18

how to calculate the probabily of survival and event happening for a time that wasn’t monitored?

Answer 18

you convert P to a rate at which events take place over time (r). then if occurs at constant rate you can calculate the P for a different time, and 1 - P is chance of event.

Question 19

in survival graph how to know if event rate increases or decreases?

Answer 19

upward curve (sad smile) = increase. flat line is constant. downward curve (happy smile) = decrease

Question 20

how to account for local conditions for survival rate?

Answer 20

you use Kaplan Meier estimation or cox proportional hazards model

Question 21

whats an assumption for cox?

Answer 21

the groups have to be proportional, the lines can’t cross. you can test this using Scaled Schoenveld residuals.

Question 22

what does cox estimate?

Answer 22

relative risk

Question 23

can you remove censored data in Kaplan Meier?

Answer 23

no

Question 24

if you have two groups in a Kaplan Meier graph, when is the difference likely significant?

Answer 24

if they don’t overlap.

Question 25

what’s the null hypothesis for cox?

Answer 25

Beta (regression coefficients for independent variables) are 0.

Question 26

Why don’t you compare the mean time- event between groups using t-test or regression?

Answer 26

Because this ignores censoring

Question 27

Why can’t you use proportion of events and logistic regression to compare mean - time events?

Answer 27

this ignores time

Question 28

what is ‘median’ in kaplan output?

Answer 28

time to event

Question 29

in a cox proportional hazard output, what is the hazard of the individual that got the treatment relative to the baseline hazard?

Answer 29

100* Exp(coef)