Global Persistence, Local Residual Structure: Forecasting Heterogeneous Investment Panels
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915977811197952 |
|---|---|
| author | Roshka, Oleg |
| author_facet | Roshka, Oleg |
| contents | On a 93-actor quarterly panel mixing macro indicators, institutional data, and firm-level investment ratios, global factor augmentation degrades prediction for actor subgroups whose dynamics are misrepresented by the shared basis. A two-stage architecture -- global pooled AR(1) for shared persistence, block-specific local models for residual dynamics -- improves full-panel out-of-sample $R^2$ from 0.630 to 0.677 ($Δ= +0.047$, CI $[+0.036, +0.058]$, 10/10 windows, placebo $p \leq 0.001$). A held-out decade test (block partition frozen on 2005--2014 data, evaluated on unseen 2015--2024 windows) confirms the gain ($Δ= +0.050$, 10/10), and a stratified placebo that fixes the macro/firm data-type split and permutes only firm-sector assignments corroborates ($z = 7.25$, $p \leq 0.001$). Cross-regime replication on a 109-actor UK/EU heterogeneous panel ($Δ= +0.017$, 8/8 windows) and a combined US + UK/EU panel of 202 actors ($Δ= +0.030$, placebo $z = 9.68$ -- exceeding the original US-only $z = 7.82$) confirms the architecture transfers across regimes. A 146-firm CapEx/Assets robustness check refines the scope condition: the gain depends on cross-sectional dispersion in autoregressive structure, which data-type heterogeneity reliably produces but which is also present in firm-only panels under suitable ratio choices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09821 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Global Persistence, Local Residual Structure: Forecasting Heterogeneous Investment Panels Roshka, Oleg Econometrics Portfolio Management Statistical Finance 62M10, 62P20, 62P05, 62H25 On a 93-actor quarterly panel mixing macro indicators, institutional data, and firm-level investment ratios, global factor augmentation degrades prediction for actor subgroups whose dynamics are misrepresented by the shared basis. A two-stage architecture -- global pooled AR(1) for shared persistence, block-specific local models for residual dynamics -- improves full-panel out-of-sample $R^2$ from 0.630 to 0.677 ($Δ= +0.047$, CI $[+0.036, +0.058]$, 10/10 windows, placebo $p \leq 0.001$). A held-out decade test (block partition frozen on 2005--2014 data, evaluated on unseen 2015--2024 windows) confirms the gain ($Δ= +0.050$, 10/10), and a stratified placebo that fixes the macro/firm data-type split and permutes only firm-sector assignments corroborates ($z = 7.25$, $p \leq 0.001$). Cross-regime replication on a 109-actor UK/EU heterogeneous panel ($Δ= +0.017$, 8/8 windows) and a combined US + UK/EU panel of 202 actors ($Δ= +0.030$, placebo $z = 9.68$ -- exceeding the original US-only $z = 7.82$) confirms the architecture transfers across regimes. A 146-firm CapEx/Assets robustness check refines the scope condition: the gain depends on cross-sectional dispersion in autoregressive structure, which data-type heterogeneity reliably produces but which is also present in firm-only panels under suitable ratio choices. |
| title | Global Persistence, Local Residual Structure: Forecasting Heterogeneous Investment Panels |
| topic | Econometrics Portfolio Management Statistical Finance 62M10, 62P20, 62P05, 62H25 |
| url | https://arxiv.org/abs/2604.09821 |