Ryan Batten, PhD(c)
@ryanbatten.bsky.social
- Biostatistician by trade
- PhD candidate in Clinical Epidemiology at Memorial University
- Love statistics & R!
- Area of expertise: causal inference using real-world data
Blog: www.causallycurious.com
- PhD candidate in Clinical Epidemiology at Memorial University
- Love statistics & R!
- Area of expertise: causal inference using real-world data
Blog: www.causallycurious.com
For example, say we have propensity scores for both groups. However there is a lack of overlap.
We decide to focus on the area where there is overlap.
We do this by applying overlap weights.
The population these results apply to would be the overlap population!
2/2
We decide to focus on the area where there is overlap.
We do this by applying overlap weights.
The population these results apply to would be the overlap population!
2/2
December 18, 2024 at 5:51 PM
For example, say we have propensity scores for both groups. However there is a lack of overlap.
We decide to focus on the area where there is overlap.
We do this by applying overlap weights.
The population these results apply to would be the overlap population!
2/2
We decide to focus on the area where there is overlap.
We do this by applying overlap weights.
The population these results apply to would be the overlap population!
2/2
ggplot2 is like electricity. I don't need it to survive, but I much prefer it
December 14, 2024 at 6:10 PM
ggplot2 is like electricity. I don't need it to survive, but I much prefer it
Don't think this is the paper you're referencing but there's one from Sander Greenland (2021) talking about non-collapsibility (aka why using marginal effects for certain measures gives a different result than conditional effects)
Paper: www.jclinepi.com/article/S089...
Paper: www.jclinepi.com/article/S089...
Noncollapsibility, confounding, and sparse-data bias. Part 1: The oddities of odds
To prevent statistical misinterpretations, it has long been advised to focus on estimation instead of statistical testing. This sound advice brings with it the need to choose the outcome and effect measures on which to focus. Measures based on odds or their logarithms have often been promoted due to their pleasing statistical properties, but have an undesirable property for risk summarization and communication: Noncollapsibility, defined as a failure of the measure when taken on a group to equal a simple average of the measure when taken on the group's members or subgroups.
www.jclinepi.com
December 12, 2024 at 7:39 PM
Don't think this is the paper you're referencing but there's one from Sander Greenland (2021) talking about non-collapsibility (aka why using marginal effects for certain measures gives a different result than conditional effects)
Paper: www.jclinepi.com/article/S089...
Paper: www.jclinepi.com/article/S089...
Fantastic to see simulation on the list! After learning how to use simulations, use them almost every day
December 11, 2024 at 2:11 AM
Fantastic to see simulation on the list! After learning how to use simulations, use them almost every day
For IPTW which causal estimand was it? If it was ATE, then it's estimating something different from PSM.
The causal estimand impacts several area. It's important to keep in mind.
PS: There are four estimands:
- ATE
- ATT
- ATU
- ATO
3/3
The causal estimand impacts several area. It's important to keep in mind.
PS: There are four estimands:
- ATE
- ATT
- ATU
- ATO
3/3
December 9, 2024 at 6:43 PM
For IPTW which causal estimand was it? If it was ATE, then it's estimating something different from PSM.
The causal estimand impacts several area. It's important to keep in mind.
PS: There are four estimands:
- ATE
- ATT
- ATU
- ATO
3/3
The causal estimand impacts several area. It's important to keep in mind.
PS: There are four estimands:
- ATE
- ATT
- ATU
- ATO
3/3
- Inverse Probability of Treatment Weighting (IPTW)
- Propensity Score Matching (PSM)
We simulate some data and choose the metrics to evaluate them.
Then we compare the methods.
We decide that one is better than the other.
That may be true...but did they estimate the same thing?
2/3
- Propensity Score Matching (PSM)
We simulate some data and choose the metrics to evaluate them.
Then we compare the methods.
We decide that one is better than the other.
That may be true...but did they estimate the same thing?
2/3
December 9, 2024 at 6:43 PM
- Inverse Probability of Treatment Weighting (IPTW)
- Propensity Score Matching (PSM)
We simulate some data and choose the metrics to evaluate them.
Then we compare the methods.
We decide that one is better than the other.
That may be true...but did they estimate the same thing?
2/3
- Propensity Score Matching (PSM)
We simulate some data and choose the metrics to evaluate them.
Then we compare the methods.
We decide that one is better than the other.
That may be true...but did they estimate the same thing?
2/3
I find the same thing! One area where its helpful is condensing emails (when possible)
December 8, 2024 at 9:50 PM
I find the same thing! One area where its helpful is condensing emails (when possible)
My take:
A frequentist approach assumes there is a fixed value. Take y = mx+b. A frequentist view assumes m is fixed.
A determinist view would be similar, assuming there is a fixed set of values.
(no refs, but interested in any you find!)
A frequentist approach assumes there is a fixed value. Take y = mx+b. A frequentist view assumes m is fixed.
A determinist view would be similar, assuming there is a fixed set of values.
(no refs, but interested in any you find!)
December 8, 2024 at 4:27 PM
My take:
A frequentist approach assumes there is a fixed value. Take y = mx+b. A frequentist view assumes m is fixed.
A determinist view would be similar, assuming there is a fixed set of values.
(no refs, but interested in any you find!)
A frequentist approach assumes there is a fixed value. Take y = mx+b. A frequentist view assumes m is fixed.
A determinist view would be similar, assuming there is a fixed set of values.
(no refs, but interested in any you find!)
I find the same thing! One solution I'm exploring is to take a previous LinkedIn post and get ChatGPT to condense.
Have to edit it, but helpful as a starting point!
Have to edit it, but helpful as a starting point!
December 6, 2024 at 3:11 PM
I find the same thing! One solution I'm exploring is to take a previous LinkedIn post and get ChatGPT to condense.
Have to edit it, but helpful as a starting point!
Have to edit it, but helpful as a starting point!
Code for plot: gist.github.com/battenr/e6f5...
Nominal Coverage for GLM
Nominal Coverage for GLM . GitHub Gist: instantly share code, notes, and snippets.
gist.github.com
December 6, 2024 at 3:10 PM
Code for plot: gist.github.com/battenr/e6f5...