Quandires, Queries, Notes, etc. #12
Replies: 3 comments
-
Note partially to self partially to @shubhi124081. Something I've noticed while digging through some of how the Pennekamp paper did their WPE calculations is that they excluded any time-series that weren't >30 observations long with zero gaps. I'm looking into this, but this feels like an incredibly tight requirement. I'm doubly confused because they then have a different section where they add
I think the best thing to do is probably all or many of the above and then compare the results, as well as calculating some sort of like "moving average" PE that "evolves" from the beginning of the timeseries maybe? I'm imagining a plot that may be useful here is like "evolving PE is plotted on one line and then another panel with a plot that shows where the gaps are so that we could like, check to see if this is in fact fucking with our estimates. Anyways, definitely something best tackled in a meeting, but was thinking about this today so wanted to pop it here now |
Beta Was this translation helpful? Give feedback.
-
So one thing that the Pennekamp paper did is take any level of time variation (so let's say the study measured it's variable of interest every day), they made that into a "time" variable from just zero to I'm wondering if for the terrestrial example, we try a couple things:
Then we can either average across each of these independently or across all of them |
Beta Was this translation helpful? Give feedback.
-
Discussion on Feb 01, 2024
A thought for the gaps:
|
Beta Was this translation helpful? Give feedback.
-
We're talking about predictability!
We’re using Discussions as a place to:
➡️ You can convert issues to discussions either individually or bulk by labels. Looking at you, issues labeled “question” or “discussion”.
Beta Was this translation helpful? Give feedback.
All reactions