Statistics

Permanent URI for this collection

http://etd.aau.edu.et/handle/123456789/32

Browse

Browsing Statistics by Issue Date

Filter results by year or month
Now showing 1 - 20 of 238
  • No Thumbnail Available
    Item
    Ranking and Selection . Procedures and their Applications to the Educational Performance of Students at Addis Ababa University
    (Addis Ababa University, 1987-06) Tadesse, Mekonnen; Dr. G.P.Mehta.
    TheStatistical Metbndology of Ranking and selecting procedures has been Investigated
  • No Thumbnail Available
    Item
    Statistical Methods in Estimating the Demand for and Supply of in Ethiopia
    (Addis Abeba university, 1988-05) Atnafu, Teklewold; Kidane, Asmerom(Professer)
    Durinq the past foux O.oca<'1es, a bo<'1y of econometric techniquE"; (l.esigneCl to deal \'li th the problem of single equation estimation as well as sil'mltaneous-c'1uations bias has been develoned and applied to a variety oE economic relationships. Such methods had \·lide application in present day develope~ countries. HOI'lever, there has been very little attempt to apply these techniqu~s to empirical relationshir>s describina the roonotarv "octor of oHveloninq countries in qeneral ani:! :Rthiopia in particular. The maj or purpose of tho study 113, th8 re fore, 1. to for);'ulatc a mathematical f'lodel descrihing the various sectors of the economy with more emnhasis on the role of money supply, 2. to apply various econometric methods and compare the1r relative efficiency in explaining the emnirical relations; 3. to identify the significant explanatory variables that are important in explaining variations in supply of mon8Y and <'leman"!. for money in Eth1opia1 4. to test a structural model of the monetary sector by first specifyina demand for and sumly of money and the interrelation Lilith other economic variables 0 The relevant t1me series data is collect9d from the Quarterly Bulletin published by the Nat10nal Bank of Ethiopia
  • No Thumbnail Available
    Item
    Applicationof new Statistical Methods to Study the Attitude of Farmers in Axaki District. Ethiopia
    (Addis Ababa University, 1988-06) Woldermariam, Berhanu; Dr . G. Sadas i van
    Since attitudes are subjective an illusi ve, scal inq techni ques for quanti fy ing att itudes are most i mpor tan t and hence r eceive a consider ab l e ~mount of attention in our l iterature
  • No Thumbnail Available
    Item
    Statistical Measures of Income Distribution with Reference to Rural Ethiopia.
    (Addis Ababa University, 1989-06) Denbel, Million; Kidane, Asmorom
    St atis tical methods of measuring the dis tribution of income have been inves tigated as far as computing facility is available
  • No Thumbnail Available
    Item
    Statistical Measures Income Distribution With Reference to Rural Ethiopia
    (Addis Abeba university, 1989-06) Denbel, Mllion; Kidane, Asmerom(Professer)
    Statistical methods of measuring the distribution of income have been investigated as far as computing facility is available. The data set utilized in this study is the sub-san~le income data of the agricultural sedentary population of Ethiopia excluding Tigrai and Eritrea. The data were collected by the Central Statistics Authority and covers a period of one year, from May 1981 to April 1982. In particular, among others, en~rical results for four inequality measures, namely, Gini cofficient, Theil's entropy index, Relative mean deviation and logartlDllic variance have been obtained. moreover the liability of the lognomal and the pareto distributions as a mathematical discription of the i-;;;.ome data under consideration have been checked. Based on the computed results, some conclusions are made
  • No Thumbnail Available
    Item
    Determinants of Fertlizer use in Northern Ethiopian Aplication of Qualitative Response Models
    (Addis Ababa, 1990) Woldemariam, Desta; Kidane, Asmerom
    In this naper the merhod of qualitative Response Model (QRM)is Applide to Investigate Determinants of Fertilizer usage amonge Ethiopian Farmer in the Northewest .the theoretical basis of the decision is based on the concept of stochastic utility Model.
  • No Thumbnail Available
    Item
    Comparison of Several Est i mators for the Common mean of Different Normal Popul ations : a Monte Carl o Aroroach
    (Addis Ababa University, 1990-06) Kiros, Gebre- Egziabher; Tessera, Dr. Abebe
    In this paper several estimators of thp common unknown mean of poss iblydifferent nor mal popuJa ti ons when t he variances are unknown a re compared thr'ough an extensive Monte'Car lo study.
  • No Thumbnail Available
    Item
    Agricultural Multivariate Stratified Sample Survey with Applications to a Food Supply System
    (Addis Abeba university, 1990-06) Zewge, Genene; Melaku, Alemayehu(PhD)
    The population studied comprises the. ~gricultur~lhOl~seno.'ds ofa co~uruty in Damota district which is found in the North Omo administrative region. It was stratified by using the agro-ecological factor as the stratifying variable into three strata. Thus, the three strata arrived at in the process were the "Dega", "Kolla", and "Woyna Dega" agroecological zones in the research area. In the case where the study variables of interest are greater than one in a stratified sample survey, the usual optimum (Neyman) allocation method cannot be applied directly since what is best for one study variable may not necessarily be best for the other. Thus, other alternative techruques developed to go about this problem have been compared. These include the compromise, chatterjee as well as proportional allocation. Other methods which involve non-linear programmingtechruques were also reviewed. The data on the study variables which were believed to be indicative of the food supply system of the area were collected These included the family size, acreage, production, expenditure, reserves and purchases of the households. This was done through interviews carried out by going to the sampled households. Prior to the conduct of the final survey, however, a pilot survey was undertaken which covered fifty households from each stratum. This was done in order to obtain the necessary information to estimate the stratum variances which were required for sample allocation purposes. The sample size 2 determination was also done scientifically by similarly using the data from the pilot survey as well as the approved budget of the survey and additional cost estimates. In addition to the above, anthropometric measures of children under five years of age were collected for the purpose of studying the nutritional status of the population \ considered
  • No Thumbnail Available
    Item
    Envestgation of Acadamic Stafe Stracher the Colege of Social Scinces Using Arcover Modeles and Adabtation of a Computer Program for Analisesa and Subseount Applications
    (Addis Abeba university, 1990-06) Gorfe Negussie; Ejigou Aynew (Professor)
    To estimate 1)ar'r:;\e'cer values, the rlata 0:': ;:he C"f' Oil Aach of the rauks, the num~Br af recruits ta eac~ o~ the ran~s and the nu~her of 10s5es ~rom each of the ran~s. from 1982/33 to 1986/87, h'.!ve \;13811 utilize,l. The 11'cthod ,,+ T13,ximum lil(,"Uhood \"as anrylieo. on tb,: nast ,1at" a f til'" (;011eo-e in order to estimate transition nrohahi1itics ~etweBr the Drobabi1ities o~ loss fro~ each of the ranks. The ~verane nun~1:,er of !Jnnu
  • No Thumbnail Available
    Item
    Attrition Rate at the Faculty of Science Addis Ababa University
    (Addis Abeba university, 1991-11) Zewotir Temesgen; Ejigou Aynew (Professor)
    In this paper, the attrition rates of students from the period 1980/81 to 1989/1990, in the Faculty of Science of Addis Ababa University, were examined. We found that freshmen attrition rate linearly decrease over time. The dampening effect of the attrition rate as the students progress from semester to semester was assessed using two attrition models: the Guttman and Olkin (1989) model and a re parameterized model that we formulated. computer programs were prepared to obtain the maximum likelihood estimates for the underlying parameters in each model. consistent results were found in the two models; the progress of Students in consecutive semesters appeared to show a difference from batch to batch
  • No Thumbnail Available
    Item
    Factors that Influeced the Extent of Damages to Aborting Women at the Gandhi Memorial Hospital in Addis Ababa
    (Addis Ababa University, 1992-06) Bekele, Zeleke; Ejigou, Prof.Ayenew
    out of a totalof 9817- cases of-abortation that were Observed _ at the Gandhi MellOrial-,-Bospital
  • No Thumbnail Available
    Item
    In this paper interbirth interval in rural community of Ethiopia was considered. The aim was to study the distribution of this variable and to see if it varies across regions and socio economic groups. The data for the study was obtained from a socio demographic multipurpose survey conducted in rural Ethiopia in 1989 and 1990. The approach of the study was to fit probability density functions and then generate probabilities so that relate this probabilities to fertility rates and levels. While none of the densities fitted perfectly to each consecutive birth interval, the lognormal distribution was found to be relatively better for the first and second intervals. A wider mean first birth interval was observed in Northwest and a relatively smaller one in south, indicating a relatively high fertility rate in the Southern region. For lower parities, interval length of 1.45-2.45 years was observed as a most probable interval length and this shifts to .45-1.45 years at higher parities. For a given interval length and birth order, probability of having a child is higher in south and smaller in Northwest, indicating a relatively high fertility in South and a lower one in the Northwestern region. In a final consideration of family size, education, sex of the first two children in a family and religion, there was no significant difference observed in birth interval pattern in different regions of the country
    (Addis Abeba university, 1992-06) Medhin, Girmay; Kidane, Asmerom(Professer)
    In this paper interbirth interval in rural community of Ethiopia was considered. The aim was to study the distribution of this variable and to see if it varies across regions and socio economic groups. The data for the study was obtained from a socio demographic multipurpose survey conducted in rural Ethiopia in 1989 and 1990. The approach of the study was to fit probability density functions and then generate probabilities so that relate this probabilities to fertility rates and levels. While none of the densities fitted perfectly to each consecutive birth interval, the lognormal distribution was found to be relatively better for the first and second intervals. A wider mean first birth interval was observed in Northwest and a relatively smaller one in south, indicating a relatively high fertility rate in the Southern region. For lower parities, interval length of 1.45-2.45 years was observed as a most probable interval length and this shifts to .45-1.45 years at higher parities. For a given interval length and birth order, probability of having a child is higher in south and smaller in Northwest, indicating a relatively high fertility in South and a lower one in the Northwestern region. In a final consideration of family size, education, sex of the first two children in a family and religion, there was no significant difference observed in birth interval pattern in different regions of the country
  • No Thumbnail Available
    Item
    A Study on Error Sixes and Required Sample Sixe in Sequential Probability Ratio Test Amonte Carlo Approach
    (Addis Abeba university, 1993-12) Dilba, Gemechis; Tessera, Abebe(PhD)
    In this paper computer simulation is employed to investigate the nature of the error sizes and the distribution of sample size required in a sequential probability ratio test (SPRT). In the test we can distinguish between two kinds of error probabilities. The first kind are the specified error probabilities which are usually denoted by a and B, and the second kind are the true error probabilities which may be denoted by at and Bt• Wald has shown that the relation at + Bt ~ a + B holds true. The objective of this project is to investigate the relation between at and a, and between Bt and B. As sample size required in SPRT is a random variable, its distribution is also studied. Two probability distributions: Bernoulli and normal (known variance) are selected for the study. The study shows that in ,t.he' case 'of norma'l' distribution, when the parameters under rio:: 5rrd' :~i' ;~re: ,sl~g~~i~ :f*~: :*p,~'tt and a = B, the estimates of true error, 'probahiIi ties, C',1:'e less 'than their corresponding specifi~d ~rror i)r('b~hi!iit~es and"that 'they are close to each other. The est:lmat,es ~t ;t' 'a'h? ~t ,~1~9 decr:ease as d = 9 1 - 90 increases. Th~s, lillJ.q~s, t~a,t, tlJ.~ ~9t~a,i ~iflks, {iz:e by far less than the specified value for large d. When a and Bare not equal, there are times when the estimate of at or Bt exceeds its corresponding specified error size as observed. But, still if the parameters under HO and HI are far apart, the estimates indicate that at ~ a and Bt ~ B. For Bernoulli distribution, the results are not very far from those of normal except that in some cases the estimates of at or Bt are found to be greater than a or B which led to disobeying the inequality at + Bt ~ a + B. This may be attributed to sample fluctuation. And finally, sample size distribution is observed to depend mainly on d = 9 1 - 9 0 (90 < 9 1). The mean and variance of the required sample size increase rapidly as d decreases. Further, the distributions are all positively skewed. It is also observed that in rare occasions there is a chance that the sample size in SPRT exceeds the size one needs in non-sequential test
  • No Thumbnail Available
    Item
    A Study on Error Sizes and Required Sample Size in Sequential Probability Ratio Test
    (Addis Ababa University, 1994-01) Ayalew, Dereje
    The Gedamsa volcano lies on the floor of the northern sector of the Main Ethiopian Rift. It is characterized by a polygenic caldera resulting from large pyroclastic eruptions. KlAr dating performed by previous studies indicates an age of 0.8 to 0.1 Ma for the exposed volcanic products. Volcanologic and stratigraphic studies allowed recognition of several phases of activity during the evolution of Gedemsa. The lowest exposed products are represented by acidic lavas, which are covered by thick plinian fall pumice deposits. This are followed by an ignimbrite deposit and by intra-caldera lava flows and interbedded pyroctastic products. The caldera, is clearly a composite structure resulting from several collapses which occurred after plinian and ignimbritic eruptions. A separate stage of volcanic activity connected to the Wonji Fault System (basaltic volcanism) formed surge deposits and numerous basaltic cinder cones and lavas, both within and outside the caldera depression. The volCC!nic products from Gedemsa volcano are petrologically and geochemically diverse. Alkaline and peralkaline silicic lavas and pyroclastics (trachytes and rhyolites) are by far the most abundant products. The mafic rocks are only represented by the mafic inclusions occurring within some of the post-caldera products. The younger riftrelated activity is, instead, represented by Na-transitional basalt. On the whole, the rocks occurring in the area have a very marked bimodal distribution, a situation which is typical of almost all the young volcanism of the Ethiopian Rift Valley. Major and trace element variations of peralkaline silicic volcanic rocks from Gedemsa volcano support an origin by crystatlliquid fractionation starting from mafic parental liquids, with separation of olivine, plagioclase, clinopyroxene and opaques during the ear1y to intermediate stages and of alkalifeldspar and a few mafic phases (alkali am;>hiboles and pyroxenes) during the late stages of evolution. These processes generated strong enrichments in incompatible trace elements and depletion in compatible elements in the acidic magmas. Consequently, rhyolites display extremely high values of Zr, Y, Rb and F and low to very low abundances of ferromagnesian trace elements, Sr and 8a. Some rhyolites, howev,e r, have low Na and fluorine, most probably due to interaction with groundwaters. Such a process may represent an explanattion of the high F contents in the groundwaters of the Wonji area and of other zones inside the rift. Although, crystal fractionation best fits the geochemical variations, field and petrographic observations indicate that mixing processes were also active during the magma evolution. A model is presented for the evolution of the intemal structure of the Gedemsa volcano, based on volcanological, stratigraphic and geochemical evidence. According to this model, extensive fractional crystallization of parent mantle-derived basaltic magmas occurred in a huge shallow level magma chamber. This process, possibly accompanied by some mixing and assimilation of wall rocks, generated a zoned magma chamber whose upper part was occupied by silicic magmas. The presence of this silicic magma effectively acted as a density barrier to the mafic magma pending on the bottom of the reservoir. This expla ins why the Gedemsa eruptions were invariably characterized by emission of acid material. Huge plinian and ignimbritic eruptions generated the caldera collapse. This resulted in strong decrease in the size of the magma chamber. The post caldera eruptions tapped a smaller, still zoned reservoir. However, due to the small volumes of acidic magma standing in the upper part of the chamber, in some cases also mafic magma was brought to the surface intermingled with the acid material. The final basaltic eruptions are not related to the Gedemsa volcanic activity but represent liquids arising along regional faults which cut the rift floor, and the Gedemsa volcano itself.
  • No Thumbnail Available
    Item
    Some Statistical Measures of Regional Variation in Socioeconomic Performance the Etllopian Setting
    (Addis Abeba university, 1994-06) Fanta, Sileshi; Kidane, Asmerom(Professer)
    This study focused on the variation in the regional distribution of some socioeconomic services in Ethiopia. The paper also attempts to compare different natures of regional variation which were obtained on the basis of socioeconomic data for the year 1979 with the natures of regional variation obtained on the data of the same sort for the year 1989 . Some uni-variate descriptive measures and a multivariate method called cluster analysis were used to study the variation among regions. The six clustering procedures that are generated by a common algorithm [ Wishart (1969») were applied to investigate the natures of regional disparities in their socioeconomic status for the year 1979 and the year 1989. Different natures of regional variation for changes in socioeconomic characteristics of regions were also studied by applying six clustering procedures on the ratios the characteristics of regions in the year 1989 to that of the year 1979 Some conclusions were drawn on the basis of regional characteristics considered. Recommendations were also made to indicate some possibilities for future work in the area
  • No Thumbnail Available
    Item
    Comparison of Stochasic Models for Monthly Streamflow Sequences
    (Addis Ababa University, 1994-06) Gebreyohannes, Emanuel; Tessera, Dr. Abebe
    In this research , statistical work in stochastic modelling of hydrologic time series is discussed. The theme is the comparison of stationarity and non-stationarity approaches for stochastic simulation of monthly streamflow sequences. The paper first introduces various concepts related to stochastic modelling; the history of stochastic simulation and applications of stochastic modelling in hydrology; and the step-by-step modelling procedures. Then the paper describes how synthetic streamflow sequences can be generated using these procedures. As a particular case, synthetic streamflow sequences were generated for two streams in Ethiopia using both stationarity and non-stationarity approaches. At last, based on these synthetic flows , an attempt was made to compare the performance of the two approaches with some comments and recommendations
  • No Thumbnail Available
    Item
    Sampling Errors in Socioeconomic Surveys from Rural Settings in Ethiopia
    (Addis Ababa University, 1994-06) Tarekegn, Zelealem; Kidane, Prof . Asmerom
    In this paper an attempt was made to s tudy sampling errors from socioeconomic variables of three different areas of Gondar reg ion under three different sampling techniques . On the basis of the variances (standard errors) of each of the variables, design effects and rate of homogeneity values were computed. Depending on these values of sampling errors the accuracy and efficiency achieved in different sample designs on qualitative and quantitative socioeconomic variables were compared. Looking at the pattern of the sampling errors , out of the three techniques stratified random sampling was f ound to be highly superior for both discrete and continuous var i ables , in all of the three a reas. On the other hand these comput ed values of sampling errors s howed that for continuous variables , the performance of Cluster sampling was much better than that of Simple random sampling.
  • No Thumbnail Available
    Item
    Comparison of Stochstic Models for Monthly Streamelow Sequences
    (Addis Abeba university, 1994-06) Gebreyohannes, Emmanuel; Tessera, Abebe(PhD)
    In this research, statistical work in stochastic modelling of hydrologic time series is discussed. The theme is the comparison of stationarity and non-stationarity approaches for stochastic simulation of monthly streamflow sequences. The paper first introduces various concepts related to stochastic modelling; the history of stochastic simulation and applications of stochastic modelling in hydrology; and the step-by-step modelling procedures. Then the paper describes how synthetic streamflow sequences can be generated using these procedures. As a particular case, synthetic streamflow sequences were generated for two streams in Ethiopia using both stationarity and non-stationarity approaches. At last, based on these synthetic flows, an attempt was made to compare the performance of the two approaches with some comments and recommendations
  • No Thumbnail Available
    Item
    A Study of Influential Socio-Economic Factors Fertility in Bahirdar Town
    (Addis Ababa, Ethiopia, 1995) Ashenafi, Habtamu; Kencheko, Eshetu(PhD)
    Ethiopia is one of the developing countries that experiences a rapid population increase. Based on the 1984 census data the growth rate of the population of Ethiopia was estimated to be 2.9 percent. A population growth rate above 2 percent would pose a problem for the country's development. Therefore, it is of prime importance to study the factors which influence fertility so as to achieve a reduction in growth rate of population. In this paper an attempt has been made to assess the influence of some socio-economic factors on fertility taking a typical growing town, Bahir Dar. The method of regression was used to examine the influence of some selected factors on fertility. Among the factors considered in the study women 's employment was inversely related to fertility, though this relations hip was found to be not signifi£:a'nt" in 'the younger and .olderage groups. The educational Level of wife and husbard appeared to have an inverse relatior,sb.i.p !nth ferli ;.ity only in certain age groups. It seeme.1 chell inco'm'e 'had '" r')sitiv~ effect on fertility. There was no siginificant djffrnce in fertility between muslims and Christians, and between the Amharas and other ethnic groups taken together. The demographic feature for Bahir Dar, hopefully, can be representative of other towns in the country, and hence may be used to indicate what types of measures have to be taken in order to challenge the problem of population g r owth, especially in townships.
  • No Thumbnail Available
    Item
    Statistical Measures of Poverty with Reference to Ethiopia
    (Addis Abeba university, 1995-06) Tesfaye, Eshetu; Kidane, Asmerom(Professer)
    This paper is a project on the measurement and analysis of poverty in Ethiopia. Various statistical techniques of measuring poverty are applied. Therefore, in this paper, different measures of poverty will "be reviewed and discussed, and apply them to Ethiopian setting to compute the results and recommend the one that is appropriate for Ethiopia. In particular, among others, two measurements, namely Deficiency Risk Estimate and Gini-Coefficient, are applied to measure poverty indicators of the country. They are used to identify the percentage of under-nourished in a community in Ethiopia and the distribution of social services of different administrative regions of the country, like health services and education, respectively. Where as the other measures discussed in this paper, that is, the head-count ratio, the poverty-Gap, Sen's Index and Foster, Greer and Thorbecke measures are used to measure the incidence; intensity and severity of poverty in Ethiopia using income distribution