Establishment level manufacturing data are gathered from several countries around the world. These datasets are gathered by the Census Bureau of the respective countries and is an exhaustive Census of all establishments in some years. For example the U.S. Census Bureau performs a full Census of all manufacturing establishments in years ending in 2 and 7 and performs a survey sampling only 15 percent of establishments in other years.

This talk will be structured around three topics regarding census manufacturing datasets. First we will describe model development, estimation, and data challenges related to analyzing these datasets. Second, we propose a framework using the actual dataset to determine the best functional estimation method in contrast to the standard framework of Monte Carlo simulation. The results from our framework provide insights regarding the appropriate survey sizes needed in non-census years. Third, we will describe results from analyzing Japanese and Chilean data and will discuss future questions to investigate for these and other countries.

Healthcare costs are higher in the U.S. then anywhere else in the world. A significant portion of the costs are generated in hospitals. We investigate both the efficiency and the effectiveness of U.S. community hospitals using the Agency for Healthcare Research and Quality’s Healthcare Cost and Utilization Project 2009-2011 Nationwide Inpatient Sample, a data set which contains all discharges from an approximate 20% sample of hospitals.

Here efficiency is the productivity of the hospital measured relative to the most productive hospitals and effectiveness is how closely the hospital produced relative to the forecasted services needed. We find the effectiveness levels are slightly higher than the efficiency levels in both 2010 and 2011 indicating that hospitals are producing closer to the forecasted level than the actual service level needed. Further, both efficiency and effectiveness levels are low indicating a large variability in the level of resources hospitals use to provide the same set of services. The low effectiveness scores indicate that many hospitals have a high level of resources even relative to the forecasted demand providing some evidence for a medical arms race.

This paper proposes a unifying model and estimator we call Shape Constrained Kernel-weighted Least Squares (SCKLS). We show the relationship between the SCKLS estimator and both the Convex Nonparametric Least Squares (CNLS) and Du’s estimators. Specifically, the SCKLS estimator converges to the CNLS estimator as the bandwidth goes to zero. We compare the performance of the three estimators (SCKLS, CNLS, and Du’s estimator) via Monte Carlo simulations.

The Finnish electricity market has a competitive energy generation market and a monopolistic transmission system. To regulate the local monopoly power of network operators, the government regulator uses frontier estimation methods. We describe the new regulatory system developed for the Finnish regulator, which is based on the method Stochastic semi-Nonparametric Envelopment of Data (StoNED) and utilizes panel data to detect the excessive costs from random noise.

This presentation describes the graduate and undergraduate material handling course taught at Texas A&M. Particular emphasis is given to the content description and the case study project that pairs 2 undergraduate and 2 graduate students in teams to participate in MHI’s case study competition.

Presentation

This presentation describes some common research topics in industrial engineering and operations research. It focuses on the Department of Industrial and Systems Engineering at Texas A&M University and my laboratory. Its purposes is to further the understanding between Osaka University and Texas A&M.

Presentation

This presentation was given at the European Workshop for Efficiency and Productivity Analysis (EWEPA XIV) as the plenary talk, June 16, 2015 in Helsinki Finland. I focus on the benefits of shape constraints to improve the finite sample performance of nonparametric estimators. Existing estimators and new estimators are presented that combine kernel smoothing techniques with axiomatic functional estimation.

EWEPAPlenary5

The College Industry Council on Material Handling Education (CICMHE) is a group of 15 academic and 8 industry members that work to increase awareness, understanding, exploration, and development of material handling and logistics through projects and events.

CICMHE meet in San Diego as part of the MHI‘s annual conference. The two-day event resulted in a set of projects MHI will fund to promote material handling and logistics education along with allowing considering progress on planning the upcoming events for CICMHE such as Promat.

Bayesian StoNED or Multi-variate Bayesian Convex Regression with inefficiency: Two sides of the same coin.

Bayesian methods allow researchers to simulate regression models to investigate the effects of prior distributional assumptions and modeling restrictions on posterior estimates of model parameters. Here we try to develop a Bayesian version of Stochastic Nonparametric Envelopment of Data (StoNED). There are strong similarities between StoNED and Multi-variate Bayesian Convex Regression (MBCR) proposed by Hannah and Dunson (2013). This talk describes some of these similarities along with some computational results regarding problem size and accuracy of the estimated parameters. We propose an MBCR model with an inefficiency term as a Bayesian StoNED equivalent.

http://www.nomepre.net/index.php/workshops/114-6th-hewepa-workshop-on-25th-september-2014