Department of Statistics

Permanent URI for this collection

https://repository.udsm.ac.tz/handle/123456789/56

Browse

Now showing 1 - 20 of 47

Comparison of Estimators of Interclass and Intraclass Correlations from Familial Data
(Wiley, 1986) Srivastava, M. S.; Katapa, R. S.
When familles have different numbers of offspring, Srivastava (1984) gave an alternative approach to deriving the maximum-likelihood estimators of inter- and intraclass correlations, which requires solving only one equation. Since the procedure is iterative and requires considerable computation, several alternative estimators have been proposed in the literature. In this paper, a comparison is made between the maximum-likelihood estimator and two alternative estimators proposed by Srivastava (1984). By obtaining the asymptotic normal distributions of the estimators, it is shown that one of the easily computable estimators is comparable to the maximum-likelihood estimator.
Estimation of Interclass and Intraclass Correlations in Multivariate Familial Data
(1988) Srivastava, M. S.; Keen, K. J.; Katapa, R. S.
Asymptotically normal estimators of interclass and intraclass correlations are derived for more than two quantitative characteristics of parent and siblings in a simple random sampling of families that have different numbers of offspring. These estimators are proposed as an alternative to the maximum likelihood estimators, which can be found only by iterative methods requiring prohibitively large amounts of computation. The asymptotic variances of the proposed estimators are also given. In an illustrative example, these easily computable estimators are seen to be comparable to the corresponding maximum likelihood estimators.
Some Determinants of Nutritional Status of One- to Four-Year-Old Children in Low Income Urban Areas in Tanzania
(1992) Mbago, Maurice C. Y.; Namfua, Pelad P.
Some socio-economic and demographic factors contributing to nutritional status (underweight and wasting) of children aged 1 to 4 years (n = 949) were studied in selected low income urban areas in Tanzania. Children were classified as either normal or malnourished and logistic regression was used in the analysis. Of the demographic variables studied, sex of the child was significant using both weight-for-age and weight-for-beight indices. Males had better nutritional status than females. Mother's education level and age were significant risk factors using weight-for-age. Immunization status of the child and household density were also significant, but their effects became insignificant when morbidity and dietary variables were included in the analysis. Using weight-for-beight the place of residence and number of children trader 5 years in a household had significant effects on nutritional status though the latter was less significant when morbidity variables were incorporated. Children from big towns were significantly better off nutritionally than those from small towns. For dietary and morbidity variables frequency of feeding and diarrhoea were significant predictors of nutritional status (weight-for-age) while malaria was a significant predictor of weight-for-height
A Test of Hypothesis on Familial Correlations
(1993) Katapa, R. S.
When familial data are analysed, the model usually employed assumes independence of family observations and constancy of interclass and intraclass correlations. A statistic for testing the validity of the assumptions of family independence and constant interclass and intraclass correlations is developed. The test statistic is for constant family size; it has an asymptotic chi-square distribution. An example to illustrate the theory is given using Frets's data on head lengths. A recommendation is made on how to apply the test to the general case of varying family sizes. Another recommendation is made on models to be tried once the null hypothesis is rejected.
Mother's Marital Status as a Correlate of Child Welfare in Tanzania
(1993) Katapa, R. S.
4. Arranged Marriages
(1994) Katapa, R. S.
Some Correlates of Child Mortality in the Refugee Populated Regions in Tanzania
(1994) Mbago, Maurice C. Y.
Data from the 1988 Tanzania census were used to examine child mortality in three regions populated with Burundi refugees. Logistic and least squares analyses show that for both Tanzanian nationals and refugees low levels of maternal education are associated with high child mortality levels. Children born to mothers who are housewives are associated with low levels of mortality compared to those born to employed mothers, though the results were not statistically significant for the refugees. Maternal demographic status, computed from age and parity, has a strong effect on child survival. Unexpectedly, child mortality was lower where the water source was a well outside the village. Tanzanian mothers who are at highest risk of childbearing are roughly 6·4 times more likely to have a child death than those at lowest risk; the corresponding figure for the refugees is 36·8. This emphasises the need to intensify family planning programmes in these regions.
Social Factors Associated with Female Household Headship in Tanzania.
(1994) Katapa, R. S.
The Tanzania Health and Demographic Survey (TDHS) conducted in 1991/92 shows that 18.5% of Tanzanian households are headed by women. Using the TDHS household questionnaire data, logit regression model analysis have shown that female heads of households are older and less educated than the male heads of households. The models have also shown that female headed households are smaller in size and have fewer adult males than the male headed ones. Female headed households are over-represented in urban areas.
Statistics Training in Eastern and Southern Africa: A Study of Supply and Demand
(1997) Woodward, Mark; Dourmashkin, Neil; Twagirumukiza, Etienne; Mbago, Maurice C. Y.; da Cunha, Adrião F.
In recent years considerable concern has been expressed, from within and outside the continent, about the standard of official statistics in Africa. This has prompted the question of how effective the training of African statisticians has been. This paper describes findings from studies of current supply and future demand for statistics training in Angola, Botswana, Ethiopia, Kenya, Lesotho, Malawi, Mozambique, Namibia, Swaziland, Tanzania, Uganda, Zambia and Zimbabwe, carried out in 1993 and 1994. Recommendations for future development of training systems are given. These include strengthening in-service training in national statistics organizations and developing regional courses for professional statisticians.
Teenage Mothers in Their Second Pregnancies
(1998) Katapa, R. S.
Gender Differences in School Performance: Evidence Form the National Form IV Examination Result and Implications for Poverty
(1999) Katapa, R. S.
Correlates of Knowledge of Prevention of Sexually Transmitted Diseases among Primary School Pupils in Tanzania
(2003) Mbago, Maurice C. Y.; Sichona, Francis J.
In this paper we attempt to identify factors that determine knowledge on prevention of sexually transmitted diseases (STDs) among primary school pupils in Tanzania using data extracted from the Family Life Education KAP Survey conducted in 1999. The data used consist of a sample of 18,564 pupils (about 50% males and 50% females) from all the 20 regions of Tanzania mainland. There were significant differences between boys and girls as regards knowledge of family life education in general. Boys tended to be more knowledgeable than girls about many aspects of family life education. The findings show that only 40.1% of the respondents were able to identify all the three STDs given in the questionnaire namely gonorrhoea, syphilis and AIDS. As regards modes of HIV transmission only 37.5% had full knowledge of these, while 48.8% knew condom use and abstinence as methods of STD prevention. The bivariate analysis showed significant relationships between knowledge of condom use and abstinence as methods of STD prevention with knowledge of STDs, HIV transmission, education level of the respondents, residence and parents' education for both boys and girls. However, knowledge of STDs, HIV transmission and residence came out clearly in the logistic regression as predictors of knowledge of condom use as a method of STD prevention for both sexes. For males, mother's education was also a significant predictor of knowledge of condom use as a method of STD prevention. Furthermore, a significant predictor of knowledge of condom use for female respondents was found to be the respondent's educational level. On the other hand, predictors of knowledge of abstinence as a method of STD prevention were knowledge of STDs and HIV transmission.
Caretakers of AIDS Patients in Rural Tanzania
(2004) Katapa, R. S.
Socio-economic characteristics of caretakers of bed-ridden AIDS patients in two rural communities of Rungwe district, Tanzania were sought. The study also explored what caretaking entailed. Data were collected from 60 caretakers between September and November 2002. The proportion of female caretakers was significantly higher than that of male caretakers; the majority of the caretakers were old. The majority of the AIDS patients were family members of the caretakers. The caretakers' households lacked basic needs for the patients. Some of the caretakers sold family assets in order to buy medicines for the patients. Most of the caretakers worked under stress and there was no one to counsel them. Community members offered very little or no support to caretakers and the households were stigmatized. People in the communities knew about HIV/AIDS transmission, but their behaviour did not match their knowledge.
Socio-demographic correlates of desire for HIV testing in Tanzania
(CSIRO PUBLISHING, 2004-03-30) Mbago, Maurice
Background: Over 60% of women and men interviewed in the Tanzania Demographic Health Survey (TDHS) of 1996 and the Tanzania Reproductive and Child Health Survey (TRCHS) of 1999 indicated that they would like to be tested for AIDS virus (HIV-antibody test). This is encouraging in view of the fact that voluntary HIV testing coupled with appropriate counselling is now believed to be quite effective for the prevention of HIV infection. This paper seeks to identify some socio-demographic factors that are associated with desire for HIV testing in Tanzania. Methods: The study used data from the 1999 Tanzania Reproductive and Health Survey in which 4029 women and 3542 men were interviewed. A logistic regression analysis was used to identify correlates of desire for HIV testing for both men and women. Results: For both men and women the logistic regression results show that significant correlates of desire for HIV testing are education, residence and knowledge of HIV prevention. In particular the odds of desire for AIDS test were found to be lower for respondents with secondary school education than those with primary school education. The odds were also significantly lower for urban respondents than for rural ones. The findings further show that the odds of desire for having an AIDS test were lowest for respondents with no knowledge of HIV prevention. Conclusions: Strategic campaigns to convince people to go for HIV testing should put more emphasis on radio programmes since these are effective means of communication in rural areas where desire for testing seems to be high. Such programmes should also focus on raising awareness on HIV prevention. HIV testing facilities should also be extended to the rural areas and be offered at affordable prices.
Some Factors Associated with Time use on Non Productive Activities in Tanzania
(2005) Mbago, Maurice C. Y.
This study utilizes the International Classification of Activities for Time-Use Statistics (ICATUS) to delineate non-productive and productive activities. The study uses data from the Tanzania country-wide survey on time-use conducted between January and February 2005. An attempt was made to examine some factors associated with time-use on non-productive activities. The factors included age, residence, marital status, education and gender. The findings showed statistically significant association between non-productive activities and each of the above factors. The effect of these factors on involvement in non-productive activities was tested through a logistic regression. The results revealed that residence and gender have significant effect on non-productive activities while education has an insignificant effect (p=0.07). In particular the findings showed that respondents in rural areas are 1.5 times less likely to be involved in nonproductive activities than those in urban areas. With regard to gender the results suggested that women are 2.4 times more likely to be involved in non-productive activities than men.
Time Use Comparison of Female and Male Teenagers in Tanzania
(2005) Katapa, R. S.
A study on phase-1 time use in Tanzania was carried out by the Department of Statistics between January and February 2005. The phase-2 study was conducted between March and August 2005. The questionnaire method was employed in collecting data for the phase-1 study and data for the phase-2 study was collected by the diary method. In both phases, youths including teenage girls and boys were among people from whom data was collected. This paper is concerned with analysing data on teenagers from the phase-1 study
A Comparison of Female-and Male-Headed Households in Tanzania and Poverty Implications
(Cambridge University Press, 2006) Katapa, R. S.
Female- and male-headed households were compared using data from a Demographic and Health Survey conducted in Tanzania in 1996. Chi-squared tests showed that sex of head of household was highly significantly associated with: residence, household size and composition, radio ownership, having enough food to eat, and age and marital status of head of household. An analysis by the logit regression model showed that female-headed households were more likely than male-headed households to be in rural areas, be small, have fewer men, not have radios and not have enough food to eat. The majority of female heads of households were unmarried and older than male heads of households. The implication is that female-headed households are poorer than male-headed households.
Knowledge on HIV/AIDS and Sexual Behaviour among Youths in Kibaha District, Tanzania
(2008) Lema, L. A.; Katapa, R. S.; Musa, A. S.
Sub-Saharan Africa is more heavily affected by HIV/AIDS than any other region in the World. Half of all new HIV infections occur in young people. Identifi cation of the associated factors is likely to be useful in designing effective interventions. This cross-sectional study aimed to investigate the determinants of high-risk sexual behaviours among youths in Kibaha District, Tanzania. Data was collected using a structured questionnaire. The survey gathered data pertaining to the sexual healthy behaviours among youths, including condom use, number of sexual partners, age at fi rst sexual involvement and knowledge on sexually transmitted diseases and HIV/AIDS. A total of 322 individuals aged 15-24 years were involved in the study. More than 69% had sex at least once in their life time. Only about one-third (32.3%) of the youths reported to have used condom during the fi rst sexual intercourse and 37% during the last sex. About 21.7% of the respondents acknowledged having more than one sexual partner in the last 12 months. The majority (98.4%) of the respondents have heard of HIV/AIDS. About three quarters (74.8%) of the respondents knew where to get HIV testing services but only a small proportion (28.9%) had tested for HIV infection. Of those not yet tested, 38.2% admitted that they were ready to do so. Although 317 (98.4%) respondents were aware of HIV/AIDS, and majority, 65.2% mentioned condom as the method used to prevent its transmission, only 117 (36.3%) acknowledged using them. In conclusion, despite good knowledge on transmission of HIV among youths in Kibaha district, only a small proportion of them practices safe sex. Education programmes on safe sex practices should be strengthened to provide skills that could be effective in changing and maintaining safe sex behaviours among youths in Tanzania.
Determinants of extramarital sex by men in Tanzania: A case study of Mbeya region
(SAMA Health and Medical Publishing Group (HMPG), 2010-12) Mbago, Maurice; Sichona, Francis
This paper attempts to identify some factors associated with extramarital sex by men in the Mbeya region of Tanzania using data from a survey conducted in 2003/2004. The choice of Mbeya region was prompted by the fact that it has been found by previous studies to be one of the regions with the highest HIV prevalence rate in Tanzania. Correlates of extramarital sex that were considered include current age, education, residence, age at first sexual intercourse, age at first marriage and sex before marriage. A bivariate analysis of the survey data, which comprised a sample size of 568 married men aged between 15 and 62 years revealed statistically significant association between extramarital sex with current age, education, age at first intercourse and sex before marriage. The effect of these variables was tested through a multivariate logistic regression analysis and all the four independent variables were found to be statistically significant predictors of extramarital sex in Mbeya region.
Challenges in Establishing A Cohort-Event Monitoring Drug Safety Study in Ifakara And Rufiji HDSS
(2011-08) Amuri, Mbaraka; Kigahe, Brown; Njozi, Mustafa; Masanja, Irene M.; Selemani, Majige; Dan, Kajungu; Khatib, Rashid A.; Adounvo, Sharon A.; Abdulla, Salim; Binka, Fred; Dodoo, Alexander
The recommended artemisinin combination therapy (ACT) for treatment of uncomplicated malaria in Tanzania is artemether-lumefantrine (AL). Although Artemisinin and its derivatives are generally thought to be safe, there is currently little or no data on its safety among populations in Tanzania. In view of this INESS established a phase IV study to evaluate safety of AL through comprehensive pharmacovigilance in large populations with the aim of documenting rare adverse drug reactions and to characterize known effects in ‘real-life’. The methodology employed is cohort event monitoring which is observational, longitudinal and prospective. Patients with diagnosis of malaria for whom AL was prescribed were recruited into the cohort from four health facilities in each HDSS. Information on demographics, use of all medicines, mode of diagnosis of malaria, presenting signs and symptoms, co-diagnoses, events suspected as adverse drug reactions, reasons for stopping the drug and cause of death (if any) were collected using standardized questionnaire. They were followed up on 7 to 10 days after AL was dispensed. This report is on the number recruited so far and the challenges in getting the cohort going. 9028 patients were recruited. 9016 (99.8%) completed follow-up on day 7, of which 668 (7.4%) were done by telephone calls. 12 (0.13%) were lost during follow-up. The main challenges encountered are getting enough trained staff to recruit and follow up patients since CEM is quite labour intensive. 38 health providers and 10 field workers were recruited and offered the relevant training in collaboration with regulatory authorities. This helped to overcome the human resource challenge. Another challenge involved is the difficult to reach areas which are cut off especially during the rainy season. Follow up by telephone was adopted for these areas and this helped to reduce number of lost to follow-up. Setting up a cohort event monitoring program takes time and is demanding in terms of human resource. Training is very important in overcoming this. Involvement of all stakeholders and sponsors is a key to success

Browse

Browsing Department of Statistics by Issue Date

Results Per Page

Sort Options