Muhammad Amin

ABSTRACT This article examines volatility models for modeling and forecasting the Standard & Poor 500 (S&P 500) daily stock index returns, including the autoregressive moving average, the Taylor and Schwert generalized autoregressive conditional heteroscedasticity (GARCH), the Glosten, Jagannathan and Runkle GARCH and asymmetric power ARCH (APARCH) with the following conditional distributions: normal, Student’s t and skewed Student’s t-distributions. In addition, we undertake unit root (augmented Dickey–Fuller and Phillip–Perron) tests, co-integration test and error correction model. We study the stationary APARCH (p) model with parameters, and the uniform convergence, strong consistency and asymptotic normality are prove under simple ordered restriction. In fitting these models to S&P 500 daily stock index return data over the period 1 January 2002 to 31 December 2012, we found that the APARCH model using a skewed Student’s t-distribution is the most effective and successful for modeling and forecasting the daily stock index returns series. The results of this study would be of great value to policy makers and investors in managing risk in stock markets trading.

ABSTRACT The quantile regression technique is considered as an alternative to the classical ordinary least squares (OLS) regression in case of outliers and heavy tailed errors existing in linear models. In this work, the consistency, asymptotic normality, and oracle property are established for sparse quantile regression with a diverging number of parameters. The rate of convergence of the combined penalized estimator is also established. Furthermore, the rank correlation screening (RCS) method is applied to deal with an ultrahigh dimensional data. The simulation studies, the analysis of hedonic housing prices and the demand for clean air dataset are conducted to illustrate the finite sample performance of the proposed method.

ABSTRACT The present penalized quantile variable selection methods are only applicable to finite number of predictors or do not have oracle property associated with estimator. This technique is considered as an alternative to ordinary least squares regression in case of the outliers and the heavy-tailed errors existing in linear models. The variable selection through quantile regression with diverging number of parameters is investigated in this paper. The convergence rate of estimator with smoothly clipped absolute deviation penalty function is also studied. Moreover, the oracle property with proper selection of tuning parameter for quantile regression under certain regularity conditions is also established. In addition, the rank correlation screening method is used to accommodate ultra-high dimensional data settings. Monte Carlo simulations demonstrate finite performance of the proposed estimator. The results of real data reveal that this approach provides substantially more information as compared with ordinary least squares, conventional quantile regression, and quantile lasso.

The present penalized quantile variable selection methods are only applicable to finite number of predictors or do not have oracle property associated with estimator . This technique is considered as an alternative to ordinary least squares regression in case of the outliers and the heavy-t ailed errors existing in linear models . The variable selection through quantile regression with diverging number of parameters is investigated in this paper. The convergence rate of estimator with smoothly clipped absolute deviation penalty function is also studied. Moreover , the oracle property with proper selection of tuning parameter for quantile regression under certain regularity conditions is also established. In addition, the rank correlation screening
method is used to accommodate ultra-high dimensional data settings. Monte Carlo simulations demonstrate finite performance e of the pro-posed estimator . The results of real data reveal that this approach provides substantially more information as compared with ordinary least squares, conventional quantile regression, and quantile lasso.

This study reviews the social and ethical aspects of Genetically Modified Crops (GMCs) in Pakistan, a Muslim country. Ethical issues such as lack of sharing demerits of product and incorporation of genes from religiously prohibited species such as animals with long pointed teeth or tusks which used to kill their prey such as tigers, bears, elephants, cats, monkeys etc.; animals that are not slaughtered according to Islamic law; predator birds such as eagles, owls, etc.; pests and poisonous animals such as rats, cockroaches, centipedes, scorpions, snakes, wasps, etc.; animals that are forbidden to be killed in Islam such as bees (al-nahlah), woodpeckers (hud-hud), etc.; creatures that are considered loathsome or Haram such as lice, flies, pigs, dogs, etc. and alcohol or alcohol based items can cause serious social problems regarding the believes of the people of a Muslim country. Pakistan being deficient in proper indigenous research facilities depends on developed countries for GMCs. Islam puts no barrier in the advancement of science and technology but invites the people to explore the world to provide social justice and equality to the masses. GMCs can play a vital role in the prosperity of alarmingly populated countries like Pakistan only and only if the mentioned ethical aspects are taken seriously under appropriate domains of Sharia (Islamic Law). However, poor literacy rate, lack of communication between religious scholars and scientists, the lack of infrastructure to create and evaluate the character of GMCs and their effects on environment, health and economics are needed to be addressed. So it is suggested that these issues can be resolved for the prosperity of masses through educated religious scholars, the indigenous infrastructure for GMCs, proper legislation, proper communication and independent information. For this purpose open debates on electronic and print media, workshops, and conferences should be held to reduce the communication gap between consumers, producers, researchers, Muslim scholars, students and policy makers.

A field experiment was conducted at Nuclear  Institute for Food and Agriculture (NIFA), Peshawar, to identify high yielding bread wheat genotyp es against terminal heat stress in the central agro ecological zone of NWFP. The genotypes included in the trial were selected on the basis of
yield performance and other agronomic characters under normal and late planting conditions from NIFA Observation Nursery (NON) sown during  2001-2002. For the confirmation of their desired traits the selected genotypes were again pl anted under the same sowing conditions during 2002-2003 using two different sowing dates as  a separate factor. Statistical  analysis of the data revealed
that significant differences in days to heading,  days to maturity, plant  height, biological yield,
spikes per m
2, 1000 grain weight (g), grain yield kg ha-1 and hectolitre weight (kg) were observed for all the genotypes with respect to early and late sowing dates. The results indicated that the
overall performance of the genotypes was the best  with respect to normal sowing.  Though all the
characters were negatively affected as a result of late  sowing yet the genotypes CT-01217, CT-01222 and CT-01085 with grain yield of 4745, 4334 and 4334 kg ha-1 respectively performed well with respect to harvest index (40.5, 31.0 and 36.5 %) and medium plant height character (89, 92 and
91 cm) as compared to those of the best check line (Bakhtawar-92) which is an indication that some bread wheat genotypes among existing germplasm may have in built resistance/tolerance against terminal heat stress under late planting condition.

Penalized  regression  methods  for  simultaneous  variable  selection  and  coefficient  estimation  have  received  a  great  deal  of attention  in  recent  years.  Especially  those  based  on  the  least  absolute  shrinkage  and  selection  operator  (LASSO),  that
involves penalizing the absolute size of the regression coefficients. The ordinary least square and LASSO methods were used for selection of  most significant traits contributing towards  seed  yield in  mungbean plants  with 18  morphological and yield
associated traits and to develop the prediction model . Bayesian information criterion was applied to choose minimum tuning  parameter. Results indicated that dry weight biomass and harvest index were highly significant characters towards seed yield
while  days  to  maturity,  days to  flowering,  number  of  nodes  per  plant,  pods  per  plant  and  degree  of  indetermination  had  a
significant  affect  on  response  variable.  Based  on  the  results,  it  was  rational  to  conclude  that  high  yield  of  mungbean  crop could be obtained by selecting the breading materials with these important characters on seed yield.

The  fundamental  issues  of  statistical  inference  related  to  geographically  and
temporally weighted regression (GTWR) model are studied. Initially, the test statistics for
hypothesis  testing  problems  of  global  stationarity,  spatial  nonstationarity  and  temporal
nonstationarity are proposed by analysis of variance technique. The heteroscedasticity in
GTWR model is detected and SCORE test statistic is provided. Finally, an approximation
method is proposed to compute the p-values for aforementioned test statistics. A Simulat-ion  study  is  carried  out  to  assess  the  performance  of  these  test  methods,  and  a  real
example of per capita GDP in Chinese 92 cities is given.

The purpose of this paper is to focus on Chinese middle class retail consumers’ shopping
preferences and dissimilarities from the perspective of income differentiation. In this respect,
the overall goal of this case study is to explore segregated shopping preferences of the middleincome
retail consumers’ bias to their relative-income clusters (defined in Section 3) in urban
Dalian, China. SPSS and Excel software was used for data processing and analysis in this
study. Standard deviation computed using excel for each variable aim to measure how well the
mean represents the data involved in the study. Multiple regression models were used to test
the significance of the influence of independent variables to dependent variables. Two regression
models were used to test the significance of the explanatory variables to describe the change in
dependent variables. The relationship between the explanatory variable and dependent variables
are presented as the Classical Linear Regression Model (CLRM). Findings suggest that
affordability dissimilarities as a dependent factor to relative income differences have significant
and indicative roles and impacts on Chinese middle-class consumers’ shopping preferences
and subsequent actual purchase decisions, and as a whole on consumption patterns. The
findings can provide new insights for elaboration of competitive strategies targeting the different
income levels exclusively in a second-tier city, and inclusively in China.