Browsing by Author "Tang, Xiaoxu"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Comparative Housing Market Analysis: Minnetonka and Surrounding Communities(Resilient Communities Project (RCP), University of Minnesota, 2012) Huonder, Mark; King, Eric; Knoblauch, Katie; Tang, XiaoxuThis project was completed as part of the 2012-2013 Resilient Communities Project (rcp.umn.edu) partnership with the City of Minnetonka. Homes in Minnetonka are more expensive on average than homes in surrounding communities, and the City was interested in the potential "market leakage"--that is, purchasers looking to buy a home in the Minnetonka area but ultimately choosing to buy in a neighboring community--for mid-priced housing. Minnetonka project lead and community development supervisor Elise Durbin worked with students in HSG 5464: Understanding Housing Assessment and Analysis, to determine the mid-priced housing market for Minnetonka, as well as the neighboring communities of St. Louis Park, Hopkins, Plymouth, and Eden Prairie. Their analysis showed that Minnetonka lacks smaller, low-priced housing in comparison to surrounding communities. The students' final report and presentation are available.Item Optimizing Automatic Traffic Recorders Network in Minnesota(Minnesota Department of Transportation, 2016-01) Gupta, Diwakar; Tang, XiaoxuAccurate traffic counts are important for budgeting, traffic planning, and roadway design. With thousands of centerline miles of roadways, it is not possible to install continuous counters at all locations of interest (e.g., intersections). Therefore, at the vast majority of locations, MnDOT samples axle counts for short durations, called portable traffic recorder (PTR) sites, and obtains continuous counts from a small number of strategically important locations. The continuous-count data is leveraged to convert short-duration axle counts into average-annual-daily- traffic counts. This requires estimation of seasonal adjustment factors (SAFs) and axle correction factors at short- count locations. This project focused on developing a method for estimating SAFs for PTR sites. The continuous- count data was grouped into a small number of groups based on seasonal traffic-volume patterns. Traffic patterns at PTR sites were hypothesized by polling professional opinions and then verified by performing statistical tests. PTRs with matching seasonal patterns inherited SAFs from the corresponding continuous-count locations. Researchers developed a survey tool, based on the analytic hierarchy process, to elicit professional judgments. MnDOT staff tested this tool. The statistical testing approach was based on bootstrapping and computer simulation. It was tested using simulated data. The results of this analysis show that in the majority of cases, three weekly samples, one in each of the three seasons, will suffice to reliably estimate traffic patterns. Data could be collected over several years to fit MnDOT’s available resources. Sites that require many weeks of data (say, more than five) may be candidates for installation of continuous counters.Item Provider Payment Innovations And Care Improvement In Healthcare(2018-09) Tang, XiaoxuHealthcare reform has been the center of academic discussion in recent years. Payment innovation, by aligning the incentives of all heathcare providers, plays an important role in improving the quality of care with a lower cost. The three essays in this dissertation study different aspects of the healthcare payment innovation and care improvement policies. The first essay studies the hospital-physician gainsharing contracts. The Centers for Medicare and Medicaid Services (CMS) has introduced several Episode-based Payment Models (EPMs). Each EPM concerns a particular medical condition and a combination of pre-acute, acute and post-acute services. CMS pays the hospital and physicians participating in that EPM on a fee-for-service basis. These payments are reconciled against a target price, resulting in either a gain or loss to the hospital. The hospital may also have gains or losses from its internal operations. It may incentivize physicians to select a treatment modality that will improve quality and reduce costs by offering to share gains and losses. CMS has placed restrictions on what gains or losses may be shared and implemented stop loss and gain provisions (SLSG) for the hospital and the physicians, which affect the physicians' choice of treatment modalities. In this work, we consider a class of linear gainsharing functions that calculate a physician's per-episode share based on both the aggregate performance across all physicians, and the cost and quality outcomes achieved by that physician. In one of our models, the physicians may be heterogeneous in terms of their practice volumes and risk preferences. We show that when there are no SLSG provisions, an optimal gainsharing function lies in the class of linear functions. When there are SLSG constraints, we perform a series of numerical experiments, which reveal that the hospital SLSG provisions, the maximum savings potential, and the hospital's risk preferences primarily determine physicians' incentives for choosing certain treatment modalities. In the second essay, we use a large-scale proprietary dataset to study follow-up appointments in outpatient clinics. We propose methodologies to tag episodes of care and measure continuity of care and appointment-slot spoilage (unrebooked cancellation or no-show). We find that same-day booked follow-up (SDFU) appointments (those booked on the day the prior appointment occurred) have greater continuity of care and higher spoilage rate while controlling for a variety of patient, physician, and clinic characteristics. We construct econometric models to rigorously establish the relationships of SDFU with respect to same-doctor match and appointment slot spoilage. We develop a model selection algorithm to cycle through an exhaustive list of all variable combinations (each variable combination is referred to as a model) and select the model with the best quality (as measured by Akaike information criterion). It is shown that the SDFU indicator remains in each of the finally selected same-doctor match and the spoilage models with a highly significant and relatively sizable coefficient. The statistical evidence confirms the intuition that SDFUs are more likely to secure seeing the same doctor but at the sametime result in appointment spoilage. We then conduct testing of various model assumptions around linearity, multicollinearity, link function, and endogeneity to verify the robustness of the identified statistical relationships. Counterfactual analysis is performed to evaluate SDFU appointments as a strategy for managing follow-ups. In the third essay, we study how to manage returning customers in an appointment-based slotted-service queue with the goal of maximizing service volume. Returning customers prefer to be served by the same server that they visited in their previous visit. Applications of this model include a whole host of medical clinics, and lawyers, councillors, tutors, and government officials who deal with the public. We consider a simple strategy that a service provider may use to reduce balking among returning customers -- designate some returning customers as high-priority customers. These customers are placed at the head of the queue when they call for a follow-up appointment. In an appointment based system, this policy can be implemented by booking a high-priority returning customer's appointment right before the customer leaves the service facility. We focus on a need-based policy in which the decision to prioritize some customers depends on their return probability. We analyze two systems, one in which the size of the waiting room is limited, and another in which it is not. We show that with limited waiting-room, a service system should not prioritize some returning customers in order to maximize the throughput rate. However, it is always optimal to prioritize some customers in the system with no limit on the waiting room. In those systems, we prove that the throughput rate is a quasi-concave function of the threshold under the assumption that returning customers see time averages (RTA). These findings will allow service systems to determine optimal operating policies that are both easy to implement and provably optimal. The three essays are written as three self-contained chapters, each with its own motivation, analysis, and conclusions. While they each focuses on a different topic, the common theme is to establish evidence as well as design and analyze mechanisms that would improve the quality and efficiency of healthcare. The research work documented in this dissertation contributes theoretically and empirically to the literature, has practical policy implications, and sets the stage for future research.Item Weigh-in-Motion Sensor and Controller Operation and Performance Comparison(Minnesota Department of Transportation, 2018-01) Gupta, Diwakar; Tang, Xiaoxu; Yuan, LuThis research project utilized statistical inference and comparison techniques to compare the performance of different Weigh-in-Motion (WIM) sensors. First, we analyzed test-vehicle data to perform an accuracy check of the results reported by the sensor-vendor Intercomp. The results reported by Intercomp mostly matched with our own analysis, but the data were found to be insufficient to reach any conclusions about the accuracy of the sensor under different temperature and speed conditions. Second, based on the limited data from the Intercomp and IRD sensor systems, we performed tests of self-consistency and comparisons of measurements to inform the selection of a superior system. Intercomp sensor data were found to be not self-consistent but IRD data were. Given the different measurements provided by the two sensors, without additional data, we were not able to reach a conclusion regarding the relative accuracy or the duration of consistent observations before needing recalibration. Initial comparisons indicated potential problems with the Intercomp sensor. We then suggested alternate approaches that MNDOT could use to determine whether recalibration was required. Finally, we analyzed ten-month data from the IRD WIM system and four-month data from the Kistler WIM system to evaluate relative sensor accuracy. While both systems were found to be self-consistent within the data time frame, the Kistler system generated more errors than the IRD system. Conclusions regarding relative accuracy could not be reached without additional data. We identified the sorts of measurements that would need to be monitored for recalibration and the methodology needed for estimating future recalibration time.