Nepalese Journal of Statistics

Inverse Exponentiated Odd Lomax Exponential Distribution: Properties and Applications

Arun Kumar Chaudhary, Lal Babu Sah Telee, Vijay Kumar — Tue, 27 Dec 2022 00:00:00 +0000

Mentioned in manuscript abstract.

Impact of the Targeted Extension Program on Rice Productivity in Tamil Nadu, India

Parijat Ghosh, Suresh Babu, Deepayan Debnath, Khyam Paneru — Tue, 27 Dec 2022 00:00:00 +0000

Background: Based on a randomized experiment by treating one group of farmers with an extension package and the other group as usual in Thanjavur district of Tamil Nadu, India, we examined the impact of the targeted extension package on farmers’ rice yield.

Objective: The objective of the study was to investigate whether the chosen targeted extension package would significantly increase farmers’ rice yields or not.

Materials and Methods: We estimated a multiple linear regression model to determine the effect of several independent variables, including plot size, amount of money borrowed, and farmers’ income on the rice yield.

Results: We found that the rice yield among the farmers who received the extension package had increased compared to the group of farmers with no extension support. The regression coefficient of extension (1 = yes, 0 = no) is statistically significant (p-value = 0.063) at a 10% level of significance.

Conclusion: Assessing the impact of the targeted extension package on the farmers is important in utilizing good agricultural practices to increase rice productivity. We concluded that a targeted extension program is crucial for increasing rice yield among rural farmers in Southern India.

Keywords: Farm income, randomized control trial, rice yield, southern India, targeted extension.

Burden of Respiratory Diseases Attributable to Household Air Pollution in Nepal: National and Provincial Estimates

Srijan Lal Shrestha — Tue, 27 Dec 2022 00:00:00 +0000

Background: Household air pollution (HAP) is widespread in Nepal particularly in rural poor households where use of unprocessed biomass fuels (wood, animal dung and crop residues) for cooking is abundant. Studies have shown that health effects associated with HAP are primarily respiratory and cardiovascular diseases which are amongst the top burden of diseases in Nepal.

Objective: The study is conducted to estimate Attributable Fraction (AF) and corresponding Attributable Burden (AB) of diseases such as childhood pneumonia, acute respiratory infection/pneumonia and COPD/asthma which can be associated with HAP in Nepal, nationally and sub-nationally.

Materials and Methods: Estimates on fuel use in Nepal disaggregated by rural and urban areas and provinces are obtained from Nepal Multiple Indicator Cluster Survey (NMICS), 2019 published by Central Bureau of Statistics (CBS). The corresponding total disease burdens of Nepal related to respiratory diseases are obtained from the Department of Health Services (DoHS) for 2019/20. Estimates of model coefficients of the targeted respiratory diseases that can be attributed to HAP are obtained from several studies conducted previously in Nepal. Methodology adopted by World Health Organization (WHO) for estimation of AF and AB is applied in the present analysis.

Results: The estimated AF and AB of childhood pneumonia, ARI/pneumonia and COPD/asthma are obtained as 34.6% (95% CI = 7.4%-56.4%) and 7.3 (96% CI = 1.5-11.8) per 1000 under five children, 42.5% and 63.6 per 1000 population and 54.8% and 10.3 per 1000 population, respectively. AFs are found substantially higher (1.3-1.5 times) in rural Nepal compared to urban Nepal. Provincially, Karnali is found worst affected with highest attributions (45.3% - 65.6%) for the accounted burden of diseases and Bagmati found least affected with lowest attributions (18.7% - 34.6%) for the year 2019/20.

Conclusion: HAP is found to be a potential risk factor with high attributions for the occurrence of respiratory ailments in Nepal.

Inverse Exponentiated Odd Lomax Exponential Distribution: Properties and Applications

Arun Kumar Chaudhary, Lal Babu Sah Telee, Vijay Kumar — Tue, 27 Dec 2022 00:00:00 +0000

Background: New family of distributions has important functions in generalization of distributions by modifying some existing distributions for getting more flexible irrespective to applied and practical view point. The Inverse Exponentiated Odd Lomax Exponential Distribution (IEOLE) having four parameters is suggested. Proposed model is based on T-X family of distribution which is the extended form of beta-generated distribution. Based on the LSE, MLE, and CVM methods, the parameters of the proposed distribution are estimated. Different model validation criteria and model comparisons are done by considering other existing models.

Materials and methods: IEOLE is compound distribution derived by using theoretical concept of Odd Lomax Exponential distribution and T-X family of distribution. The parameters of the proposed distribution are estimated through the least square, Cramer–Von Mises and maximum likelihood methods. The applicability of the proposed model is evaluated using R programming on two real-life time data sets.

Results: The statistical properties and different characteristics like the hazard rate function, the cumulative distribution function, quantile function, skewness, and kurtosis of the proposed model are discussed. Box plots, TTT plot, density fits etc. shows that the proposed model fits better to considered two real data sets. Different model validation criteria such as AIC, BIC, and CAIC are obtained and compared with some existing well-known probability distributions.

Conclusion: This study presents new probability model called Inverse Exponentiated Odd Lomax Exponential distribution. The density curves of the model show that it is unimodal having right skewed. The suggested model has proven to be versatile for modeling real-world data due to its increasing-decreasing, right-skewed form. Also, the hazard rate function (HRF) graph is decreasing, decreasing-increasing or inverted bathtub shaped according to the value of the model constants. Different validation criteria show that the suggested model fits data well and the goodness-of-fit shows that proposed model has lesser test statistic value and higher p- value with respect to some existing models.

A Comparison of Trend Models for Predicting Tea Production in Bangladesh

K. R. Das, N. Sultana, P. K. Karmokar, M. N. Hasan — Tue, 27 Dec 2022 00:00:00 +0000

Background: Tea (Camellia sinensis) is a manufactured popular beverage that is mostly consumed around the globe including Bangladesh. Tea consumptions are increasing day by day due to its healthcare effects in the world as well as in Bangladesh. To meet the ever-growing population’s demand in Bangladesh, it is important to predict the production of tea.

Objective: Although it is found in the literatures that studies have examined different trend models for tea and agricultural crops, no such study has been found to choose best trend model for predicting the production of tea in Bangladesh. Therefore, an attempt is made to identify the best trend model based on different model selection criterion for the prediction of tea production in Bangladesh.

Materials and Methods: Six trend models namely linear, logarithmic, inverse, quadratic, cubic, and compound were applied on tea production dataset (1976 to 2020) collected from the Food and Agriculture Organization Corporate Statistical Database (FAOSTAT) website. For justification of the model, different model section criteria have been checked.

Results: The results showed that the compound trend model is the most suitable among considered trend models for predicting the tea production in Bangladesh. Finally, the yearly growth rate of tea production for the period from1976 to 2020 found the compound growth rate of tea production in Bangladesh as 1.02 per year. It is important to note that for the next five years, forecasted increasing rate could be 4840.91 tonnes for the yearly tea production of Bangladesh. Furthermore, remarkable increased progresses of production have been noticed as 23585.7 and 21691.01 tonnes, respectively for the years 2019 and 2020 by the re-estimated model due to the proper nourishing and maintaining the input supply chain from government ends.

Conclusion: In the respect of the growing demand, the best-fitted trend model applied herewith through outlier checking and related sophisticated justification tools on the tea production area could help to accumulate knowledge for the practitioner.

On the Use of Logistic Regression Model and its Comparison with Log-binomial Regression Model in the Analysis of Poverty Data of Nepal

Krishna Prasad Acharya, Shankar Prasad Khanal, Devendra Chhetry — Tue, 27 Dec 2022 00:00:00 +0000

Background: Previous literatures have indicated that log-binomial regression model is an alternative for the logistic regression model for frequent occurrence of event of outcome. The comparison of the performance of these two models has been found with reference to clinical/epidemiological data. Nonetheless, the application of log-binomial model and its comparison with the logistic model for poverty data has not been described.

Objective: To compare logistic and log-binomial regression model in terms of variable selection, effect size, precision of effect size, goodness of fit, diagnostics, stability of the model, and the issue of failure convergence.

Materials and Methods: Cross sectional data of 5988 households of Nepal Living Standard Survey 2010/11 has been used for the analysis. The performance of logistic and log-binomial model has been compared in terms of variable selection, effect size, and its precision for each covariate, goodness of fit using Hosmer - Lemeshow (H-L) test, diagnostics of the model, stability of the model using bootstrapping method, and the issue of failure convergence.

Results: Logistic model overestimates the effect size, yields wider 95% confidence interval than that of log - binomial model for each covariate. The greater elevation in risk for covariates varies from 13% to 173%. Logistic model satisfies goodness of fit of the model (p = 0.534), diagnostics tests, and stability of the model. However, log-binomial model grossly violates the goodness of fit of the model (p = 0.0004) but satisfies the model diagnostics and stability criteria.

Conclusion: Log-binomial model satisfies all criteria for model development and diagnostics except gross violation in goodness of fit of the model. However, logistic regression model satisfies all the criteria including goodness of fit of the model. On the basis of the entire comparison of model performance, logistic regression model is better fitted than the log-binomial model in fitting the poverty data set of Nepal.