Master of Science in Statistics - Main Campus
Permanent URI for this collection
Browse
Browsing Master of Science in Statistics - Main Campus by Title
Now showing 1 - 20 of 22
Results Per Page
Sort Options
- ItemAgricultural production and economic growth in Somalia from 1986 to 2016(Kampala International University, College of Economics & management., 2018-09) Idiris Adam, YusufThe study aimed at examining the effect of agricultural production on economic growth in Somalia from the period of 1986 to 2016 using time series data. Specifically, the study examined the causality and the effect of agricultural production on GDP growth. The objective was motivated by the fact that the problem statement emphasized that agricultural production has not yielded expected economic growth in Somalia. The study hypothesized that no casualty between agricultural production and economic growth and that there is no significant effect of agriculture production on economic growth in Somalia. The study followed a multiple linear regression analysis which gives best linear unbiased estimates to establish relationships between GDP and the independent variables. Prior to the regression stationarity among variables was tested using ADF tests. The test results showed that all the study variables were nonstationary at level except agricultural production that only became stationary at level. The granger causality test showed that in Somalia, agricultural production does not granger cause GDP growth. The regression model showed that there is a significantly positive effect of agricultural production (13i=0.5058) and growth at 5% level, interest rate, inflation rate and exchange rate effects were positively insignificant. The study concluded there is no causality between economic growth and agricultural production. The thither concluded that agricultural production has a significantly positive effect on economic growth. Thus, sustained economic growth in Somalia can be achieved through expansion of agricultural production combined with good exchange rates. This study therefore recommends that government should enabling economic and political environment to promote agricultural productivity in the country
- ItemAssessing the effects of geographical expansion of Consumer Price Index (CPI) on inflation in Uganda(Kampala International University, 2017-05) Kaisiromwe, SamThe study details the effects of increasing Consumer Price Index (CPI) geographical coverage on inflation in the country.
- ItemAssessing the effects of geographical expansion of consumer price index on inflation in Uganda(Kampala International University, College of Economics & Management, 2017-05) Kasiromwe, SamThis study details the effects of increasing Consumer Price Index (‘CPI,) geographical coverage on inflation in the country. The study looked at the level 0/significance of Headline inflation and its related components, before and and geographical coverage increment. A comparison of analytical results obtained with two different CPI coverage, inflation numbers with Fort Portal Centre included in the computations and inflation numbers without Fort Portal Centre. The study applied Student’s t—test for the comparison of two means assuming unequal variance. The before and after study indicated that monthly Headline inflation is significantly different across the two data sets (P (T< =1,) two-tail = 0.0096 is less than 0.05). In addition, the monthly core inflation is significantly different across the two inflation trends (P (T< =~ two-tail = 0.0003 is less than 0.05). However, the study showed that the monthly inflation of Food Crops and related items is not significantly diffident across the two inflation trends, P (T<=t~) two-tail = 0.1361 is greater than 0.05). Similarly, the monthly Energy, Fuel and Utilities Inflation is~ different between the two inflation trends (P (T< =t,) two-tail = 0. 1361 is greater than 0.05). The result of Food Crops indicated that the expansion did not have any effect on the group ‘s CPI trends in the region. Thus the price changes in the two urban centres in Food Crops are the same and this could be because of the same climatic conditions of the western region. However, a further comparison of the two centres of Mbarara and Fort Portal, gave a clear distinction of the inflation trends in the separate urban towns. The significant difference in the Core inflation indicated that the group items in different urban centres have unique prices and thus more urban towns should be brought on board in CPI computation to further improve on the accuracy of inflation estimates in the country. Since the study revealed that there were changes in headline inflation due to expansion of coverage, the Uganda Bureau of Statistics should continue expanding the coverage of CPI items especially in the for eastern part of the country which is not uniquely represented in the national CPI. The EFU inflation trends were not affected by expansion of coverage due to the fact that Utilities Such as Water and electricity have a uniform price throughout the country thus emphasis in expansion should be put on improving the core Inflation trends which is mostly used by policy makers in the country. This research has filled the gap of the effects of geographical coverage of CPI and its effects on Inflation trends in Uganda. This study sets itself apart from generic economic researches that have been done before because; it combines the tools of econometrics, mathematics and statistics to analyze a statistical phenomenon: inflation before and after geographical expansion. Due to the fact that these results of the rebased CPI are only reflecting the urban expenditure patterns of Uganda, it is recommended that a study be carried out including the rural expenditure patterns. This research recommends that Uganda Bureau of Statistics (UBOS,) should begin the process of computing Rural Inflation trends in the country which will give a clear view of a complete picture of how inflation trends behave in the country.
- ItemComparative empirical power of univariate normality tests under symmetric, asymmetric and scaled distributions(Kampala International University, 2017-05) Muyombya, Solomon MatovuThe study aims at conducting an empirical comparison of power of univariate normality tests under symmetric, asymmetric and scaled distributions.
- ItemDeterminants of child mortality and morbidity in South Sudan(Kampala International University. College of Economics and Management, 2017-01) Latjor, Kel MalualThe main objective of this study was to examine factors associated with childhood mortality and morbidity in South Sudan. The specific objectives were to establish childhood mortality, examine the effect of childhood factors on morbidity as well as examining the contribution of mother factors on childhood mortality and morbidity. The study used both descriptive and inferential analysis using secondary data from Second South Sudan household health survey (SSHHS2). Using univariate, bivariate, logistic regression and nested logistic models, the study estimated the odds of dying and survivorship probabilities for under-five mortality. The results provided estimates of childhood mortality by bio-demographic, socio economic characteristics, residence and state level. The results showed unexpected pattern for infant and under five mortality rates across residence, mother education and wealth quintiles. Therefore, these childhood indicators are higher in urban areas (118), primary education (118) and richest household (117). The proportion of children who received all vaccinations is very low (54.1%) compared with those who didn’t receive any vaccinations. Children residing in urban areas (61.8) are more likely to be fully immunized compared to children in rural areas (38.2%). This is due to availability of health facilities in urban areas. The education of the mother has got a very poor relationship with the overall level of child mortality (Chi = 0.647, P-value <0.05). Based on the results, it can be concluded that birth interval affects survival when there is an interval of less than two years between pregnancies, demonstrating the importance of spacing on child survival. These factors were important in affecting child mortality. These factors may require to be taken into account in efforts that seek to address child mortality in South Sudan. The Childhood contributors to mortality and morbidity risk is diarrhea, because of large number of males and females that took part in the survey had diarrhea at least in the previous weeks prior to the study. Breast feeding, malaria infections were also great contributors to morbidity since they presented infection figures that were high in the study. In order to avoid prevalence of malaria, diarrhea and pneumonia in infants and under five years of age, the government of South Sudan in conjunction with NGOs should implement effective educational programs that aim at promoting and prolonging breastfeeding that may have a considerable effect on child survival.
- ItemDeterminants of maternal mortality of Somalia in the period 1990to 2012(Kampala International University, College of Economics and Management, 2015-06) Da’ud, Ali AserThis study investigated the influence of gross domestic product per capita, total fertility rate and HIV/AIDS prevalence rate (termed as determinants) on maternal mortality of Somalia in the period 1990-2012. This model is dedicated from demographic transition theory-derived from modernization theory. Secondary data between 1990 and 2012 inclusive collected from the publications of United Nations Statistics Division (UNSD) and World Health Organization (WHO) was used for this study. The trend of each of the above mentioned variables have also been examined in this study to show their movements and changes with the time. In order to determine the relationship between GDP per capita, total fertility rate, and HIV/AIDS prevalence rate as explanatory and maternal mortality ratio as dependent variable and the influence of independent variables on maternal mortality, the researcher used Pearson correlation coefficient and ordinary least square (OL.S) regression analysis with the help of STATA, versionl2, Line graphs were also used to examine the trends of the four research variables. The findings of this study showed that the trend of GDP per capita of Somalia in the study period is not predictable and there were fluctuations from time to time, GDP per capita of Somalia has experienced decreasing trend in three periods; from 1991 to 1992, 1999 to 2005 and from 2009-2012 while it has showed increasing trend in the periods; 1993-1998 and 2006-2008.The trend of the total fertility rate of Somalia in the period under, there were two equal and opposite trends. In the first decade (from 1990 up to 2000) an increasing trend while in the last decade (from 2001 to 2012) the trend was declining. In HIV/AIDs prevalence rate, there was generally rising trend of HIV/AIDs prevalence rate in Somalia in study period. The maternal mortality ratio of Somalia in the period 1990-2012 exposed increasing trend in the period covered by the study under consideration. Consequently the extent of maternal mortality ratio is as high as 978 deaths per 100000 live births. The study also showed that the explanatory variables (GDP per capita, TFR and HIV/AIDS prevalence rate) have strong relationship to the maternal mortality ratio as R2 coefficient of determination was found 81%. The study concluded that GDP per capita, TFR and HIV/AIDS prevalence rate have high influence on the maternal mortality and therefore, it is in line with the demographic transition theory. Based on the findings of this study, it is therefore, recommended that incomes of the population among them vulnerable groups should be elevated by giving microfinance to poor families, put forward policies to reduce fertility rate such as education and employment opportunities given to the women, and Community awareness campaign to be taken to warn people the ways that HIV/AIDS spreads.
- ItemEconomic growth and child mortality in Uganda (1990 — 2010)(Kampala International University, College of Economics & Management, 2012-09) Mwebesa, EdsonThis research study set out to investigate the relationship that exists between Economic Growth and Child Mortality in Uganda from 1990 — 2010. The study used Expost facto methods as it used already existing facts, descriptive and inferential methods (correlation and regression analysis) in investigating whether there was a significant relationship between Economic Growth and Child Mortality in Uganda. The study found out that there is a negative relationship between Economic Growth and Child Mortality of (r = -0.306) and Adjusted R2 = 0.0460 at 0.05 level of significance showing that as economic growth increases, child mortality reduces.Up on regression, at 0.05 and 0.1 levels of significance, the data showed that there is no significant relationship between economic growth and child mortality in Uganda from 1990 — 2010 and the relationship was significant at 0.25 level of significant.
- ItemEffect of mortality, fertility and net migration on population growth in Uganda (1985-2015)(Kampala International University, College of Economics and Management, 2017-10) Abdulahi, Mohamud OsmanThe study aimed at examining the effect of mortality rate fertility rate and net migration on population growth in Uganda from the period of 1985 to 2015 using time series data. Specifically, the study aimed at examining how each of these variables affects population growth. The objectives were; to examine the relationship between mortality rate and population growth rate in Uganda, to determine the relationship between fertility rate and population growth rate in Uganda are and to assess the relationship between net migration and population growth rate in Uganda rate. The hypothesis of the study was that there is no significant relationship between the independent variables of mortality rate, fertility rate, net migration and the dependent variable of population growth in Uganda. The study tested for stationarity among variables using ADF and Philip Perron methods. The stationarity results showed that all the variables of the study were stationary at level. Correlation analysis was used to exhaustively discuss the objectives. The findings from the correlation analysis indicated that fertility rate (r=0.228) and net migration (r=0.275) had appositive relationship with population growth while mortality rate (r=-0.30) had a negative relationship with population growth rate. Furthermore, the regression model showed that net migration has a positive significant effect on population growth also fertility rate has a positive non significant relationship with population growth rate. On the other hand, mortality rate has a negative significant impact of population growth. The study concluded that fertility rate and net migration are positively related to population growth while mortality rate is negatively related to population growth. Basing on the findings, this study recommended that there should be improvement on the health facilities across the country as a way of reducing infant and child mortality and that the policy makers must ensure that there is equitable and proportional distribution of resources to all geographical locations whether urban or rural in the country. Finally, the study recommended that through government and NGOs, contraception counseling be provided by trained family or general physicians and be conducted prior to marriage as this will better inform couples with choices of contraception. This will also contribute to meeting the unmet need for contraception and reducing unwanted fertility thus reducing population growth rate in the country.
- ItemExamining social - economic indicators of maternal mortality in Burundi (2005-2015)(Kampala International University, 2017-04) Rumuri, Berny ChristianThe study aimed at examining social - economic indicators that explain mortality rate in Burundi.
- ItemFive - child - killer diseases and under - five mortality in Yola Adamawa state, Nigeria (2001-2015)(Kampala International University, 2017-01) Waniyos, Hamidu UmaruThe study was set to investigate the prevalence of the five - child - killer diseases and under - five mortality.
- ItemFive child-killer diseases and under-five mortality in Yola Adamawa state, Nigeria (2001-2015)(Kampala International University, College of Economics and Management, 2017-01) Hamidu, Umaru WaniyosThe study was set out to investigate the prevalence of the five-child killer diseases and its cause effect on under-five mortality. It was driven by four major objectives; Determining the prevalence rate of the five child-killer diseases; Determining the proportion of mortality due to the five child-killer diseases to the total under-five mortality in the studying area; Examining the correlation between the five child-killer diseases and under-five mortality and Determining the cause effect of the five child-killer diseases on under-five mortality. The study used an entirely quantitative approach using secondary data between 2001 and 2015 obtained from the document of Adamawa state, Primary Health Care Development Agency (PHCDA). Data was collected regarding the number of children immunized, diseases and deaths due to Pneumonia, Diarrhoea, Measles, Tetanus, Polio and overall under-five mortality within that time frame. The study used uni-variate descriptive analytical tools, measures of prevalence rate per a thousand, measures of proportionality, con-elation analysis and regression tools for analyzing and developing a model for describing the data. The results indicate that the prevalence rates have generally been decreasing with Pneumonia recording the highest prevalence and Tetanus recording the lowest prevalence. Polio was excluded from the analysis because it did not register any incidences or deaths. The data also showed that pneumonia and diarrhea recorded the highest proportion of deaths while tetanus and measles recorded the lowest. The correlation matrix revealed that Pneumonia, Measles and Tetanus had strong positive and significant correlations with under-five mortality while diarrhoea had a weak positive and insignificant correlation. The regression model showed that there is a strong positive and significant relationship between Pneumonia and mortality and a weak non-significant relationship between diarrhoea and mortality. Furthermore, there was a strong but non-significant relationship between measles and mortality and a weak non-significant relationship between tetanus and mortality. The four variables explained 72.02 percent of the variation in overall mortality and the overall model was very significant. Due to high incidences of pneumonia and diahoea, the study made some recommendations and conclusions
- ItemHealth service delivery and maternal survival at Banadir Hospitals For 2001 — 2010 In Mogadishu, Somalia(Kampala International University, College of Economics and Management., 2012-09) Nur Haji, Hassan IsmailThis study was set out to establish the relationship between health service delivery and maternal survival at Banadir hospitals for 2001 up to 2010 in Mogadishu, Somalia the study wanted to establish the foUowing to determine the trend and level of health service delivery for 2001 to 2010 at Banadir Hospitals, to establish the trend and the level of maternal survival-for 2001 to 2010 at Banadir Hospitals, and to investigate the relationship between the health service delivery and maternal survival for 2001 to 2010 at Banadir Hospitals in Mogadishu, Somalia. Using a quantitative approach and exposit facto design, data on Health service delivery and maternal survival were collected from trusted sources using data record sheets. Data were analyzed at bivariate level using correlation and regression analysis. The computed {t-value =45.9195] is exceeds [t-value =1.83] at 0.05 level of significance and 9 degrees of freedom. Then the null hypothesis that a health service delivery is equal to zero is rejected and accepts the alternative hypothesis that the mean is not zero at 0.05 level of significance. The computed (P-value = 0.0000) < (p= 0.05). Thus, the mean (1001.5) is significantly greater than zero at 5% level of significance. This implies that rate of health service delivery of Banadir hospitals in Mogadishu Somalia is very high. The computed t-value=13.7312 and tabulated t-value at 0.05 level of significance and 9 degrees of freedom is t =1.83. Since (t~ =13.7312) > (ttabl.83) then null hypothesis that Maternal survival is equal or less than zero is vi rejected at 0.05 level of significance. Since P=0.0000 then mean of Maternal survival is greater than zero at 5% level of significance. Maternal survival is the dependent variable; of particular interest is which independent variable has correlation with maternal survival. In this case it is professional 95.6%. A change in maternal surv~,al is explained 74% by changing Beds delivery, a change in maternal survival is explained 83.4% by changing Ambulances, and a change in maternal survival is explained 85.7% by changing X ray. The strongest correlation among the independent variables is between Ambulances and x-rays (0.922) was called multicollinearity. The four independent variables explain 92.28% of the variation in maternal survival. We were considered for each independent like a unit change in maternal survival was caused changing by professionals of 116.4912, reduction in maternal survival was caused changing by ambulances of 12.644427, reduction in maternal survival was caused changing, by Beds delivery of 4.126387, and a unit change in maternal survival was caused changing by x-rays. The recommendations and suggestions for further studies arise from study findings above. Enhancement and training with Somalis health sector have to skill with health personality, the government of Somalia should encourage to the hospital according all requirement through minster of health and the central Bank of Somali reduce at least to lO% to encourage the investment like supply of Banadir hospitals.
- ItemPopulation growth and youth unemployment in Uganda (1991-2014)(Kampala International University. College of Economics and Management, 2017-05) Abdifatah, Said AhmedThis study was motivated by the fact the Uganda has one of the fastest population growth rates in the world accompanied by high unemployment rates thus the study aimed at investigating the relationship between population growth rates and youth unemployment in Uganda (1991 to 2014). The specific objectives of the study were; to find out the long run relationship between the population growth rate and youth unemployment rate in Uganda, to examine the causality between population growth and youth unemployment as well as to determine the effect of population growth rate on youth unemployment rate in Uganda. The hypothesis of the study was; there is no significant relationship between population growth rate and youth unemployment, There is no granger causality between population growth rate and youth unemployment rate in Uganda and there is no significant effect of population growth rate on youth unemployment rate in Uganda. The study was carried out using secondary data collected from 1991 to 2014. Augmented Dickey- Fuller (ADF), tests were carried out on the variables of population growth rate and youth unemployment and were found to non-stationary at level but stationary after first difference. Cointegration results of Trace and Maximum Eigenvalue findings showed that there is no long run relationship between population growth rate and youth unemployment. Granger causality tests also indicated that population growth causes youth unemployment in Uganda. A regression model encompassing all variables under study was developed to help assess how population growth rate in Uganda impacts youth unemployment rate. The results indicate that the independent variables account for 40.3% changes in youth unemployment rate. The overall model was significant on the basis of the F-statistic and the coefficient of determination that was reported by the data. The study concluded that there is appositive significant relationship between population growth rate and youth unemployment as was revealed from the model. Thus having discovered that there is a problem of rampant population growth rate in Uganda, this study recommended that there is need to formulate population control measures like family planning methods that are aimed at reducing that rate at which population of Uganda grows. To encounter the problem of increasing youth unemployment, the study recommended that there should be proper and adequate education system and training facilities that empowers young men and women with skills that make them job creators rather than job seekers.
- ItemPopulation growth and youth unemployment in Uganda (1991-2014)(Kampala International University, 2017-05) Abdifatah, Said AhmedThe study investigated the relationship between population growth rates and youth unemployment in Uganda.
- ItemPopulation growth and youth unemployment in Uganda (1991-2014)(Kampala International University, College of Economics and Management, 2017-05) Abdifatar, Said AhmedThis study was motivated by the fact the Uganda has one of the fastest population growth rates in the world accompanied by high unemployment rates thus the study aimed at investigating the relationship between population growth rates and youth unemployment in Uganda (1991 to 2014). The specific objectives of the study were; to find out the long run relationship between the population growth rate and youth unemployment rate in Uganda, to examine the causality between population growth and youth unemployment as well as to determine the effect of population growth rate on youth unemployment rate in Uganda. The hypothesis of the study was; there is no significant relationship between population growth rate and youth unemployment, There is no granger causality between population growth rate and youth unemployment rate in Uganda and there is no significant effect of population growth rate on youth unemployment rate in Uganda. The study was carried out using secondary data collected from 1991 to 2014. Augmented Dickey- Fuller (ADF), tests were carried out on the variables of population growth rate and youth unemployment and were found to non-stationary at level but stationary after first difference. Cointegration results of Trace and Maximum Eigenvalue findings showed that there is no long run relationship between population growth rate and youth unemployment. Granger causality tests also indicated that population growth causes youth unemployment in Uganda. A regression model encompassing all variables under study was developed to help assess how population growth rate in Uganda impacts youth unemployment rate. The results indicate that the independent variables account for 40.3% changes in youth unemployment rate. The overall model was significant on the basis of the F-statistic and the coefficient of determination that was reported by the data. The study concluded that there is appositive significant relationship between population growth rate and youth unemployment as was revealed from the model. Thus having discovered that there is a problem of rampant population growth rate in Uganda; this study recommended that there is need to formulate population control measures like family planning methods that are aimed at reducing that rate at which population of Uganda grows. To encounter the problem of increasing youth unemployment, the study recommended that there should be proper and adequate education system and training facilities that empowers young men and women with skills that make them job creators rather than job seekers.
- ItemPrivate sector investment and economic growth in Uganda (1985-2014)(Kampala International University, 2017-10) Mohamoud, AbdukadirThe study aimed at examining the effect of private sector investment and economic growth in Uganda from 1985-2014.
- ItemPrivate sector investment and economic growth in Uganda (1985-2014)(Kampala International University, College of Economics and Management, 2017-10) Mohamoud, Abdulkadir DiriyeThe study aimed at examining the effect of private sector investment on economic growth in Uganda from the period of 1985 to 2014 using time series data. Specifically, the study examined the causality, the long-run relationship between private sector investment and economic growth and also the impact of private sector investment on GDP growth. The objective was motivated by the fact that the problem statement emphasized that private sector investment has not yielded expected economic growth in Uganda. The study hypothesized that no casualty and long-run relationship between private sector investment and economic growth and that there is no significant effect of private sector investment on economic growth in Uganda. The study followed a multiple linear regression analysis which gives best linear unbiased estimates to establish relationships between GDP and the independent variables. Prior to the regression stationary among variables was tested using ADF and Phillip Perron tests. The test results showed that all the study variables were stationary at level except trade, population and inflation rate that only became stationary after first difference. The granger causality test showed that in Uganda, private sector investment does not granger cause GDP growth. Johansen Co-integration tests showed existence of co-integration among variables. The regression model showed that there is a significantly positive effect of private sector investment (f3~=1 .454) and growth at 5% level, population growth (136=-0.874) showed a negatively significant effect on growth. Inflation rate and exchange rate effects were positively insignificant while trade and gross capital formation effects were insignificantly negative at 5% level. The study concluded there is no causality between economic growth and private sector investment and no a long-run equilibrium relationship between private sector investment in Uganda. The further concluded that private sector investment has a significantly positive effect on economic growth whereas population growth has a significantly negative effect on economic growth. Thus sustained economic growth in Uganda can be achieved through expansion of private sector investment combined with good exchange rates and price legislation. This study therefore recommends that government should enabling economic and political environment to promote privatization in the country.
- ItemReal exchange rate, inflation rate and private investments in Uganda (1990-2014)(Kampala International University, College of Economics & Management, 2017-05) Mohamed Abdullah, Adam M.The main objective of the study is to examine the impact of real exchange rate and inflation on private investments in Uganda. The two objectives were to determine the effect of real exchange rate on private investment; to determine the effect of inflation rate on private investment. The study used Real exchange rate, Inflation rate, Bank credit, Foreign direct investment, Public investment and trade as the determinants of private investment using secondary data for a period of 1990-2014 gathered from the world bank database. Analysis was carried out using a combination of both correlation and an ordinary least squares multivariate regression model. The data shows that the level of private investment has steadily been increasing for the 24 -year period considered in this study. Furthermore, the rate of inflation in Uganda has been quite irregular though averagely stable in the recent years with some slight movements up and down. Additionally, the real exchange rates have been decreasing though at a rather irregular rate for between 1990 and 2014. The results of the regression analysis show that there exists very significant negative effect of real exchange rate on private investment in Uganda. Further analysis indicates that there exists a negative and significant effect of inflation rate on private investment after log transformation in Uganda. The study concludes that inflation is very insignificant in explaining the observed trend in private investment. Thus, an increase in inflation may lead to a decrease in private investment. The study further concludes that there is a very significant negative effect of overall real exchange rate on the level of private investment in an economy. In other words, an increase in the average value of real exchange rate in the economy is expected to result into a decrease in the average level of private investment in the economy. Since the results reveal that mild changes in the overall rate of inflation have got a stimulatory effect on private investment, the study recommends that it is imperative for the policy makers to adopt structural reforms that will keep the inflation rate in check so as to stimulate the economy. Furthermore, due to the very significant effect of the real exchange rate (price level) on private investment in Uganda, the study recommends that policy makers ought to adopt strategic and systematic that would prevent the exchange rates from escalating through strategies that would bring more foreign currency into the economy since its impact on private investment can easily be felt. The study also recommends that policy makers should formulate competition policies within the Ugandan trade sector as this will not only help reduce fake goods in the market, but also help expand access to finance for private investors as this will bring more money in circulation, offer wider choices of products, and encourage better services hence economic growth of the country.
- ItemSimulation study on the performance of robust outlier labelling methods(Kampala International University, College of Economics and management, 2023-10) Abdiweli, Ahmed JamaThe identification and labeling of outliers play a crucial role in data analysis and modeling tasks. Robust outlier labeling methods aim to accurately identify observations that deviate significantly from the majority of the data points while being resilient to noise, measurement errors, and data corruption. In this simulation study, we evaluate the performance of various robust outlier labeling methods using synthetic datasets. To conduct the study, we defined the simulation setup by specifying the characteristics of the datasets, including the number of variables, sample size, distributional assumptions, and proportion of outliers. Synthetic datasets were generated based on these specifications, incorporating both normal observations and outliers with known characteristics. A set of robust outlier labeling methods was selected for evaluation. These methods were designed to effectively handle outliers and provide reliable labels. Implementation of the selected methods was carried out using a programming language, ensuring proper application to the generated datasets. Performance metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC) were defined to assess the effectiveness of the outlier labeling methods. Each method was applied to the synthetic datasets, and the results were recorded. The performance metrics were calculated based on the known labels of the synthetic outliers. The collected results were analyzed and compared to identify the strengths and limitations of each robust outlier labeling method. The performance metrics were used to assess accuracy, robustness, and computational efficiency. To ensure the reliability of the findings, the simulation study was repeated with different simulation setups and datasets, validating the consistency of the results across multiple iterations. Based on the findings, conclusions were drawn regarding the performance of the evaluated robust outlier labeling methods. The most effective methods for the specific characteristics of the datasets used in the study were identified. These findings provide valuable insights for researchers, practitioners, and data analysts in choosing appropriate outlier labeling methods for their data analysis and modeling tasks. In summary, this simulation study contributes to the understanding of the performance of robust outlier labeling methods and provides a systematic evaluation framework for comparing and selecting suitable methods in the presence of outliers.
- ItemSolow-swan model for the analysis of the effect of foreign direct investments in Ugandan Economic Growth(Kampala International University, College of Economics and management, 2023-02) Mohamed, Nur AbdiReports that global foreign direct investment (FDI) inflows grew from $23 billion in 1975 to $1.95 trillion by 2017. Lower-middle income economies have seen a significant increase in foreign direct investment (FDI) inflows as well as a rise in growth rates over the past few decades. At the aggregate level, GDP growth for lower-middle income economies was strong over the past four decades. In 1975, GDP for these economies was just 311 billion dollars. But by 2017, this figure had grown to 6 trillion dollars. FDI accounted for 0.37% of GDP in 1975 and 1.94% of GDP in 2017. In 2017, upper-middle income economies received three times more foreign direct investment (FDI) than lower-middle income economies, but the annual growth rates were similar. There is a question of whether foreign direct investment (FDI) stimulates economic growth in lower-middle income economies, and to what extent. This is an issue of interest because it has implications for how these economies can develop. There is some evidence that FDI does stimulate economic growth in lower-middle income economies. This is likely because it makes these economies more productive and efficient. However, this effect is not always positive. Therefore, it is important to consider the effects of FDI on the economy as a whole. Generally, FDI appears to be a valuable tool for growth in these economies. The purpose of this paper is to contribute to the ongoing debate about whether foreign direct investment (FDI) has a positive or negative effect on economic growth in lower-middle income economies with data more up to date.