A study compares mean-squared forecast error (MSFE) for sector-specific financial-liquidity-preference (FLP) and job vacancy rate models across one-quarter to one-year horizons. Models integrating earnings-call indicators with FLPs show lower MSFE than earnings-call-only benchmarks, particularly at longer horizons (H=4). Sectoral FLP additions to earnings-call data reduce MSFE for manufacturing and services vacancy rates, with strongest gains at H=3 and H=4. Figures C4 and C5 use color-coded bars (yellow/green for manufacturing, blue/turquoise for services) to scale MSFE by 100 for horizons H=1–4. Table C5 reports MSFE for aggregate and sectoral vacancy rates, showing the full model (FLP, UR, and EC) has lowest errors. FLP combined with sector-specific economic conditions outperforms FLP alone but lags the full model. Diebold–Mariano tests confirm significant improvements for the full model over alternatives. Results are presented for post-COVID and full samples, separately for manufacturing and services.
© European Central Bank, 2025.
Summary derived from the ECB website (https://www.ecb.europa.eu ).
Made by AI. If you spot anything of concern write us at contact@cybach.com. We’ll promptly correct irregularities.