Edited, memorised or added to reading queue

on 01-Jul-2022 (Fri)

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

Flashcard 7101870378252

Tags
#causality #statistics
Question
In observational data, it is unrealistic to assume that the treatment groups are exchangeable. In other words, there is no reason to expect that the groups are the same in all relevant variables other than the [...].
Answer
treatment

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
data, it is unrealistic to assume that the treatment groups are exchangeable. In other words, there is no reason to expect that the groups are the same in all relevant variables other than the <span>treatment. <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101872475404

Tags
#causality #statistics
Question
We denote by π‘Œ(1) the potential outcome of happiness you would observe if you were to get a dog ( 𝑇 = [...] )
Answer
1

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
We denote by π‘Œ(1) the potential outcome of happiness you would observe if you were to get a dog ( 𝑇 = 1 )

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101874048268

Tags
#causality #statistics
Question
What do we do when we go to actually estimate quantities such as 𝔼 𝑋 [ 𝔼[π‘Œ | 𝑇 = 1, 𝑋] βˆ’ 𝔼[π‘Œ | 𝑇 = 0, 𝑋] ] ? We will often use a model (e.g. linear regression or some more fancy predictor from machine learning) in place of the [...] 𝔼[π‘Œ | 𝑇 = 𝑑, 𝑋 = π‘₯] . We will refer to estimators that use models like this as model-assisted estimators. Now that we’ve gotten some of this terminology out of the way, we can proceed to an example of estimating the ATE
Answer
conditional expectations

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
lly estimate quantities such as 𝔼 𝑋 [ 𝔼[π‘Œ | 𝑇 = 1, 𝑋] βˆ’ 𝔼[π‘Œ | 𝑇 = 0, 𝑋] ] ? We will often use a model (e.g. linear regression or some more fancy predictor from machine learning) in place of the <span>conditional expectations 𝔼[π‘Œ | 𝑇 = 𝑑, 𝑋 = π‘₯] . We will refer to estimators that use models like this as model-assisted estimators. Now that we’ve gotten some of this terminology out of the way, we can proceed t

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101875883276

Tags
#causality #has-images #statistics


Question
if the DAG were simply two connected nodes 𝑋 and π‘Œ as in Figure 3.8, the local Markov assumption would tell us that we can factorize 𝑃(π‘₯, 𝑦) as 𝑃(π‘₯)𝑃(𝑦|π‘₯) , but it would also allow us to factorize 𝑃(π‘₯, 𝑦) as 𝑃(π‘₯)𝑃(𝑦) , meaning it allows distributions where 𝑋 and π‘Œ are [...]. In contrast, the minimality assumption does not allow this additional independence
Answer
independent

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
cal Markov assumption would tell us that we can factorize 𝑃(π‘₯, 𝑦) as 𝑃(π‘₯)𝑃(𝑦|π‘₯) , but it would also allow us to factorize 𝑃(π‘₯, 𝑦) as 𝑃(π‘₯)𝑃(𝑦) , meaning it allows distributions where 𝑋 and π‘Œ are <span>independent. In contrast, the minimality assumption does not allow this additional independence <span>

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101877718284

Tags
#causality #statistics
Question
The causal graph for interventional distributions is simply the same graph that was used for the observational [...] distribution, but with all of the edges to the intervened node(s) removed.
Answer
joint

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
The causal graph for interventional distributions is simply the same graph that was used for the observational joint distribution, but with all of the edges to the intervened node(s) removed.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101880077580

Tags
#causality #statistics
Question

Rather, my outcome is only a function of [...]. We’ve been using this assumption implicitly throughout this chapter. We’ll now formalize it.

Assumption 2.4 (No Interference) π‘Œ 𝑖 (𝑑 1 , . . . , 𝑑 π‘–βˆ’1 , 𝑑 𝑖 , 𝑑 𝑖+1 , . . . , 𝑑 𝑛 ) = π‘Œ 𝑖 (𝑑 𝑖 )

Answer
my own treatment

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Rather, my outcome is only a function of my own treatment. We’ve been using this assumption implicitly throughout this chapter. We’ll now formalize it. Assumption 2.4 (No Interference) π‘Œ 𝑖 (𝑑 1 , . . . , 𝑑 π‘–βˆ’1 , 𝑑 𝑖 , 𝑑 𝑖+1 , . . . , 𝑑 𝑛 ) = π‘Œ

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7101881912588

#GAN #data #sequential #synthetic
In sequential data, information can be spread through many rows, like credit card transactions, and preservation of correlations between rows β€” the events β€” and columns β€” the variables is key
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
Generating synthetic time-series and sequential data is more challenging than tabular data where normally all the information regarding one individual is stored in a single row. In sequential data, information can be spread through many rows, like credit card transactions, and preservation of correlations between rows β€” the events β€” and columns β€” the variables is key. Furthermore, the length of the sequences is variable; some cases may comprise just a few transactions while others may have thousands.

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7101883747596

Tags
#causality #statistics
Question
When we say β€œidentification” in this book, we are referring to the process of moving from a causal estimand to an equivalent [...] estimand
Answer
statistical

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
When we say β€œidentification” in this book, we are referring to the process of moving from a causal estimand to an equivalent statistical estimand

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101885582604

Tags
#causality #has-images #statistics


Question
We refer to the flow of [...] along directed paths as causal association
Answer
association

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
We refer to the flow of association along directed paths as causal association

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101888466188

Tags
#causality #statistics
Question

Definition 3.4 (d-separation) Two (sets of) nodes 𝑋 and π‘Œ are d-separated by a [...] 𝑍 if all of the paths between (any node in) 𝑋 and (any node in) π‘Œ are blocked by 𝑍

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

Answer
set of nodes

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

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

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101892136204

Tags
#causality #statistics
Question
Regular Bayesian networks are purely statistical models, so we can only talk about the flow of [...] in Bayesian networks.
Answer
association

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Regular Bayesian networks are purely statistical models, so we can only talk about the flow of association in Bayesian networks.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7101894757644

Tags
#causality #statistics
Question
Positivity is the condition that all subgroups of the data with different covariates have some probability of receiving [...] value of treatment
Answer
any

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Positivity is the condition that all subgroups of the data with different covariates have some probability of receiving any value of treatment

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7101905767692

earch and review in SuperMemo is a review of a subset of elements that contain a given search phrase. For example, before an exam in microbiology, a student may wish to review all his knowledge of viruses using the following method:
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

SuperMemo: Subset learning
ty, difficulty, interval, recency, text size, etc. The review may also be semantic or neural where connections between elements determine the sequence of review. Review types Search and review S<span>earch and review in SuperMemo is a review of a subset of elements that contain a given search phrase. For example, before an exam in microbiology, a student may wish to review all his knowledge of viruses using the following method: search for all elements containing the phrase virus (e.g. with Ctrl+F) review all those elements (e.g. with Ctrl+Shift+L) The review may include all subset elements (e.g. Learning : Rev