Association Models

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/28

encourage image

There's no tags or description

Looks like no tags are added yet.

29 Terms

1
New cards

Confounding


When another variable distorts the observed association between an exposure and an outcome.


2
New cards

Effect modification:

When the association between an exposure and an outcome differs depending on another variable.

How do we identify whether an effect differs between groups?

3
New cards

Outcome

Predictor

Method

Binary

Binary/categorical


Continuous

Binary


Continuous

Categorical (3+ groups)


Binary

Continuous


Continuous

Continuous


Survival

Categorical


Survival

Continuous



Outcome

Predictor

Method

Binary

Binary/categorical

Chi-square test

Continuous

Binary

t-test

Continuous

Categorical (3+ groups)

ANOVA

Binary

Continuous

Logistic regression

Continuous

Continuous

Linear regression

Survival

Categorical

Log-rank test

Survival

Continuous

Cox regression


4
New cards

crude association

association calculated without adjusting for other variables.

5
New cards

The structure of confounding: DAG

knowt flashcard image
6
New cards

How can we deal with confounding?

  1. By design: Randomization, as in a randomized controlled trial.

  2. Covariate adjustment: Include potential confounders in a regression model.

  3. Re-weighting approaches: Give different observations different weights to account for differences between groups.


7
New cards

When does covariate adjustment work?

1. No unmeasured confounding

We need to have collected information on the relevant confounders.

For example, if both age and cholesterol are influenced by another important variable, but we never measured that variable, we cannot adjust for it in our regression model.

2. Correct model specification

We must use an appropriate statistical model.

For example, if the relationship between age and cholesterol is strongly nonlinear, but we fit a simple linear regression, our model may not represent the relationship correctly.

So, even if we have measured the confounders, incorrect modelling can still produce misleading results.

8
New cards

Suppose men are older than women and men also have higher cholesterol. What happens to the crude association between age and cholesterol?

It is overestimated

9
New cards

Suppose women are older than men but women have lower cholesterol. What happens to the crude age–cholesterol association?

It is underestimated

10
New cards

Adjusting for a collider can create a false association

Advanced cancer stage → Hospital admission ← Other serious illness

Hospital admission is the collider because both variables point towards it.

Why is adjusting for it a problem?

Imagine looking only at patients who were admitted to hospital. Among those patients, someone without advanced cancer may be more likely to have been admitted because of another serious illness.

This can create an apparent relationship between advanced cancer stage and other serious illness, even if they were not related in the general population.

11
New cards

Difference between cofounder and mediator

  • Confounder: a variable that influences both the exposure and outcome.

  • Mediator: a variable through which the exposure influences the outcome.


12
New cards

What is a heterogeneous effect?

The effect of a treatment or exposure is not necessarily the same for everyone.

13
New cards

You want to investigate whether exercise affects glucose levels. Which variable is the outcome and which is the predictor?

Outcome = glucose. Predictor/exposure = exercise.

14
New cards



15
New cards



16
New cards

How do you assess whether BMI confounds the exercise–glucose association?

Compare the exercise coefficients in crude and adjusted models. A change greater than 10% suggests confounding.

17
New cards

The crude coefficient is 6.3 and the adjusted coefficient is 5.0. Calculate the percentage change.

knowt flashcard image
18
New cards

The crude coefficient is 0.08 and adjusted coefficient is 0.076. Is there substantial confounding?

No. The change is 5%, below the 10% rule of thumb.

19
New cards

How do you test whether a continuous confounder is associated with a continuous outcome?

Use linear regression

20
New cards



21
New cards

In regression output, the interaction p-value is 0.003. What do you conclude?

Significant evidence of effect modification

22
New cards

The interaction p-value is 0.42. What do you conclude?

Insufficient evidence of effect modification.

23
New cards

Coffee = 5.6945 and Coffee:Sex = 1.4914. Calculate the coffee effect in males.

5.6945+1.4914=7.1859


Each additional unit of coffee is associated with an increase of 7.186 beats/min in males.

<p>5.6945+1.4914=7.1859</p><p></p><p>Each additional unit of coffee is associated with an increase of 7.186 beats/min in males.</p>
24
New cards

A researcher investigates whether diabetes confounds the association between blood pressure and BMI. Which two models are required?

mod1 <- lm(mass ~ pressure, data = SynthDiabetes2)

mod2 <- lm(mass ~ pressure + diabetes,

data = SynthDiabetes2)


(crude and adjusted)

25
New cards

In the adjusted model, the diabetes coefficient has p = 0.001. Does this alone prove confounding?

No. Also compare the crude and adjusted pressure coefficients.

26
New cards

A researcher investigates whether N-stage modifies the association between ENS and time to distant metastasis. Which regression model is appropriate?

Write the R code to investigate this interaction.

Cox regression, because the outcome is survival time.

mod1 <- coxph(
  Surv(DMtime, DM) ~ ENS * factor(N),
  data = DM
)
summary(mod1)


27
New cards

The likelihood ratio test gives p = 0.25. Is there evidence of effect modification?

No. There is insufficient evidence of interaction.

28
New cards

What is the appropriate regression model when the outcome is DM12 (yes/no)?

Logistic regression.

29
New cards

Crude linear model

lm(y ~ x, data=d)

Adjusted linear model

lm(y ~ x + z, data=d)

Linear interaction

lm(y ~ x * z, data=d)

Logistic regression

glm(y ~ x, data=d, family="binomial")

Logistic interaction

glm(y ~ x * z, data=d, family="binomial")

Cox regression

coxph(Surv(time,status) ~ x, data=d)

Cox interaction

coxph(Surv(time,status) ~ x * z, data=d)

Odds ratios

exp(coef(mod))

OR confidence intervals

exp(confint(mod))

Nested model comparison

anova(mod0, mod1)

Likelihood ratio test

lrtest(mod0, mod1)