Kuo-Chung Huang

Using Randomized Response to Estimate the Proportion and Truthful Reporting Probability in a Dichotomous Finite Population

In this paper, an alternative randomized response procedure is given that allows us to estimate the population proportion in addition to the probability of providing a truthful answer. It overcomes a difficulty associated with traditional randomized response techniques. Properties of the proposed estimators as well as sample size allocations are studied. In addition, an efficiency comparison is carried out to investigate the performance of the proposed technique.

Vibrio necrotizing soft-tissue infection of the upper extremity : Factors predictive of amputation and death

BACKGROUND Vibrio necrotizing soft-tissue infection (VNSTI) is characterized by rapidly progressing soft-tissue necrosis and fulminant septicemia in the at-risk host. Despite advancing antibiotic and infection control practices, VNSTI is still a highly lethal and disabling disease. By evaluating prognostic factors for fatality and major amputation in VNSTI patients, this study was intended to improve treatment strategies, reduce mortality and minimize amputations. METHODS We performed a cohort study of patients with VNSTI in the upper extremity at a trauma center which cares for residents in the costal southern Taiwan. Patients were considered for enrollment in this study if they met the following criteria: (1) histopathologically or surgically proven necrotizing soft-tissue infections of the upper extremities and (2) isolation of Vibrio species from soft-tissue lesions and/or blood collected immediately after arrival at emergency department. All patients were treated with a specified combination of parenteral antibiotic therapy (the combination of a third-generation cephalosporin and tetracycline), aggressive resuscitation and prompt débridement. The main outcome measures in this investigation included inpatient mortality and major amputation. RESULTS Sixteen patients were enrolled in the 5-year study from July 2002 to June, 2007. The overall mortality rate in this case series was 18.6%. Another 25% of surviving patients required major amputations. These subjects were, then, divided into two groups based on treatment outcome: unsatisfactory (death and major amputation) and satisfactory (survival without major amputation). The two patient groups did not differ in demographic data, treatment protocol, bacteriological findings or APACHE II and LRINEC scores. Patients with unsatisfactory results had a higher incidence of septic shock requiring vasopressor/inotropic support (p=0.020), severe hypoalbuminemia with less than 2g/dL (p=0.001) and elevated AST (p=0.039) than those with satisfactory results. The former also had longer ICU stay (p=0.039) and a higher incidence of comorbidity during hospitalization (p=0.024). CONCLUSION APACHE II or LRINEC scoring system cannot be used as a reliable tool for early detection of VNSTI. For treating such a highly lethal and disabling disease, clinical acumen remains of paramount importance regardless of the scores. Expanding purpura in these patients is considered an ominous sign and may indicate surgical intervention. A serial survey of ALT/AST or CPK levels can reflect the extent of muscle damage and help determine the optimal time of amputation. Severe hypoalbuminemia also serve as poor prognostic factors implicating a high probability of death or major amputation.

Model for End-Stage Liver Disease (MELD) Score as a Predictor and Monitor of Mortality in Patients with Vibrio vulnificus Necrotizing Skin and Soft Tissue Infections

Background Vibrio vulnificus necrotizing skin and soft tissue infections (VNSSTIs) usually predispose patients with or without preexisting liver disease to septic shock, and then evolve to multiple organ dysfunction syndrome (MODS), thus resulting in high mortality in humans. However, clinicians do not have a valid prediction model to provide a reliable estimate of case-fatality rate when caring for these acutely and/or critically ill patients. Methods/Principal Findings We retrospectively analyzed 39 consecutive patients with VNSSTIs (mean age: 65.7 ± 11.3 years) at our institution between 2007 and 2010. All patients were treated with the same protocol. Demographic and clinical characteristics, disease severity on admission, treatment details, and outcomes were collected for each patient and extracted for analyses. We studied the predictive value of the model for end-stage liver disease (MELD), modified MELD including sodium (MELD-Na), and laboratory risk indicator for necrotizing fasciitis (LRINEC) scores for case-fatality. Logistic regression and receiver operating characteristic (ROC) curve analyses were performed. The mean MELD, MELD-Na and LRINEC scores on admission were 15.1 ± 1.1, 17.7 ± 1.1, and 3.4 ± 0.4 points, respectively. After admission, these patients had temporary or progressive deterioration of nearly all their scores and lab values. The area under the ROC curve for the MELD and ΔMELD scoring models were 0.929 (p = 0.002) and 0.897 (p = 0.005), respectively. An optimal MELD/ΔMELD cutoff value ≥ 20/2 had a good sensitivity and specificity (all > 80%), with a 64/13-fold increased odds for case-fatality. Additionally, the development of severe forms of anemia (p = 0.014) and hypoalbuminemia (p = 0.019) were associated with an increased case-fatality rate. Discussion The MELD/ΔMELD scoring model is an effective risk stratification indicator at the time of admission and also an excellent condition monitor during hospitalization for medical care of acutely and/or critically ill patients with VNSSTIs.

Estimation of sensitive quantitative characteristics in randomized response sampling

Abstract This paper considers the problem of procuring honest responses for sensitive quantitative characteristics. An alternative survey technique is proposed, which enables us to estimate the population mean unbiasedly and to gauge how sensitive a survey topic is. An asymptotically unbiased estimator of sensitivity level is proposed, and conditions for which unbiased estimation for population variance being available is also studied. In addition, an efficiency comparison is worked out to examine the performance of the proposed procedure. It is found that higher estimation efficiency results from higher variation of randomization device.

Simple random sample equivalent survey designs reducing undesirable units from a finite population

In this paper, we consider fixed size sampling plans for which the first order inclusion probabilities are identical for all units and the second order inclusion probabilities are constant for every pair-wise unit. The statistical conditions are identified under which these plans are equivalent to the usual simple random sampling plan. These sampling plans are constructed to reduce undesirable units.

Constructing indirect randomized response techniques using symmetry of response

This paper considers the problem of estimating the population proportion when the study variable is sensitive in nature. Some indirect randomized response techniques are proposed, which maintain the requirement of efficiency and protection of confidentiality. In addition to unbiasedly estimating population proportion and variance, an efficiency comparison is also carried out to examine the performance of the proposed techniques. It is found that the proposed technique is more efficient than Warner [11], and Christofides [5] techniques.

On estimation of ratio of population means in survey sampling when some observations are missing

This paper aimed at the improved estimation of ratio of population means inthe presence of some observations are missing. Two estimators are proposed and their properties of relative bias as well as mean square error are studied.Also, a comparison of the proposed estimators with reespect to the four types of ratio estimators, suggested by Toutenburg and Srivastava [3], is given.

A survey technique for procuring trustworthy data on sensitive quantitative character in finite population

Abstract Singh [3] suggested a survey technique to deal with quantitative sensitive characters through Moors’ [2] strategy. However, a psychological problem may arise which yields some interviewees to give incorrect answers about a non-sensitive character. To eliminate the response bias and to improve respondent’s cooperation, an alternative randomized response technique is proposed, which has some other advantages over the usual unrelated question technique. Principal properties of the estimator of the population mean are studied. Also, an empirical study is carried out to examine the performance of the proposed strategy.

The control of a conveyor under the economical aspect

Abstract The control of conveyor to support the operations of machine loading and unloading has become rebellious and crucial to the management. However, through the mathematical model proposed in this paper, this issue becomes realistically and concretely solvable. This study not only meditates the conception of balancing the number of parallel machines and adjusting conveyor speed into the objective, but also develops a heuristic method to optimize the combinatorial problem for maximizing profit. In addition, the versatility of this study is exemplified through a numerical study. This paper definitely contributes an applicable scheme for production scheduling in manufacturing and provides a valuable tool to conclusively optimize the profit of a given production lot size for operations research engineers in today’s manufacturing with profound insight.

A survey technique for procuring honest responses

Abstract This paper considers the problem of unbiased estimation for the proportion of sensitive characteristics. A survey technique without any use of randomization devices is proposed, which is constructed by using an unrelated, innocuous characteristic together with random group strategy. The proposed technique contributes in higher estimation efficiency and better protection for personal privacy, which results in a greater degree of respondents’ cooperation. And it may be operated through cheaper approaches such that the survey costs would be reduced.