Department of Quantitative Methods

Permanent URI for this collection

https://escholar.umt.edu.pk/handle/123456789/1162

Browse

Now showing 1 - 16 of 16

Factora affecting children immunization in Lahore
(University of Management and Technolog, 2017) Syeda Tahseen Fatima
Immunization is the cost effective way to prevent disease with use of vaccine. In 1974 WHO introduce expanded program of immunization (EPI) to vaccine children throughout the world. Cross sectional study was conducted to contribute information regarding factors effecting immunization in children <3 years of age at Lahore. Immunization coverage is better in Lahore as compare to other cities but still vaccination status of children in Lahore is not 100%. Factors may include poor knowledge about vaccination nearby health care center, vaccination card etc... Interviews were conducted specifically designed questionnaire with question about reasons of poor immunization status among children. Analysis included descriptive and cluster analysis is used. Two clusters were formed, in cluster 1, Parents had illiterate (Mother 96.8% & Father 48.5%). 92.5% parents had knowledge about vaccination. In cluster 2, Parents had also illiterate (Mother 96.8% % Father 64.8. The application of Health facility by the population of Lahore is better. In immunization status is not up to the target and various determinants are attached with the poor immunization status. If those determinants for vaccination were escaped, the coverage of vaccine could easily reach national targets. Access to nearby health care facility, parental educational levels, socioeconomic status, and knowledge about the vaccination can contribute to the better immunization status in Lahore.
Performance assessment of some existing and new ridge regression estimators
(University of Management and Technolog, 2017) Himmad Khan
An important assumption of the multiple linear regression model is that the regressors should be independent, which is violated in practice. Due to violation of this assumption, the problem of multicollinearity occurs and results into unreliable statistical inference for the model parameters. To cope this, several biased estimation techniques, including ridge regression, have been proposed in the literature. In ridge regression, the key problem is to estimate the ridge parameter and there are several methods in the literature for this purpose. In this thesis, we propose six different shrinkage estimators, named as HMS1 to HMS6 and further compare them to some existing methods, like HK, KMS, KSM, KMED and KGM. We use Monte Carlo simulations to assess the performance of different estimators assuming the mean square error as a performance comparison criterion. In particular, we assess the performance assuming various choices of error distribution, error variance, the correlation among the predictors, the sample size and the number of predictors. In addition to simulation study, we also analyze a real life example for the comparison of different estimators. On the basis of simulation study and real data example, we found that our new proposed estimators outperform in most of the assumed conditions, especially when the error distribution is Normal, level of collinearity, variance between errors and predictors were moderate to high. However, it was also observed that the estimators KMS, KSM and HMS1 performed better than other estimators when the collinearity and error variance were small or moderate. when the error distribution is students-t , we observed that the estimators KGM, KMS, HMS1 and HMS5 outperformed among others. Moreover, we noticed that for high level of collinearity, and different values of variance of error terms, the HMS5 outperformed among others.
Dynamics of Solow residual technology – a case of Pakistan
(University of Management and Technolog, 2017) Fatima Jamil
Technology is usually considered as a determinant of productivity, manufacturing industries are more commonly observed to use technology in order to enhance their level of productivity. This study has tried to capture the impact of technology on its contribution in industrial value addition, environment quality and capacity to create jobs. For this three models are constituted for the case of Pakistan. This study has used Vector Error Correction Model, utilized to estimate long run pattern of changes in technology. The results showed that technology has a positive impact on industrial value addition, it improves the environmental quality by reducing the carbon emissions and it has the potential to create jobs and reduce unemployment in long run.
Relationship between ease of doing business and GDP
(University of Management and Technology Lahore, 2017) Shahid, Faiza
Business is of immense importance for the life of a country. Economy of whole country depends on its business. Each Govt. is introducing new policies and programs to increase business in country as well as to make easiest to do business for investors. Many factors are considered for doing business in any country such as its market, currency rate of country, demand of product or service in country, costs, inflation rate, climate and culture etc. Culture of Muslim and Non-Muslim countries is very different due to many factors such as finance system of Muslim countries, consumption pattern of different things, concept of interest, social culture, religious holiday, weekend days, economic role of women, joint family system and sharia etc. In this paper, we identified the difference in Mean of Ease of Doing Business in Muslim and Non-Muslim countries by using the ANOVA models. Moreover we not only described the effect of Gross Domestic Product on Ease of Doing Business but we also considered the social and environmental factors too while considering the relation of business and GDP. Moreover we extended our study by showing the path by Which GDP effect EODB. We used the measure of Social Progress index for social and environmental factors and we checked the mediation effect of Social Progress Index in relation of Ease of Doing Business and Gross Domestic Product. We used the bias corrected mediation technique for testing indirect effect.
Agent base simulation Fashion retail chain
(University of Management and Technolog, 2016) Saeed, Azam
This research develops a multi-agent simulation model for fashion retail supply chain. Intelligent agents are designed using SQL to performed key roles of supply chain management for fashion retail. Baseline model is validated and proposed model is designed using pooled inventory warehouse to make supply chain more responsive. Results shows that pooled inventory having a positive impact on customer services level, merchandise performance and mark-downs percentage is also reduced. Supply chain physical cost can also reduce by using deploying intelligent agents in real life and performance of these agent can improve by analyzing of simulation results and gaps analysis
Agent base simulation Fashion retail chain
(University of Management and Technology Lahore, 2016) Saeed, Azam
This research develops a multi-agent simulation model for fashion retail supply chain. Intelligent agents are designed using SQL to performed key roles of supply chain management for fashion retail. Baseline model is validated and proposed model is designed using pooled inventory warehouse to make supply chain more responsive. Results shows that pooled inventory having a positive impact on customer services level, merchandise performance and mark-downs percentage is also reduced. Supply chain physical cost can also reduce by using deploying intelligent agents in real life and performance of these agent can improve by analyzing of simulation results and gaps analysis.
A Comparison of Different Weather Forcasting Models
(University of Management and Technology, 2017) Zaheer Abbas
In this thesis, we studied the performance of different statistical models and compare their forecast accuracy. In particular, we used multiple linear regression (MLR), seasonal autoregressive fractional integrated moving average (SARFIMA), and artificial neural network (ANN). A dynamic non-linear autoregressive (NAR) back-propagation ANN algorithm has been applied to estimate the forecast accuracy. For ANN model, we used moving average (MA) and Holt-Winter exponential smoothing (HW-ES) transformations for pre-processing the data. The monthly data of different weather parameters have been obtained from the Lahore Metrological department, Pakistanto apply the aforementioned models. The results showed that the ANN model with MA transformation of the data has the smallest root mean square error and the highest correlation coefficient for different weather parameters. Thus, ANN outperforms than the rest models in this study and it can be used to efficiently forecast the weather parameters.
Determinants of inflation
(University of Management and Technology Lahore, 2016) Ghaffar, Sadia
In this study we will discuss about the determinants of Inflation in developing and developed countries we select the topic about determinants of inflation because all the countries worldwide are facing the problem of price rises. . The problem of inflation in Pakistan has been gradually increasing since separation and we know when prices will rise than the currency of a country will not be stable of a country. We try our best to make the best combination of the dependent and independent countries to get some meaningful results our objective in the study to find out the factors that are effecting the inflation in these days. For this purpose we collect the data from world developed indicator and index Mundi first of all we select the developing and developed countries by following the world developed indicator site after this we made the four groups of the developing countries and four groups of developed countries then we use the unit root test to find out the stationary of the variables then we run the Pooled Mean group estimators to find out the long run and short run equations we use the Shapiro wilks test to find out the normality of the model and for the purpose of Autocorrelation we use Autocorrelation Lagrange multiplier test and for model specification use the link test we check the Homoscadisty by using the White Hetroscadisticity test for the purpose of finding the Multicolinarty use variance inflation factor and tolerance method and to find out that there is co integration or not we use Kao residual co integration test.
Exploring the factors affecting the purchase of different mobile phone brands:A case study of universities of Lahore
(University of Management and Technology Lahore, 2017) Javed, Madiha
In this study we explore the effects of various factorsin selecting a specific mobile brand by students of different universities of Lahore.Multinomial logistic model has been utilized to check significance and effect of the variables. Results revealed that gender, age, discipline of study, job status, no. of family members, no. of employed family members and mobile phone price has turned out to be statistically significant indicators for selection of mobile brand. Gender, age, discipline of study, job status and no. of family member have positive effect on selecting mobile brands such as Samsung, Nokia, LG, Huawei and Others. While no. of employed family members and mobile phone price have negative effecting on selecting these brands.
Income Inequality Comparison through Parametric Modeling
(University of Management and Technology Lahore, 2017) Hussnain Abbas
This study takes into account the determination of income inequality by non-parametric and parametric approach and comparison of the two techniques in the context of Multiple Indicator Cluster survey (MICS) data of Punjab for the years 2007-08 and 2013-14. Different probability distributions namely Pareto, exponential, generalized Pareto, gamma, Weibull, log-normal, Singh Maddala, Fisk, beta type II and generalized beta type II, have been applied in order to select a suitable distribution for the per capita income of Punjab, Pakistan, for the period of 2007-08 and 2013-14. For this purpose Akaike information criterion (AIC) and Bayesian information criteria (BIC) have been used to choose the best model for the data sets.We find that the Generalized Beta distribution of second kind (GBII) is more appropriate for the given data set. Parameters of the aforementioned distributions have been estimated using the maximum likelihood estimation method. Moreover, Lorenz curves, Gini coefficient (parametric and nonparametric) have been used to measure the income inequality for the data sets. Parametric Gini coefficient for generalized Pareto distribution, not available in literature, has been also derived. On the basis of parametric Gini coefficient value, it is found that there is a decrease of 0.04 in income inequality in 2013-14 as compared to 2007-08 for the province of Punjab. There also exists a difference in point estimates of Gini coefficient estimated by parametric and non-parametric methods.
Exploring and Comparing Factors Affecting the Reading Abilities of Grade-III Students- A Case Study of Army Public Schools of Lahore
(University of Management and Technology, 2017) Mujahid, Sidra
In this study we investigate different factors affecting the reading abilities of Grade III students’ in Army Public Schools of Lahore. Data has been collected from 10 APSACS Schools. A sample of 299 respondents has been drawn using probability proportional to size sampling technique. Ordinal Logistic Regression analysis has been used to explore the factors affecting students’ reading achievement. It is concluded that occupation, facility library and comments on pictures have a significant effect on students’ reading achievement.
Mixture regression cum ratio estimators of population mean under stratified random sampling
(University of Management and Technology Lahore, 2017) Iqbal, Kanwal
In this thesis, single phase Mixture Regression cum ratio Estimators by using auxiliary variables and auxiliary attributes simultaneously have been proposed under Stratified Random Sampling. Special cases of the estimator are discussed and their mean square errors are also derived mathematically. A simulation technique has been used to observe the properties of proposed estimator which shows that the distribution of proposed estimator approximately normal.. An empirical study has been conducted by incorporating quantitative and qualitative characteristics in the form of auxiliary attributes and variables simultaneously to compare the performance of proposed estimator. Comparisons are made with Moeen et al. (2012) single phase mixture regression cum ratio estimator under simple random sampling. It has been found that the mixture regression cum ratio estimator using multiple auxiliary variables and attributes simultaneously under stratified random sampling is more efficient than Moeen et al., (2012) mixture regression cum ratio estimator under simple random sampling
Mixture regression estimators of population mean under stratified random sampling
(University of Management and Technology Lahore, 2017) Fatima, Madiha
In this study, Mixture Regression Estimators for single phase sampling under stratified random sampling have been proposed, by incorporating the simultaneous use of information on auxiliary variables and attributes. The estimators have been proposed for three different cases and their mean square errors have been derived mathematically. A Simulation study has been done by using simulated data, to check the distribution of proposed estimators. This study shows that proposed estimators, seems to follow the normal distribution. An empirical study has also been done by considering two natural data sets. Mean square errors (MSE’s) for the proposed estimators have also been computed and Efficiency comparisons made with single phase mixture regression estimators proposed by Moeen et al. (2012). On the basis of MSE’s computed through simulation and empirical studies, it is to be concluded that proposed estimators are more efficient than that of estimators proposed by Moeen et al. (2012) for simple random sampling.
Effects of Social Applications on Students Academic Performance in Pakistan: A case study of Lahore
(University of Management and Technology, 2016) Jawad, Tehreem
Social applications is the act of the growing the quantity of the ones business and social contacts by making associations through people frequently through social applications, for example, facebook, likendln, imo, twitter, whatsapp, and viber and so on. The fame of the social applications has quickly expanded in the recent years. Social applications gives numerous sorts of services and advantages to its clients like helping them to attach with new people groups, offers conclusions with like personality individuals on the web. In any case, the principle disadvantage of the chat rooms was that you may not know the individual with whom you are collaborating with. The presentation of profiles on social applications sites permitted individuals to know more information about a person before they interface with them. The purpose of our research is to explore the significant factors which have effect on the student’s academic performance. The study of this research is quantitative in nature. The target populations for this research are the university students of the Lahore. The sampling method which is utilized for this exploration is the stratified random sampling. As indicated by the rule of the hair & Anderson our total sample size for this research is 245. Then STATA has been used to analyze the collected data. Survey results were analyzed using the Multiple Linear regression. The results show that the significant and harmful association between the time spent on the social package and the academic execution. Student’s characteristic, time management, and predictor behavior is the positive impact on the academic execution as the time management enhance the student’s academic performance is also increases.
Consumer choice towards modern and traditional stores while buying FMCG
(University of Management and Technology, 2016) Akram, Nazia
There are different kind of features which attract the customers for the decision making of particular store selection such as variety, quality of product, price, discounts and staff behaviour. These factors build an image in the eyes of costumers. The purpose of the study is to find the important factors that attract customers towards the modern stores. For that purpose six important factors are extracted after extensive study of literature that are product variety, store atmosphere, staff courtesy, price structure and location convenience. In this paper logistic regression has been used in order to see the contribution of the mentioned factors to store selection. A total of 300 respondents were sampled from traditional and modern stores using systematic random sampling. Stores in this study is a dichotomous variable with two categories, modern and traditional. Because of this binary nature of the dependent variable logistic regression approach was found appropriate. Of five independent variables used in the study two were found most significantly associated in all models i.e. location and atmosphere. But curtsey factor was appeared insignificant in main logistic model as well as most of the sub models. The findings showed that logistic regression is the most promising tool in providing meaningful interpretations in such type of researches.
Yield forecast modeling For wheat crop Using agro meteorological data
(University of Management and Technology Lahore, 2016) Farooq, Muhammad
This thesis explores the possibility of using remote sensing images and its derived products, Normalized Difference Vegetation Index (NDVI), to assess and measure wheat yield potential. Panel regression models were developed for the Gujranwala division at different stage of spatial aggregation. Through the panel regression analysis, the study identified the relationship between the crop vegetation over the growing period and the final crops yield. The vital goal of the research is to inspect whether the NDVI model can generate precise and timely yield forecasts. The present study primarily focuses on the variation of crop yield through NDVI based panel regression analysis is used as a tool to achieve this objective. The NDVI model is used to represent crop vegetation density or greenness (reflectance of all agro metrological parameter) of the vegetation cover. It proves that, crops yield can be predicted more effectively and accurately by using NDVI base model as an alternative tool against the conventional models. The Redundant and Housman test which guides about the fixed effect model is suitable in this study. The NDVI base fixed effect model fits the crop yield data extremely well, with high R-square value at about 90%. The results suggest that NDVI for the month of January, February and March were ideal for wheat yield assessment. Market participants rely mainly on apt and precise crop yield forecasting to make informed buying and selling decisions which results in well organized resource distribution. It is an important point to mention that weather forecast network is not being used effectively and official crop production and yield estimations are not based on the accurate and timely information in Pakistan where agricultural growth is crucial for eradicating poverty. A practical and cost effective solution is provided for them by using Remote sensing and NDVI. The relationship between the accumulation of crop vegetation over the growing season and crop yields is confirmed in the present research. The NDVI panel regression model suits the crop yields data quite well in spite of a relative difference between forecast and actual official wheat yield. The three independent NDVI variables had positive impact on crop yield though to a varying degree.

Browse

Recent Submissions