You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Once we've built a model, we analyze the distribution of its residuals = (test data predicted value - test data actual value). There are four complementary diagnostics: raw residuals, histogram, QQ, ACF (correlogram).
trentmc
changed the title
[Component name] Benefit_yyy, via building_xxx
[UX, sim] SARIMAX: 4 prediction residuals plots: raw time series, ACF, PACF, QQ
May 9, 2024
trentmc
changed the title
[UX, sim] SARIMAX: 4 prediction residuals plots: raw time series, ACF, PACF, QQ
[UX, sim] SARIMAX: Plot analytics of model prediction residuals: raw residuals, histogram, QQ, ACF (correlogram)
May 9, 2024
trentmc
changed the title
[UX, sim] SARIMAX: Plot analytics of model prediction residuals: raw residuals, histogram, QQ, ACF (correlogram)
[UX, sim] SARIMAX: Plot diagnostics of model prediction residuals: raw residuals, histogram, QQ, ACF (correlogram)
May 9, 2024
trentmc
changed the title
[UX, sim] SARIMAX: Plot diagnostics of model prediction residuals: raw residuals, histogram, QQ, ACF (correlogram)
[UX, sim] SARIMAX: Analyze model prediction sanity, via diagnostic plots of prediction residuals
May 9, 2024
trentmc
changed the title
[UX, sim] SARIMAX: Analyze model prediction sanity, via diagnostic plots of prediction residuals
[Sim, Analytics] SARIMAX: Analyze model prediction sanity, via diagnostic plots of prediction residuals
May 11, 2024
trentmc
changed the title
[Sim, Analytics] SARIMAX: Analyze model prediction sanity, via diagnostic plots of prediction residuals
[Sim plots] Analyze model prediction sanity, via diagnostic plots of prediction residuals
May 11, 2024
trentmc
changed the title
[Sim plots] Analyze model prediction sanity, via diagnostic plots of prediction residuals
[Sim plots] Analyze model prediction sanity, via ARIMA-style diagnostic plots of prediction residuals
May 11, 2024
TODOs
Background / motivation
Parent epic: #1006 "Explore SARIMAX modeling"
Once we've built a model, we analyze the distribution of its residuals = (test data predicted value - test data actual value). There are four complementary diagnostics: raw residuals, histogram, QQ, ACF (correlogram).
How: use one of:
ARIMA_model.plot_diagnostics()
(example).statsmodels.graphics.tsaplots.plot_acf
,plot_pacf
, and ?? for QQ? Example 0: neptune.aiPrototype
Examples
Example 1: Sikligar thesis
Ref - py notebook
Example 2: PSU
Ref - PSU course, lesson 03
Example 3: plot at different autocorrelation lags
Eg at lags of 1m, 2m, ..., 5m, 10m, ...
Ref ethan rosenthal.com 3 plots above "Reversible Transformations" section
Via this code
The text was updated successfully, but these errors were encountered: