Edited, memorised or added to reading queue

on 23-Oct-2024 (Wed)

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

Flashcard 7629770984716

Tags
#causality #statistics
Question
[...] encompasses the assumption that is sometimes referred to as β€œno multiple versions of treatment.”
Answer
consistency

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
consistency encompasses the assumption that is sometimes referred to as β€œno multiple versions of treatment.”

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7629863783692

Tags
#DAG #causal #edx
Question
the most important take-home message: we need expert knowledge to determine if we should adjust for a variable. The statistical criteria are [...] to characterize confounding and confounders.
Answer
insufficient

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 most important take-home message: we need expert knowledge to determine if we should adjust for a variable. The statistical criteria are insufficient to characterize confounding and confounders.

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7629874269452

Tags
#DAG #causal #edx
Question

Two sources of [...]:

- common cause (confounding)

- conditioning on common effect (selection bias)

Answer
bias

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
Two sources of bias: - common cause (confounding) - conditioning on common effect (selection bias)

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7629876890892

Question
Why use a survey to ask customers about their experiences when data about customer interactions can be used to predict both [...] and the likelihood that a customer will remain loyal, bolt, or even increase business?
Answer
satisfaction

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
Why use a survey to ask customers about their experiences when data about customer interactions can be used to predict both satisfaction and the likelihood that a customer will remain loyal, bolt, or even increase business?

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7629879250188

Tags
#causality #has-images #statistics


Question
If we condition on a descendant of 𝑇 that isn’t a mediator, it could [...] a path from 𝑇 to π‘Œ that was blocked by a collider. For example, this is the case with conditioning on 𝑍 in Figure 4.13. This induces non-causal association between 𝑇 and π‘Œ , which biases the estimate of the causal effect
Answer
unblock

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
If we condition on a descendant of 𝑇 that isn’t a mediator, it could unblock a path from 𝑇 to π‘Œ that was blocked by a collider. For example, this is the case with conditioning on 𝑍 in Figure 4.13. This induces non-causal association between 𝑇 and π‘Œ , which biase

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7662640958732

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
Many alternative model specifications and network architectures offer the promises of improvements over vanilla LSTM models. They have already been proven superior in some domains. Such alternative specifications include Gated Recurrent Units, BiLSTM (Siami-Namini, Tavakoli, & Namin, 2019), Multi-Dimensional LSTM (Graves & Schmidhuber, 2009), Neural Turing Machines (Graves, Wayne, & Danihelka, 2014), Attention-Based RNN and its various implementations (e.g., Bahdanau, Cho, & Bengio, 2014; Luong, Pham, & Manning, 2015), or [...] (Vaswani et al., 2017).
Answer
Transformers

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
eural Turing Machines (Graves, Wayne, & Danihelka, 2014), Attention-Based RNN and its various implementations (e.g., Bahdanau, Cho, & Bengio, 2014; Luong, Pham, & Manning, 2015), or <span>Transformers (Vaswani et al., 2017). <span>

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7662643055884

#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Generally speaking, explaining the predictions of vector-based methods is more difficult than often as- sumed. This holds even for linear models like logistic regression. Features are often preprocessed, for example to binarize counts (Sec. 2). Furthermore, they are typically strongly correlated, making it troublesome to interpret individual coefficients [6]. Table 3 shows exemplary features weights in a logistic regression model used to predict order probabilities. If hundreds of features are utilized and are correlated and preprocessed, explaining the impact of consumer actions becomes a complex and confusing task
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
res for every time-step. Calculations at timesteps t and t βˆ’ 1 would be highly redundant: features at t represent the complete history until t and not only what happened in between t βˆ’ 1 and t. <span>Generally speaking, explaining the predictions of vector-based methods is more difficult than often as- sumed. This holds even for linear models like logistic regression. Features are often preprocessed, for example to binarize counts (Sec. 2). Furthermore, they are typically strongly correlated, making it troublesome to interpret individual coefficients [6]. Table 3 shows exemplary features weights in a logistic regression model used to predict order probabilities. If hundreds of features are utilized and are correlated and preprocessed, explaining the impact of consumer actions becomes a complex and confusing task <span>

Original toplevel document (pdf)

cannot see any pdfs