Nepalese Journal of Statistics Nepalese Journal of Statistics is the official journal of the Central Department of Statistics, Tribhuvan University, Kirtipur, Nepal. en-US <p>© Central Department of Statistics, Tribhuvan University, Kirtipur, Kathmandu, Nepal</p><p>The author of article must sign the copyright permission or the author must assign copyright to the Central Department of Statistics, Tribhuvan University prior to publication.</p><p>All rights reserved.</p> (Shankar Prasad Khanal, PhD) (Sioux Cumming) Wed, 18 Sep 2019 18:44:33 +0000 OJS 60 Have You Seen the Standard Deviation? <p><strong>Background:</strong> Sarkar and Rashid (2016a) introduced a geometric way to visualize the mean based on either the empirical cumulative distribution function of raw data, or the cumulative histogram of tabular data.</p> <p><strong>Objective:</strong> Here, we extend the geometric method to visualize measures of spread such as the mean deviation, the root mean squared deviation and the standard deviation of similar data.</p> <p><strong>Materials and Methods:</strong> We utilized elementary high school geometric method and the graph of a quadratic transformation.</p> <p><strong>Results:</strong> We obtain concrete depictions of various measures of spread.</p> <p><strong>Conclusion:</strong> We anticipate such visualizations will help readers understand, distinguish and remember these concepts.</p> Jyotirmoy Sarkar, Mamunur Rashid ##submission.copyrightStatement## Mon, 16 Sep 2019 00:00:00 +0000 A Generalised Exponential-Lindley Mixture of Poisson Distribution <p><strong>Background:</strong> The exponential and the Lindley (1958) distributions occupy central places among the class of continuous probability distributions and play important roles in statistical theory. A Generalised Exponential-Lindley Distribution (GELD) was given by Mishra and Sah (2015) of which, both the exponential and the Lindley distributions are the particular cases. Mixtures of distributions form an important class of distributions in the domain of probability distributions. A mixture distribution arises when some or all the parameters in a probability function vary according to certain probability law. In this paper, a Generalised Exponential- Lindley Mixture of Poisson Distribution (GELMPD) has been obtained by mixing Poisson distribution with the GELD.</p> <p><strong>Materials and Methods:</strong> It is based on the concept of the generalisations of some continuous mixtures of Poisson distribution.</p> <p><strong>Results:</strong> The Probability mass of function of generalized exponential-Lindley mixture of Poisson distribution has been obtained by mixing Poisson distribution with GELD. The first four moments about origin of this distribution have been obtained. The estimation of its parameters has been discussed using method of moments and also as maximum likelihood method. This distribution has been fitted to a number of discrete data-sets which are negative binomial in nature and it has been observed that the distribution gives a better fit than the Poisson–Lindley Distribution (PLD) of Sankaran (1970).</p> <p><strong>Conclusion:</strong> P-value of the GELMPD is found greater than that in case of PLD. Hence, it is expected to be a better alternative to the PLD of Sankaran for similar type of discrete data-set which is negative binomial in nature.</p> Binod Kumar Sah, A. Mishra ##submission.copyrightStatement## Wed, 11 Sep 2019 17:18:41 +0000 Comparison of Cox Proportional Hazards Model and Lognormal Accelerated Failure Time Model: Application in Time to Event Analysis of Acute Liver Failure Patients in India <p><strong>Background:</strong> Different survival analysis techniques such as nonparametric, semi-parametric, parametric Accelerated Failure Time (AFT) models have been generally applied to analyze time to event data. In order to identify the prognostic factors for survival of Acute Liver Failure (ALF) patients, previous studies applied Cox Proportional hazards (CPH) model, Lognormal AFT and Log-Logistic AFT model satisfying respective model’s assumptions and goodness of fit of each model. However, comparison of CPH model and AFT model has not been reported so far for ALF data with short follow up time.</p> <p><strong>Objective:</strong> To compare CPH model and Lognormal AFT model based on different parameters for assessing the model performance and prospective validation of the finally selected model.</p> <p><strong>Materials and Methods:</strong> Altogether 1099 ALF patients’ data from liver clinic of All India Institute of Medical Sciences, New Delhi India were analyzed based on the retrospective cohort study design. For validating the final model, a separate data set of 138 ALF patients from the same clinic was used. CPH model and Lognormal model’s performance was assessed through selection of variables in the final model, R2 type statistic, goodness of fit of the model, visual assessment of Cox-Snell’s residuals plot and robustness of the model. The prospective validation of the over scored CPH model was done by comparing overall survival, regression coefficients, observed and predicted survival curves between original and validation data set.</p> <p><strong>Results:</strong> It is found that 60% of variation in the partial log-likelihood is explained by the CPH model whereas 39% of variation in full log-likelihood is explained by Lognormal AFT model. Cox-Snell residuals plot for CPH model seems less deviated from the line of ideal fit, replications of variables measured through bootstrapping resampling technique in CPH model are on the higher side, model predicted and observed survival curves in each risk stratum were closer than that of Lognormal model. The survival experience of original data and validation data set for CPH model does not seem to be very different (p = 0.07) at 5% level of significance.</p> <p><strong>Conclusion:</strong> Both CPH and Lognormal AFT model are found well fitted and can be applied either of them for this ALF data. While comparing the model performance, the CPH model for the identification of prognostic factors for the survival of ALF patients is found comparatively better.</p> Shankar Prasad Khanal, V. Sreenivas, Subrat K. Acharya ##submission.copyrightStatement## Mon, 16 Sep 2019 00:00:00 +0000 Multinomial Logistic Regression Model to Identify the Factors Associated with Academic Performance of Hearing Impaired Students of Some Selected Districts of Nepal <p><strong>Background:</strong> Education for hearing impaired (HI) students is always challenging for schools, teachers, parents and even for students themselves. For their education, government has established special schools and included them in mainstream school with hearing peers also called integrated school. Although all these efforts for their education, their academic performance is affected by different factors.</p> <p><strong>Objective:</strong> This study is focused to assess factors which affects the academic performance of HI students of Jhapa, Morang and Sunsari districts.</p> <p><strong>Materials and Methods:</strong> This study is a cross-sectional study and based on primary data collected through structured questionnaire. Academic Performance is categorized as Below Average, Average and Good. A sample of 238 HI students from eleven schools of three districts were selected using two stage stratified random sampling methods. Sixty teachers were also chosen for assessing some variables. Data were analyzed using descriptive and inferential statistical methods. To determine the significant factors influencing the academic performance of HI students, Multinomial Logistic Regression (MNLR) model was used.</p> <p><strong>Results:</strong> From the fitted MNLR model, variables like attendance [Odds Ratio (OR) =0.951], type of school (OR=27.39), level of study (OR=4.551), additional handicapping condition (OR=5.202), communication capacity of students (OR=9.477) and instructional material (OR=3.028) are found to be significant in the model Below Average versus Average level of academic performance of HI students. Similarly, the variables like type of school (OR=7.875 and 9.572), level of study (OR= 0.556), purpose of parents' visit (OR= 0.410) and instructional material (OR= 0.304) are found to be significant in the model Good versus Average level of Academic performance of HI students.</p> <p><strong>Conclusion:</strong> The results of the study illustrates that several factors are associated with academic performance of HI students. Concerned authorities are suggested to provide suitable infrastructure, HI students friendly curriculum, special training to teacher and awareness to family, society and hearing peers to improve the academic performance of HI students.</p> Tara Devi Rijal, Gauri Shrestha ##submission.copyrightStatement## Mon, 16 Sep 2019 00:00:00 +0000 Study of Factors Affecting the Entrepreneurship Behavior of Returned Migrants Using Binary Logistic Regression Model <p><strong>Background:</strong> Entrepreneurship or business ownership is a significant source of employment and economic growth. Many studies conducted by different researchers have shown that increase in entrepreneurial activities helps to reduce unemployment. Thousands of Nepalese youths exodus for foreign migration every year for employments due to lack of adequate working environment in Nepal. In this context, identification of significant factors influencing the entrepreneurship behavior of returned migrants could be useful for planner, decision makers, and other concerned authorities.</p> <p><strong>Objective:</strong> To explore the entrepreneurship status of returned migrants and to ascertain the factors influencing the entrepreneurship behavior of returned migrants.</p> <p><strong>Materials and Methods:</strong> This study was based on primary data of 393 returned migrants collected through convenience sampling in Sarawal Rural Municipality of Parasi district, Nepal. People who stayed abroad at least one year and returned during 2010 to 2017 were included in the study. On the basis of Industrial Enterprise Act, 2016a, Nepal, a person who has invested Nepalese rupees five lakh or more in business besides housing and land is considered as an entrepreneur. The response variable is entrepreneurship status and it is defined according to the aforementioned act. Both quantitative and categorical variables were used as predictor variables. Factors associated with entrepreneurship behavior were extracted using Chi-square test and binary logistic regression model.</p> <p><strong>Results:</strong> Out of sample of 393 returned migrants, 137 (34.9%) were entrepreneur and rest 256 (65.1%) were non-entrepreneur. Results showed that for main occupation of household head odds ratio (OR) = 4.008 &amp; confidence interval (CI) = 2.396 to 6.703. Similarly, for educational status of returned migrants OR = 2.650 &amp; CI = 1.599 to 4.392. For the covariate skills learnt at abroad OR = 2.750 &amp; CI = 1.654 to 4.573.</p> <p><strong>Conclusion:</strong> The study revealed that majority of returned migrants were non-entrepreneur. The factors ‘main occupation of household head’, ‘educational status of returned migrant’, ‘remittance received at home per year’ and ‘skills learnt abroad’ are the major determinants behind the entrepreneurship behavior of returned migrants. It is suggested that higher education and adequate skills should be taken before departing from home country so that the migrants can earn more money which will help to start their own businesses once they get back to their home country.</p> Madhav Kumar Bhusal, Hari Prasad Pandey ##submission.copyrightStatement## Mon, 16 Sep 2019 00:00:00 +0000 Linkages between Time to Reach Education Centers, Health Facility Centers, Poverty Status and Geography: A Multivariate Approach <p><strong>Background:</strong> The first, third and fourth goals of SDG are concerned with ending poverty in all its forms everywhere, ensure healthy lives and promote well-being for all at all ages and ensure inclusive and equitable quality education and promote lifelong learning opportunities for all, respectively. Nepal is committed to ensuring all children with access to free, compulsory, and good-quality basic and secondary education in Nepal.</p> <p><strong>Objectives:</strong> This study aims to compare the average time to reach education centers and health facility centers by poverty status and ecological region.</p> <p><strong>Materials and Methods:</strong> This study is based on NLSS 2011 data. In this study two major factors of access to facility namely education and health are considered. Four variables on access to education and three variables on access to health are used. Mean vectors, correlation matrices, and covariance matrices have been computed. The Multivariate Analysis of Variance is used to compare the mean vectors and to check the homogeneity of the variance-covariance matrix using Box's M test. Four tests namely Wilk's Lambda, Lawley- Hoteling trace, Pillai trace and Roy's largest root have been used to compare the mean vectors.</p> <p><strong>Results:</strong> This study has shown that the average time to reach each nearest education center of poor households is higher than non-poor households in each ecological region. The average time to reach the primary school is lowest and highest to reach secondary school in each poverty status and ecological region. The average time to reach the nearest health post is lowest among different health facility centers in each poverty status and ecological region. The p-values of each Box's M and Pillai trace tests are less than 0.0001.</p> <p><strong>Conclusion:</strong> The mean vectors of time to reach the nearest education center are significantly different between poor and non-poor households in each ecological region. The average time to reach the health facility centers is also significantly different in poor and non-poor households within each ecological region.</p> Pravat Uprety ##submission.copyrightStatement## Mon, 16 Sep 2019 00:00:00 +0000