L10: Causality Flashcards

1
Q

Factorise problem on slides 6-8?

A

Yes?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Marginalise problem on slides 10-13?

A

Yes?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Definition of causal inference?

A

X causes Y if and only if changing X leads to a change in (the distribution of) Y, keeping all else constant.

Existence of causal effect
X has a causal effect on Y if there are values a and b for X such that p(Y |do(X = a)) not equal to p(Y |do(X = b))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is the danger of observational studies?

A

Can mistake correlation for causation. Need to try to control for confounders and compare similar subgroups (usually still not enough for a causal discovery in general)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is Simpson’s Paradox?

A

Simpson’s paradox is a phenomenon in probability and statistics in which a trend appears in several groups of data but disappears or reverses when the groups are combine

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Definition causal effect

A

The causal effect is the magnitude by which Y is changed by a (unit) change in X.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is the interventionist approach to causality?

A

Taking an action while keeping other relevant factors constant.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Describe counterfactual thinking

A

From time t − 1 to time t, we decide to change from Y_old to Y_new .
* Yold and Ynew represent two options that we are investigating about which one is best – they are not related to time.
* What would have happened
had we not done what we did?
* Estimating the effect
of the intervention:
* Naive: E[Ynew (t)] − E[Yold (t − 1)]
* Causal: E[Ynew (t)] − E[Yold (t)] (compare the effect of both options at the same time against each other)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Describe the three methods for answering causal questions and some examples

A
  • Randomization (harder but most valid)
    * A/B test
    * Multi-armed bandits
  • Natural Experiments (intermediate)
    * Regression discontinuity
    * Instrumental Variables
  • Conditioning (easy but less valid)
    * Stratification
    * Matching
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Difference between internal and external validity

A

Internal validity
Validity of conclusions drawn within context of particular study

External validity
Generalizability of empirical findings to new environments, settings or populations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Give examples of do-operations

A

Do-operation on switch S = on:
“glue the switch in the position on”.

Do-operation on B = bright:
“short-cut the electrical circuit
such that there is always light”.

p(Y = 1|do(X = 1)):
probability of re-arrest if program were compulsory for all prisoners

Note that generally p(Y = 1|X = 1) not equal to p(Y = 1|do(X = 1)).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Definition of Causal Bayesian Network

A

A Causal Bayesian Network is a tuple (G,P(· | ·)) where
* G is a DAG with vertices X1, . . . , Xn, and
* P(· | ·) is a family of conditional probability tables.
The model encodes the PMF p(X1, . . . , Xn) = Product of P(Xi| pa(Xi))

AND

For any subset W of V = {1, . . . , n} and joint configuration xW = {Xj = xj
: j ∈ W },
we have (truncated factorisation formula)
p(X1, . . . , Xn|do(xW )) = Y
i∈V \W
P(Xi
| pa(Xi)) ·
Y
j∈W
I(Xj = xj)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Describe the Bayesian Networks for slide 59 and whether the causal Bayesian networks are the same

A

Yes?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Write down the formula after the intervention on X2 in slide 61-62

A

Yes?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Describe the formulas for causal effect

A

Total average causal effect (ACE) of X = a with respect to X = b on Y is
ACE(a, b) = E(Y |do(X = a)) − E(Y |do(X = b))
The amount of causal effect (CE) of X = a with respect to X = b on Y = y is
CE(a, b, y) = p(Y = y|do(X = a)) − p(Y = y|do(X = b))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Complete the derivation on slide 66/68

A

Yes?

17
Q

Can you do the causal effect example on slide 87?

A

Yes?

18
Q

What is the interventionist interpretation of causality?

A

Taking an action while keeping other relevant factors constant

19
Q

What is counterfactual thinking?

A

Counterfactual thinking enables us to reason causally about what did not happen

If have old world Y(t-1) then could naively compare E[X(t)]-E[Y(t-1)] but the causal way would compare at the same timestamp, i.e. that the old world also developed E[X(t)]-E[Y(t)]