# on 18-May-2022 (Wed)

#### Annotation 7070692543756

 #causality #statistics The Positivity-Unconfoundedness Tradeoff Although conditioning on more covariates could lead to a higher chance of satisfying unconfoundedness, it can lead to a higher chance of violating positivity. As we increase the dimension of the covariates, we make the subgroups for any level π₯ of the covariates smaller. The Positivity-Unconfoundedness Tradeoff This is related to the curse of dimensionality. As each subgroup gets smaller, there is a higher and higher chance that either the whole subgroup will have treatment or the whole subgroup will have control. For example, once the size of any subgroup has decreased to one, positivity is guaranteed to not hold.

#### pdf

cannot see any pdfs

#### Flashcard 7070797663500

Tags
#causality #statistics
Question
The idea is that although the treatment and potential outcomes may be unconditionally associated (due to confounding), within levels of π , they are not associated. In other words, there is no [...-ing?] within levels of π because controlling for π has made the treatment groups comparable.
confounding

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
an> The idea is that although the treatment and potential outcomes may be unconditionally associated (due to confounding), within levels of π , they are not associated. In other words, there is <span>no confounding within levels of π because controlling for π has made the treatment groups comparable. <span>

#### Original toplevel document (pdf)

cannot see any pdfs

#### Flashcard 7088143207692

Question
Galois Theory Galois theory is what?
the interplay between polynomials, fields, and groups

status measured difficulty not learned 37% [default] 0

#### pdf

cannot see any pdfs

#### Annotation 7088153955596

 #causality #statistics not only is association not causation, but causation is a sub-category of association. Thatβs why association and causation both flow along directed paths.

#### Parent (intermediate) annotation

Open it
Association flows along all unblocked paths. In causal graphs, causation flows along directed paths. Recall from Section 1.3.2 that not only is association not causation, but causation is a sub-category of association. Thatβs why association and causation both flow along directed paths.

#### Original toplevel document (pdf)

cannot see any pdfs

#### Flashcard 7088156052748

Tags
#causality #statistics
Question
The minimal building blocks of DAGs consist of chains, forks, [...], two unconnected nodes, and two connected nodes.
immoralities

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
The minimal building blocks of DAGs consist of chains, forks, immoralities, two unconnected nodes, and two connected nodes.

#### Original toplevel document (pdf)

cannot see any pdfs

#### Flashcard 7088157887756

Tags
#causality #statistics
Question
The main reason for moving from exchangeability (Assumption 2.1) to conditional exchangeability (Assumption 2.2) was that it seemed like a more [...] assumption
realistic

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
The main reason for moving from exchangeability (Assumption 2.1) to conditional exchangeability (Assumption 2.2) was that it seemed like a more realistic assumption

#### Original toplevel document (pdf)

cannot see any pdfs

#### Flashcard 7088159722764

Tags
#causality #statistics
Question

Definition 3.4 (d-separation) Two (sets of) nodes π and π are d-separated by a set of nodes π if all of the paths between (any node in) π and (any node in) π are [...] by π

Source: Pearl (1988), Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference

blocked

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
Definition 3.4 (d-separation) Two (sets of) nodes π and π are d-separated by a set of nodes π if all of the paths between (any node in) π and (any node in) π are blocked by π Source: Pearl (1988), Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference

#### Original toplevel document (pdf)

cannot see any pdfs

#### Flashcard 7088161557772

Tags
#causality #has-images #statistics

Question

We assumed π is discrete when we summed over its values, but we can simply replace the sum with an [...] if π is continuous. Throughout this book, that will be the case, so we usually wonβt point it out

To jest kluczowe rΓ³wnanie.

integral

status measured difficulty not learned 37% [default] 0

#### Parent (intermediate) annotation

Open it
We assumed π is discrete when we summed over its values, but we can simply replace the sum with an integral if π is continuous. Throughout this book, that will be the case, so we usually wonβt point it out To jest kluczowe rΓ³wnanie.

#### Original toplevel document (pdf)

cannot see any pdfs

#### Annotation 7088164441356

 #causality #statistics The Positivity-Unconfoundedness Tradeoff This is related to the curse of dimensionality. As each subgroup gets smaller, there is a higher and higher chance that either the whole subgroup will have treatment or the whole subgroup will have control. For example, once the size of any subgroup has decreased to one, positivity is guaranteed to not hold.

#### Parent (intermediate) annotation

Open it
sfying unconfoundedness, it can lead to a higher chance of violating positivity. As we increase the dimension of the covariates, we make the subgroups for any level π₯ of the covariates smaller. <span>The Positivity-Unconfoundedness Tradeoff This is related to the curse of dimensionality. As each subgroup gets smaller, there is a higher and higher chance that either the whole subgroup will have treatment or the whole subgroup will have control. For example, once the size of any subgroup has decreased to one, positivity is guaranteed to not hold. <span>

#### Original toplevel document (pdf)

cannot see any pdfs

#### Flashcard 7088166276364

Tags
#causality #statistics
Question
Exchangeability means that the treatment groups are exchangeable in the sense that if they were swapped, the new [...] group would observe the same outcomes as the old treatment group