DSpace Collection:
http://dspace.cityu.edu.hk:80/handle/2031/770
2016-02-11T14:29:43ZConvex bounds for dependent risks with applications to robust optimization
http://dspace.cityu.edu.hk:80/handle/2031/6984
Title: Convex bounds for dependent risks with applications to robust optimization
Authors: Li, Xiaobo (李曉波)
Abstract: Consider a portfolio that consists of multiple assets for which the risks are dependent.
Robust bounds for the risk of the portfolio given the partial dependency structure
of the asset returns have received considerable attention. In this paper, we develop
new convex bounds for the case with overlapping multivariate marginal dependencies.
We propose an infinite dimensional linear programming based method to find these
bounds in Conditional Value-at-Risk version for sum risk function and general multivariate
marginal structure. Polynomial complexity results for discrete distribution
case are developed for this problem. The results are extended to the approximation
on the distribution of sum risk. With the tight bound on conditional value at risk of
the joint portfolio, we propose a novel robust portfolio selection model that can deal
with overlapping multivariate distributional information. Under some mild assumptions,
the optimization problem can be solvable in polynomial time. Some numerical
examples are presented.
Notes: CityU Call Number: HD61 .L568 2012; viii, 72 leaves 30 cm.; Thesis (M.Phil.)--City University of Hong Kong, 2012.; Includes bibliographical references (leaves 68-72)2012-01-01T00:00:00ZApplication of Hong Kong consumer satisfaction index : formulation of investment portfolio and relationship with the Hong Kong macro-economic condition
http://dspace.cityu.edu.hk:80/handle/2031/6500
Title: Application of Hong Kong consumer satisfaction index : formulation of investment portfolio and relationship with the Hong Kong macro-economic condition
Authors: Wu, Chi Wai ( 吳志偉)
Abstract: Consumer satisfaction has well been recognized as a critical element for successful
businesses. Sweden produced the first nation-wide Consumer Satisfaction Index in
1989 to measure Consumer satisfaction in an objective way, followed by several
other countries with their own versions of the same index. Although numerous
studies exist in the literature exploring the relationship between consumer
satisfaction, company performance and other economic indicators, most of them
use only consumer satisfaction indices from the western countries, e.g. SCSB and
ACSI etc. This thesis addresses two main applications of Hong Kong Consumer
Satisfaction Index (HKCSI).
Using HKCSI data, the effect of consumer satisfaction on company equity value
were identified for 16 listed companies using linear regression model. A
hypothesized investment portfolio was built and its return is compared with market
return using Capital Asset Pricing Model (CAPM). The return is 175% in 6 years
time, which is 1.4 times higher comparing with market return (73%). The beta risk
of the whole period is 0.799, and this indicates the portfolio risk is not
significantly different from the market. This study shows that consumer
satisfaction can be applied for formulating investment portfolio with better
performance than market rate.
The second study went on by exploring the influences of Hong Kong
macroeconomic conditions on consumer satisfaction using the principal
component analysis and Least-square Regression. Two principal components,
namely Economic Growth and Economic Condition, have been found to account
for 85.1% of the variation in HKCSI. By investigating the association between
macroeconomic conditions and consumer satisfaction, firm can have better
understanding on how economic effects affecting its own satisfaction score.
Notes: CityU Call Number: HF5415.335 .W8 2011; viii, 119 leaves : ill. 30 cm.; Thesis (M.Phil.)--City University of Hong Kong, 2011.; Includes bibliographical references (leaves 96-104)2011-01-01T00:00:00ZModeling and analysis of loading strategies for outbound logistics with RFID technology
http://dspace.cityu.edu.hk:80/handle/2031/6284
Title: Modeling and analysis of loading strategies for outbound logistics with RFID technology
Authors: Wei, Jie (魏潔)
Abstract: Logistics planning has become a major concern for most enterprises in recent years since logistics/distribution-related costs comprise a significant part of the total cost. In outbound logistics, loading activities play an important role and represent a major portion of logistics costs since they can impact the lead time to delivery of products to the final customers. In this study, we conduct a case study on a giant printing and paper bags manufacturer which has some problems with its current FIFO (first in, first out) loading strategy. When trucks arrive at the production plant for loading finished goods, some products have not yet been finished, with some percent still on the production line. This makes the trucks wait in the loading bay for unbearably long time and trucks which arrive early but have to await loading block other trucks ready for loading. Consequently, the average time trucks spend in the plant increases, while throughput, i.e. the number of trucks loaded decreases. Moreover, many trucks fail to leave the plant by the predefined time and miss their due date, which seriously impacts delivery performance. In this study, we reengineer the current loading processes and design some alternative strategies for loading operations. Some of these alternative strategies are dynamic, which make use of real-time production information provided by RFID technology. There are some literatures about applications of RFID in logistics and supply chain management but there have been few studies about its applications in loading for outbound logistics. Our study can fill this gap and give some practical guidelines for real logistics operations in production plants.
In the first chapter, we briefly introduce the concept of logistics management and outbound logistics, RFID technology, and literature review of RFID's applications in logistics and supply chain management, as well as literature on simulation studies. Following these is the description of current loading operations process and problems associated with it. Chapter 2 introduces the methodology we use. We begin with an introduction of discrete event simulation, which is the main methodology we adopt. Then data collection procedures are discussed, followed by the experimental design illustration, which includes independent and decision variables, dependent variables, and inputs of different parameters. The function of simulation tool ProModel is introduced in the following section. One way ANOVA test and 95% confidence interval are used to test whether there are any significant differences among different loading strategies with respect to average operations time in system. If there is significant difference among different loading strategies, we use fisher's least significance test to identify which sets of strategies perform differently from each other. In the last section of Chapter 2, we introduce the methodology of model validation. Model validation is the process of determining whether the model is a meaningful and accurate representation of the real system, and it's usually the tool for decision making. We introduce Naylor and Finger's three-step approach for model validation and compare the model input-output transformation through a turing test since most of our model's output is based on the new configuration, in which statistical testing is almost impossible.
Chapter 3 focuses on the reengineered loading operations process with RFID adoption in the loading bay. When a truck is scheduled for loading, its products are transported from the warehouse to the loading bay at the same time when the truck undertakes local travel within the plant, for empty weighing and delivery note submission operations. This reengineering reduces trucks' waiting time for loading, and, therefore, reduces the total average time trucks spend in system, i.e. in completing loading operations. Simulation results under the two scenarios verify
this hypothesis.
In Chapter 4, we first introduce deployment of RFID in the production line, and then illustrate
four different product loading strategies. Simulation models of operations of these strategies are
built for comparison. The results indicate that when finished percentage is in normal distribution,
there are no significant differences between most strategies in terms of average operations time,
except between the shortest remaining time ( SRT) and the earliest due date ( EDD) strategy.
However, in the sensitivity analysis, in which products' finished percentage is lower, there are
significant differences between FIFO and SRT, SRT and EDD, and EDD and S/RPTi , in
terms of the time measure. Among these strategies, with respect to average operations time in
system, SRT performs best in both the original experiment and sensitivity analysis. FIFO has
the second best performance in the original experiment while S/RPT performs second best in
sensitivity analysis. The sequence of performance in terms of throughput (total number of trucks
loaded) is the same as in case of average operations time. With regard to percentage of tardy
trucks, two RFID-enabled dynamic strategies, SRT and S/RPT , rank first and second,
respectively, followed by EDD and FIFO.
In Chapter 5, we improve the single product loading and extend it to mixed products loading
strategies. Strategies FIFO and EDD perform the same as in single product loading. However,
SRT and S/RPT must be changed since there are several different remaining production times
for the same truck also, as several kinds of products are to be loaded on the same truck.
Therefore, we choose the maximum remaining production time as a truck's remaining time, and
change the two models accordingly. Original and sensitivity analysis simulation results suggest
that with respect to average operations time in system, SRT has the best performance, especially when finished percentage is lower. S/RPT and FIFO have similar performances while EDD
has the worst performance. Tardiness related measure has the same performance sequence as that
of single product loading.
In conclusion, our simulation study indicates that a combination of well-designed strategies and
advanced RFID technology can greatly improve the performance of outbound logistics. It is
expected that more and more research into RFID's applications will be conducted for
performance improvement in outbound logistics.
Notes: CityU Call Number: HD38.5 .W444 2009; xiv, 135 leaves : ill. 30 cm.; Thesis (M.Phil.)--City University of Hong Kong, 2009.; Includes bibliographical references (leaves 94-97)2009-01-01T00:00:00ZTwo essays in applied econometrics on duration analysis and model selection
http://dspace.cityu.edu.hk:80/handle/2031/6127
Title: Two essays in applied econometrics on duration analysis and model selection
Authors: Guo, Yingwen (郭穎文)
Abstract: The thesis consists of two essays in applied econometrics. Essay 1 adopts duration
analysis to investigate what factors affect the length of an "interest rate spell" - the
period during which the interest rate instrument remains unchanged under inflation
targeting. Nowadays, an increasing number of countries have transitioned to
inflation-targeting regime, and most of them have achieved stable economic growth
and low rates of inflation. Not surprisingly, inflation targeting has attracted growing
interest among economists in recent years. Shih and Giles (2009) first applied
duration analysis to model the length of an interest rate spell under inflation
targeting, and their analysis was directed to the experiences of Canada. This essay
extends Shih and Giles (2009) work through a cross-national analysis of eight
inflation-targeting countries (or areas). Both parametric and nonparametric methods
are employed for the analysis. The conclusion is consistent with that of Shih and
Giles (2009), that is, the length of an interest rate spell is affected by both the rate of
inflation and the rate of economic growth; the influence of exchange and
unemployment rates proved to be insignificant. Moreover, empirical results support
that inflation-targeting central banks usually design their monetary policies based on
the Taylor Rule.
Essay 2 compares the performances of four model selection criteria: Akaike’s
information criterion (AIC), the Schwarz Information criterion (SIC), the smallsample
bias corrected AIC (AICc) and the small-sample bias corrected SIC (SICc)
in a linear regression model with heteroskedasticitic or mutually dependent errors.
Monte Carlo simulation was used to conduct the analysis. AIC and SIC are widelyused
information criteria, but they have a tendency to overfitting in small samples.
The AICc and SICc can reduce this small-sample bias. Most literature compares the
model selection criteria in the situation when the error terms are identically and
independently distributed. Ohtani (2003) first examined their small-sample
performances in a linear regression model with first-order autocorrelated errors.
Stipulated by Ohtani (2003), this essay considers other types of error terms,
including multiplicative heteroskedasticity, the first-order moving average (MA (1))
and the first-order autoregressive conditional heteroskedasticity (ARCH (1)). It was
found that AIC and SIC tend to overfit in small samples, and AICc and SICc
outperform AIC and SIC respectively. As the sample size increases, AIC and SIC
have a decreasing tendency to overfitting and respectively converge to AICc and
SICc. In addition, SIC and SICc perform better than AIC and AICc respectively.
Notes: CityU Call Number: HB539 .G86 2010; vii, 86 leaves 30 cm.; Thesis (M.Phil.)--City University of Hong Kong, 2010.; Includes bibliographical references (leaves 81-86)2010-01-01T00:00:00Z