Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

nonlinear estimation #87

Open
wants to merge 616 commits into
base: main
Choose a base branch
from
Open

nonlinear estimation #87

wants to merge 616 commits into from

Conversation

thorek1
Copy link
Owner

@thorek1 thorek1 commented Jul 22, 2024

No description provided.

Thore Kockerols and others added 30 commits October 1, 2024 15:09
fix jacct
ed993af
lower tol on measurement errors, robust gradual init finding
f529a6f
add separate model and config for measurement error
0f605e8
no init but longer NUTS adaptation phase
e22650c
add ea raw data
b4462f8
@thorek1
rescale measurement error shocks
a95756c
@thorek1
reactivate init finder
b220058
use the initial params found
29c83a8
1000 adaptation steps
9e43496
gamma priors for taylor rule (avoid negative values)
988db0a
hard coded starting values
e5c2ac6
@thorek1
todos estimation
737e3e3
@thorek1
add no labor option for estim
5a99e95
carry over found params only if LLH is finite, same for sampler init
b0f18c3
more robust mat mul and fact
f7f75aa
constelab also in case of dlabobs
1177527
eplicit inits
762e28c
early return inf if not solved for 1st,2nd,3rd order sols
ffa8d7b
verbose error messages during solve process
0439ee1
verbosity in the filters
3ea94ba
NSSS early termination, count func and grad calls, verbose option
51bbde9
@thorek1
fix type instability
f37f6dc
@thorek1
fix type instability
50a35ec
@thorek1
fix forward diff errors in get NSSS
94c463a
@thorek1
try warm start with both GN and LM before starting points
eed3a53
init params that work for EA 2nd order
6344995
Merge branch 'nonlinear-estimation' of https://github.com/thorek1/Mac…
7d1dfa2 
…roModelling.jl into nonlinear-estimation
@thorek1
back to only gauss newton. check whether that fixes test errors
318fa50
callback, init params and sections
def8739
no print in callback
f70c9c0
Thore Kockerols and others added 30 commits November 6, 2024 11:50
fix higher order estim
3cb4450
update neural net solution
b7b5209
fix tol for third order estim
fd925fe
@thorek1
lwoer tol on find shocks
c04d8bf
@thorek1
report errors on matrix equations (debug estim)
9ed78a0
@thorek1
different tol handling on mat eqs
e4cd20e
@thorek1
fix solved in sylvester
0f2f2d2
default schur solvers for qme
31057a5
no showing of error, lower qme tol
3e9d63e
capture potentially failing matrix inversion in higher order pert sol
c1ebea6
put homothopy continuation back in place
310e6ec
homotopy continuation approx to sol
ebde380
no shocks message
5ab5bb7
1/3 back 1/2 forward when trying to find SS
3ee8940
comments on other things to try
35888dc
@thorek1
multi macro works
b7e5e55
@thorek1
Merge branch 'nonlinear-estimation' of https://github.com/thorek1/Mac…
fd40011 
…roModelling.jl into nonlinear-estimation
@thorek1
minor typos
7a8d1ff
@thorek1
parses equations correctly but bunches them together in blocks
4d492fd
@thorek1
flattening equations solved it. multi-country-sector model parses
d041cd7
@thorek1
first attempt NK multi model
6a766a8
@thorek1
fix bug in model
0719b88
@thorek1
check stst nk mult
fb8ec6b
run it only once if finding the stst the first time
5ca3ea5
adjust SA
af1f720
@thorek1
update todo on neural net
c124f8e
nk multisector works
0a9ee8f
Merge branch 'nonlinear-estimation' of https://github.com/thorek1/Mac…
528f623 
…roModelling.jl into nonlinear-estimation
include other parameter set for NL solver to find SS in multicountry …
58163b7 
…model
multicountry model attempt
3d14a90
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@thorek1