Market conditions, temporal dynamics, and short-run forecasting of Thailand’s fattening hog prices: a dynamic regression approach

Fattening hog prices are important to livestock producers, food supply chains, and food-price monitoring, yet their short-run movements may reflect multiple market and temporal influences rather than contemporaneous changes in production inputs alone. This study develops an interpretable dynamic-regression framework for analyzing and forecasting Thailand’s fattening hog prices using monthly data from January 2001 to February 2026. The model incorporates upstream livestock-market and feed-related input conditions, seasonal and temporal components, dated level-shift controls, and an autoregressive disturbance process, with robust inference and recursive out-of-sample evaluation. The results show a positive and statistically significant association between piglet and fattening hog prices, while the included feed-related price variables provide limited incremental explanatory information either individually or jointly. Seasonal and temporal effects are also evident. The dated level-shift controls capture conditional price-level differences, although broader stability diagnostics do not provide sufficiently uniform evidence to interpret them as confirmed structural breaks. The significant AR(1) coefficient indicates serial dependence in unobserved influences rather than a direct lagged-price effect. Forecast performance is evaluated over March 2024–February 2026 under two information settings. When subsequently observed explanatory-variable values are supplied, the conditional dynamic regression produces substantially lower forecast errors than naïve, seasonal-naïve, and ARIMA benchmarks. Under a feasible forecast-origin information set using a transparent no-change assumption for future explanatory variables, however, the dynamic regression is competitive with naïve and ARIMA benchmarks but does not uniformly outperform them across horizons and accuracy measures. Using information available through February 2026, the model projects fattening hog prices of 56.61, 58.64, and 60.62 baht/kg for March, April, and May 2026, respectively, with widening model-based prediction intervals. The findings demonstrate the value of combining economic interpretability, explicit information-set discipline, and transparent uncertainty assessment for short-run livestock-market monitoring.

Authors

Institutions

Publication Details

Journal
Agricultural and Food Economics
Published
2026-11-18
DOI
https://doi.org/10.1186/s40100-026-00534-2
Primary Topic
Economics of Agriculture and Food Markets
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Market conditions, temporal dynamics, and short-run forecasting of Thailand’s fattening hog prices: a dynamic regression approach

Suwanna Sayruamyat, Winai Nadee, Nattaphat Wisedpanich
1 links
Agricultural and Food Economics
Economics of Agriculture and Food Markets
article

Market conditions, temporal dynamics, and short-run forecasting of Thailand’s fattening hog prices: a dynamic regression approach

Suwanna Sayruamyat, Winai Nadee, Nattaphat Wisedpanich
article en

Abstract

Fattening hog prices are important to livestock producers, food supply chains, and food-price monitoring, yet their short-run movements may reflect multiple market and temporal influences rather than contemporaneous changes in production inputs alone. This study develops an interpretable dynamic-regression framework for analyzing and forecasting Thailand’s fattening hog prices using monthly data from January 2001 to February 2026. The model incorporates upstream livestock-market and feed-related input conditions, seasonal and temporal components, dated level-shift controls, and an autoregressive disturbance process, with robust inference and recursive out-of-sample evaluation. The results show a positive and statistically significant association between piglet and fattening hog prices, while the included feed-related price variables provide limited incremental explanatory information either individually or jointly. Seasonal and temporal effects are also evident. The dated level-shift controls capture conditional price-level differences, although broader stability diagnostics do not provide sufficiently uniform evidence to interpret them as confirmed structural breaks. The significant AR(1) coefficient indicates serial dependence in unobserved influences rather than a direct lagged-price effect. Forecast performance is evaluated over March 2024–February 2026 under two information settings. When subsequently observed explanatory-variable values are supplied, the conditional dynamic regression produces substantially lower forecast errors than naïve, seasonal-naïve, and ARIMA benchmarks. Under a feasible forecast-origin information set using a transparent no-change assumption for future explanatory variables, however, the dynamic regression is competitive with naïve and ARIMA benchmarks but does not uniformly outperform them across horizons and accuracy measures. Using information available through February 2026, the model projects fattening hog prices of 56.61, 58.64, and 60.62 baht/kg for March, April, and May 2026, respectively, with widening model-based prediction intervals. The findings demonstrate the value of combining economic interpretability, explicit information-set discipline, and transparent uncertainty assessment for short-run livestock-market monitoring.

Agricultural and Food EconomicsVol. 14(1)
Thammasat University (TH), Kasetsart University (TH), Bangkok University (TH)
Zero hunger
Economics of Agriculture and Food Markets
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon