About

Oral 'Jug' Capps, Jr. is an Executive Professor and Regents Professor in the Department of Agricultural Economics at Texas A&M University, where he also holds the Southwest Dairy Marketing Endowed Chair and serves as Co-Director of the Agribusiness, Food, and Consumer Economics Research Center (AFCERC). His educational background includes a B.S. in Mathematics, an M.S. in Agricultural Economics, an M.S. in Statistics, and a Ph.D. in Agricultural Economics, all from Virginia Tech. Dr. Capps has a distinguished career focused on research related to consumer demand issues, applied econometrics, scanner data analysis, food labeling, health and nutrition impacts on consumer behavior, and the evaluation of commodity advertising and promotion programs. He is recognized for his rigorous, theory-based econometric methodology and applications, and he laid the foundation for data-intensive food demand research approaches. His work has significantly contributed to understanding expenditure patterns, food demand impacts of health information, and the effects of mergers and acquisitions in the food sector. Dr. Capps has authored numerous publications, including 173 refereed journal articles and six books, and has been awarded for research, teaching, mentoring, and professional service. He is also a co-founder and managing partner of Forecasting and Business Analytics, LLC, a consulting firm specializing in quantitative methods for economic problems. His contributions to the field have been recognized through various leadership roles, including past presidencies of the Southern Agricultural Economics Association and the Food Distribution Research Society, and he was named a Fellow by the Agricultural and Applied Economics Association in July 2024. His research is highly cited, ranking in the top percentages globally according to RePEc/IDEAS rankings, and he has secured substantial funding through contracts and grants.

Research topics

• Agricultural economics
• Economics
• Geography
• Mathematics
• Microeconomics
• Food science
• Forestry
• Demographic economics
• Demography
• Labour economics
• Marketing
• Business
• Econometrics
• Engineering

Selected publications

• Application of Resolution Regression and Resolution Graphs in Evaluating Probability Forecasts Generated Using Binary Choice Models

  Econometrics · 2026-02-24

  articleOpen accessSenior author

  Binary choice models are widely used in econometric modeling when the dependent variable corresponds to discrete outcomes. With appropriate decision rules, these models provide predictions of binary choices generated from predicted probabilities. The accuracy of these predictions in terms of classifying probabilities to events that occurred versus those that did not is a key issue. The use of expectation-prediction success at present is the standard method used to assess the accuracy of these predictions. However, this method is limited in its ability to correctly classify probabilities in the absence of appropriate predetermined cut-off levels. We propose alternative methods to classify probabilities generated through binary choice models, namely resolution graphs and resolution regressions that measure the ability to sort predicted probabilities against observed outcomes. Using probabilities generated from the use of logit models applied to purchasing decisions of various non-alcoholic beverages made by U.S. households, we compare probability sorting power using expectation-prediction success as well as resolution graphs and resolution regressions. Based on expectation-prediction success, the logit models performed better at classifying outcomes related to purchasing isotonic drinks, regular soft drinks, diet drinks, bottled water, and tea. Based on resolution regressions, the null hypothesis of perfect sorting of probabilities was rejected for all non-alcoholic beverages. Although the logit models generated upward-sloping resolution graphs as expected, they were relatively flat compared to the 45-degree perfect sorting line. Going forward, we recommend using resolution regression and resolution graphs to capture sorting of probabilities in addition to the conventional metrics used in ascertaining the ability of binary choice models to predict out-of-sample behavior.

  PublisherOA PDFDOI

• Unit Value Imputation Methods Using Household Scanner Data: A Case Study of Milk Purchases

  Journal of Agricultural and Applied Economics · 2025-05-14

  articleOpen accessSenior authorCorresponding

  Abstract We compared three common unit value imputation methods using household purchase data from 2018 to 2020 concerning five milk categories. Regression-based imputation outperformed household mean and retailer mean imputations, based on root mean squared error, mean absolute error, and mean absolute percent error. In a censored QUAIDS model, retailer mean imputation yielded statistically different estimates from the other two methods concerning compensated own-price and cross-price elasticities. We demonstrated that different price imputation methods used in household demand estimation generate different results in predicted prices and estimated price elasticities, and these differences may not necessarily be trivial.

  PublisherOA PDFDOI

• A short-run analysis of the impact of imports of Hass avocados from Mexico on the U.S. avocado industry

  The International Food and Agribusiness Management Review · 2025-02-04

  articleOpen access1st authorCorresponding

  Abstract Using data from November 2011 to March 2022, we estimate a vector autoregression model to examine the relationship among Mexican Hass avocado imports, prices received, and volumes of Californian Hass avocados packed by California packers/handlers. We trace the impacts of changes in Mexican imports over a 12-month time horizon. A 1% increase in Mexican imports today leads to increases in pack prices of 0.21% and to decreases in pack volumes of 0.29% on average five months to twelve months later. The cumulative impact of a 1% increase in Mexican imports results in a 1.71% increase in pack prices and a 2.31% decrease in monthly pack volumes, translating to a 0.64% decline in monthly revenue accruing to California packers/handlers. Consequently, the modest rise in pack prices coupled with the modest shrinkage of volumes of Californian Hass avocados packed and the modest loss in revenue accruing to California packers/handlers suggest on the surface that Hass avocado imports from Mexico in the short run do not “seriously injure” the U.S. avocado industry. These findings also suggest that future U.S. avocado grower appeals for relief against imports from Mexico are not likely be upheld by the U.S. International Trade Commission. Our results are short term only and these effects, compounded over time, potentially may become injurious to producers and packers in California.

  PublisherDOI

• The role of the expanded food and nutrition education program in improving healthy eating index scores for low-income households in selected counties in Texas

  PLoS ONE · 2025-05-02

  articleOpen access1st authorCorresponding

  The Expanded Food and Nutrition Education Program (EFNEP) is a federal initiative aimed at improving the dietary behaviors and nutrition knowledge of low-income households. This study evaluates the impact of Texas EFNEP on the dietary quality of participants using data from across ten counties over four fiscal years (2019-2022). Dietary quality was assessed using the Healthy Eating Index-2015 (HEI), calculated from 24-hour dietary recalls collected before and after participation in the program. The study analyzed changes of HEI scores across fiscal years, counties, socio-demographic characteristics, and public assistance program participation. The Texas EFNEP intervention resulted in a statistically significant improvement in overall HEI scores, 4.23 on average. The greatest dietary improvements were noted in Tarrant and Hidalgo counties. Among racial groups, participants identified as Asian showed the most improvement on average, followed by participants identified as white and as black. On average, Hispanic participants experienced greater dietary improvements than non-Hispanic participants. Based on regression analysis, geographic location and participation in public assistance programs such as the Child Nutrition Program (CNP) significantly impacted total HEI scores, but age, income, and hours taught in EFNEP were not statistically significant determinants. Statistically significant improvements were detected in eight of the nine adequacy components of the HEI, including total fruit, whole grains, and dairy. Concerning the moderation components, statistically significant changes were evident for refined grains, added sugar, and saturated fat. However, the program was less effective in moderating sodium intake, a known dietary challenge in low-income populations. The findings suggest that the Texas EFNEP contributed to improvements in overall dietary quality, including enhancements in both adequacy and moderation components of the Healthy Eating Index. These findings are consistent with prior research concerning the effectiveness of EFNEP studied in other states and regions.

  PublisherDOI

• The effect of immigration policy regime change on state-level participation rates of the special supplemental nutrition program for women, infants, and children in the United States

  Food Security · 2024-10-07 · 1 citations

  articleOpen accessSenior authorCorresponding

  Abstract The change in immigration policy in state-level participation rates of the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) in the United States by citizenship and ethnicity was estimated over the period 2013-2018 using the Triple Difference estimate method. The principal finding was that the state-level WIC participation rate for Hispanic non-citizens was lower by 8.6% relative to all other groups (Hispanic citizens, non-Hispanic citizens, and non-Hispanic non-citizens). This study then not only provides quantitative evidence concerning the ongoing debate about the impact of the immigration policy changes under the Trump administration but also extends the extant literature by estimating the causal effects of immigration policy regime change on WIC participation of non-citizens.

  PublisherOA PDFDOI

• A Micro-perspective Analysis of the Demand for Greek and Non-Greek Yogurt in the United States Over Calendar Years 2018 to 2020

  Journal of Agricultural and Applied Economics · 2024-05-01 · 1 citations

  articleOpen access1st authorCorresponding

  Abstract Using the Heckman framework, we develop profiles of households who purchase Greek yogurt and non-Greek yogurt and estimate own-price, cross-price, and income elasticities of demand. Attention is centered on the impacts of age, race, education, and ethnicity of the household head, household income, household size, region, the presence of children, and prices of Greek yogurt and non-Greek yogurt. This analysis rests on data acquired from Nielsen pertaining to 164,484 households over calendar years 2018–2020. Own-price elasticities are estimated to be −1.36 for Greek yogurt and −0.70 for non-Greek yogurt. Additionally, these yogurt products are not only substitutes but also necessities.

  PublisherOA PDFDOI

• US household demand system analysis for dairy milk products and plant‐based milk alternatives

  Journal of the Agricultural and Applied Economics Association · 2024-10-01 · 5 citations

  articleOpen access1st authorCorresponding

  Abstract Using the QUAIDS model, we analyze interrelationships among dairy milk and plant‐based milk alternatives (PBMA) for US households from 2018 to 2020 using NielsenIQ. We adopt the Shonkwiler–Yen methodology to account for censored observations. PBMA demand is inelastic, while milk products show elastic demand. PBMA substitutes for traditional white milk and organic milk. Traditional flavored milk and PBMA as well as lactose‐free and organic milk are complements. PBMA and lactose‐free milk are independent goods. Demographic factors like income, household size, and education significantly affect budget share, alongside women, infants, and children participation and the pandemic.

  PublisherOA PDFDOI

• Habitual behavior of household food expenditure by store type in the United States

  PLoS ONE · 2023-09-08 · 1 citations

  articleOpen accessSenior authorCorresponding

  We examine how socio-demographic factors, spending habits, and characteristics of the retail food environment affect household expenditure across all food and beverage categories by store outlet in the United States. The six outlets considered are grocery stores, convenience stores, discount stores, club stores, drug stores, and dollar stores. The source of data for this analysis is the Nielsen Homescan Panel over the period between 2011 and 2015. We employ a dynamic correlated random effect Tobit model to incorporate habitual purchasing behavior as well as a novel method to deal with zero observations using the inverse hyperbolic sine transformation. The results suggest that habitual spending behavior undoubtedly is a key factor in affecting food and beverage expenditures across all store outlets. Additionally, household size, age, urbanization, education, race, ethnicity, and region are drivers of household food and beverage expenditures across the six store outlets.

  PublisherOA PDFDOI

• On the robustness/replication of econometric analyses from nonlinear models using various commonplace software packages

  Applied Economic Perspectives and Policy · 2023-04-25 · 1 citations

  articleOpen access1st authorCorresponding

  Abstract Because replicability is an important part of every scientific endeavor, this research deals with comparing and contrasting parameter estimates, standard errors, and p‐values from the estimation of five commonly encountered nonlinear models in applied econometrics. Commonplace software packages indigenous to econometrics and statistics are used, namely EVIEWS 11.0, SAS 9.4, Stata 17, and R 4.1.2 in five replication exercises to determine potential differences, if any, in empirical results. The hypothesis that mainstream software packages generate different empirical results in the estimation of nonlinear models is confirmed for the polynomial distributed lag (PDL) model and the GARCH(1,1) model. For the probit model and the Barten synthetic demand system model, the differences in parameter estimates, standard errors, and p ‐values are less evident across the four commonly used software packages. For the Tobit model, the respective sets of parameter estimates, standard errors, and p ‐values are nearly identical across the respective software packages. Economic analysts should not just accept estimation results uncritically, but instead, conduct sensitivity analyses involving the use of at least two software packages. The agricultural economics profession should adopt this recommendation as standard practice.

  PublisherOA PDFDOI

• A household-level demand system analysis of nuts in the United States

  Agricultural and Resource Economics Review · 2022 · 10 citations

  • Economics
  • Agricultural economics
  • Econometrics

  Abstract An Exact Affine Stone Index demand model is estimated to analyze the household-level demand for nine nut products (peanuts, pecans, almonds, cashews, walnuts, pistachios, mixed nuts, macadamia nuts, and other nuts) in the United States using Nielsen Homescan panel data from 2009 through 2015. The demands for all nuts are elastic. All nut products are necessities and substitutes for each other. Household sociodemographic characteristics are statistically significant drivers of the demand for nut products. Finally, the effects of changes in the magnitude of selected promotion expenditure elasticities for nuts are simulated to determine their impacts on prices and quantities demanded.

  PublisherOA PDFDOI

Frequent coauthors

• Senarath Dharmasena

  Texas A&M University

  101 shared

• Gary W. Williams

  European Bioinformatics Institute

  69 shared

• Rodolfo M. Nayga

  Agricultural & Applied Economics Association

  48 shared

• Robert E. Branson

  37 shared

• Daniel Moin

  Mitchell Institute

  36 shared

• Ann Wilkinson

  Commonwealth Scientific and Industrial Research Organisation

  36 shared

• Mario F. Crisostomo

  Kansas State University

  36 shared

• Robert O. Burton

  36 shared

Education

• B.S., Mathematics

  Virginia Tech

• M.S., Agricultural Economics

  Virginia Tech

• M.S., Statistics

  Virginia Tech

• Ph.D., Agricultural Economics

  Virginia Tech

Awards & honors

• Fellow by the Agricultural and Applied Economics Association…