Introduction to Epidemiology

Question 1

Matching?

Answer 1

restricts enrollment within comparison group: subjects in comparison are chosen so they have same distributiaton of matching factor in index group

een van drie manieren voor voorkomen confounding (randomization, restriciton).

Question 2

implication matching :

1) cohort oz
2) CC oz

Answer 2

1) unexposed have same distribution as exposed (matching factor geen cf-er meer).
2) controls same distribution of maching factor as cases). NB!! matching alleen niet genoeg, ook matching in analyse toepassen.

Question 3

doel matching

Answer 3

1) avoid confouding

2) improve efficiency of analyses (minder pt nodig).

Question 4

matching in cohort oz op geslacht

Answer 4

1) for elke E+ man, zoek een E- man
2) for elke E+ Vrouw zoek een E- vrouw.
3) result: distributie gelijk in E+ en E- groep
4) . kan individueel (one-to-one) als frequency matching.

RR crude = RR adjusted!

Question 5

matching CC op geslacht

Answer 5

1: for elke Case man, vind controle die man is.
2: for each case that is female, find controle who is female
3: same sex distribution in case and control

Question 6

matching in CC oz: hoe kan na matching sex nogsteeds cf zijn?

Answer 6

controls not sampled independently of exposure (selection bias).

Dus: corrigeren in analyse op matching factor.

Question 7

ratio matchen in CC onderzoek:

Answer 7

improves efficiency of stratified analyses (je heb tiig zowel cases als controls within strata of matching facotr).

vb: prostaat kanker oz, zorgt age matching dat je voldoende controls hebt, omdat cases waarschijnlijk ouder zijn

Question 8

Overmatching

Answer 8

kan bias veroorzaken of study minder efficient.

Question 9

Defintion effect modification (ookwel INTERACTIE in statistiek)

Answer 9

Exposure has differente effect on outcome in differen tgroups of subjection

Question 10

effect mod & effect measure

Answer 10

Afhankelijk welke effect measure je neemt is er wel of geen effect modification (bv risk difference vs risk ratio).

Question 11

detection of effect mod: (3)

Answer 11

• most studies underpowered
• must distuingish from other reasons (bias, cf by other factors, chance)
• need for clinical or biologic rationale

Question 12

Ruling out chance variation 2:

Answer 12

(1) test of homogeneity (breslow-day test, regressie)

(2) Examine stratum-specific confidence intervals:

Question 13

Rapporteren bij effect modificatie:

Answer 13

• per stratum specific result (best option
• weighted average of stratum specific estimates (Mantel-Haensze; or regression
• standadization (average effect of exposure in a standard population.

Question 14

Standardiseren in 3 stappen

Answer 14

1: select standard population
2: stratifcy by confounder (age)
3: calculate risks of outcome within levels of confounder for EXPOSED AND UNEXPOSED

Question 15

Standardization: wat voor populatie?

Answer 15

1: internanl population (full dataset)
2: external population: take common set of rates and apply to popultion to be standardized.

Question 16

Redenen voor regressie in epidemiologie?

Answer 16

To control for confounding

to predict outcomes

Question 17

Motivatie propensity score analysis

Answer 17

1: control for large number of confounder (combine individual confounders ito a summary score (propensity score)

Question 18

propensity score =

Answer 18

probability of receiving the treatment as a function of the confoudners.

Question 19

3 steps in propensity score analysis:

Answer 19

Estimate propensity score using logistic regression (P(prob o receiving treatment)

2: use PS to balance observed covariates
3: estimate differnece in outcomes between treatment groups.

Question 20

Sensitiviteit

Specificiteit

Answer 20

sens: P(Test+|D+) true positive rate : a/ a+c (verticaal)
spec: P(T-/D-) = 1 - false positive rate

b / b+d

Question 21

Pos pred val:

Neg pred val:

Answer 21

P(Disease+| T +)
a/ a+b (horizontaal)

P(D- | T -): d / a+b

Question 22

Wat is afhankelijk van prevalentie van ziekte?

Answer 22

PREDICTIVE VALUES!

prevalentie = D+ / Dtot

Question 23

diagnostic tests vs clincal predication rules:

Answer 23

Diagnostic tests predict: currect state of health

Clinical predication rules predict FUTUre state of health.

Question 24

Performance measures: discrimination

Answer 24

Disc: ability to separaate subjects in different outcome states
ROC CURVES / classification tables:

Question 25

ROC curve

ideal curve

C statistic?

Answer 25

Plots sens (true positve rate) vs 1-spec (false postive rate).

ideaal: punt in li boven hoek (area close to 1.0

AUC (C-statistic) = probability that prediciteve vlaue for a subject with outcome is > than predicited value for a subject without outcome.

Question 26

Callibration:

Answer 26

Pertains to agreement between est risk and actual outcome.

Question 27

Method of assessment: resubstitution

testing set

resampling methods:

Answer 27

use same data to build model and evaluate its performance ( cave: overtraining!)

2: splitsen training en validatie set

bootstrapping / crsoov validation

Question 28

bootstrapping:

Answer 28

resampling with replacement as many times as individuals in original data.

Build model on bootstrap sample (training set).

evaluate performance onf original set (testing set)

Question 29

cross validation

Answer 29

Divide orginal data in 10 disjoint parts

Each part used as testing set for model for remaining 90%

Average performance of 10 models on 10 testing sets:
u

Use this average as estimate of performance