for Journals by Title or ISSN
for Articles by Keywords
help
Journal Cover Research & Reviews : Journal of Statistics
  [4 followers]  Follow
    
   Full-text available via subscription Subscription journal
   ISSN (Print) 2348-7909 - ISSN (Online) 2278-2273
   Published by STM Journals Homepage  [67 journals]
  • Marshall-Olkin Generalized Family of Distributions: A Retrospect
    • Authors: Sophia P. Thomas, K. K. Jose, Lishamol Tomy
      Abstract: This paper reviews works on Marshall-Olkin extended family of distributions. Available literature shows that this generalization is flexible enough to model different types of lifetime data having different forms of failure rate. Models of the Marshall-Olkin family such as exponential, Weibull, Pareto, Lomax etc. are discussed and additional literature on these families of distributions are provided. Many extensions and generalizations of Marshall-Olkin family of distributions are also discussed.  Keywords: Compounding, characteristic function, geometric extreme stability, Harris family, Marshall-Olkin family, reliabilityThomas Sophia P, Jose KK, Lishamol Tomy. Marshall-Olkin Generalized Family of Distributions: A Retrospect. Research & Reviews: Journal of Statistics. 2017; 6(2): 35–49p.
      PubDate: 2017-09-06
      Issue No: Vol. 6 (2017)
       
  • Selection of Appropriate Artificial Neural Network Model for Predicting
           Monthly Exchange Rate (Taka per US Dollar)
    • Authors: Md. Asraful Alam, Md. Siddikur Rahman, Md. Shahajada Mia
      Abstract: The aim of this paper is to find an appropriate model of Artificial Neural Networks (ANN) for forecasting monthly exchange rate of BDT against US Dollar. Empirical results suggest that neural network model fits the exchange rate well and it is capable of forecasting the future trend of the exchange rate movement. According to the minimum in sample criteria, neural network models NN (1, 1), NN (1, 2), NN (1, 3) and NN (1, 4) are estimated. From the estimated models, we select NN (1, 2) model considering the lowest values of AIC, BIC, highest values of adjusted and summary measures of a model’s forecast accuracy: RMSE, MAE and MAPE, Z and r. This justifies the selection of Artificial Neural Network model (1, 2) as the best one in forecasting BDT/USD exchange rate.  Keywords: Forecasting, exchange rate, artificial neural network Cite this Article
      Md. Asraful Alam, Md. Shahajada Mia,
      Md. Siddikur Rahman. Selection of
      Appropriate Artificial Neural Network
      Model for Predicting Monthly Exchange
      Rate (Taka per US Dollar). Research &
      Reviews: Journal of Statistics. 2017;
      6(2): 30–34p.


      PubDate: 2017-08-30
      Issue No: Vol. 6 (2017)
       
  • A Time Series Analysis on Demand of Electricity in Nepal
    • Authors: Chandra Kanta Subedi, Ram Prasad Khatiwada
      Abstract: This study is carried out to evaluate the trend of electricity available, consumption, demand, number of consumers and revenue collection in Nepal from 1994 to 2016. In this work, autoregressive integrated moving average (ARIMA) model is fitted to study the electricity demand in the country on the basis of available data. The time series modeling technique (ARIMA Model) is used for the electricity demand to demonstrate the effect of lag value and find the trend value from moving average. Model adequacy is tested with normality test, heteroscedasticity test, and goodness of fit and ensured into satisfactory result. The predicted value of electricity demand is computed for some next years, based on the final fitted model. From the analysis we observed the average trend of electricity demand, consumption, availability and revenue collection, all in increasing order. Keywords: ARIMA model, heteroscedastity test, normality test, energy surplusCite this Article Chandra Kanta Subedi, Ram Prasad Khatiwada. A Time Series Analysis on Demand of Electricity in Nepal. Research & Reviews: Journal of Statistics. 2017; 6(2): 21–29p. 
      PubDate: 2017-08-19
      Issue No: Vol. 6 (2017)
       
  • Seasonal ARIMA Modeling and Forecasting of Rainfall in Rajshahi District,
           Bangladesh
    • Authors: Md. Binyamin, Md. Takrib Hossain, Sayed Mohibul Hossen
      Abstract: The main focus of this research is to find time series model and forecast on climate data of rainfall in Rajshahi district in Bangladesh for the period of January, 1964 to June, 2014. The secondary data were collected from Bangladesh Agricultural Research Council (BARC) for the purpose of model identification and forecast up to the year 2020 of the identified model. To test the stationarity of the series graphical method, correlogram and unit root test were used. The time series plot shows that the series has slightly downward trend. From the autocorrelation function (ACF) and partial autocorrelation function (PACF) it was found that there is a seasonal effect in the data. Akaike information criterion (AIC) is used for model selection. Box-Jenkins methodology is also used for model selection and forecasting. The chosen model was seasonal autoregressive integrated moving average (SARIMA). For residual diagnostics, correlogram Q-statistic and histogram and normality test were used. Also, Chow test was used for stability testing. Using model selection criterion and checking model adequacy, it is found that the model is suitably in shape. For the forecast period from July 2014 to December 2020, the maximum rainfall of Rajshahi is in the month of June and July, which is the rainy season in our country. On an average, the maximum rainfall of Rajshahi is 14 mm in the month of July. The maximum rainfall of Rajshahi will be14.82 mm in the month of July in 2020. Keywords: Correlogram, unit root test, PACF, ARIMA, SARIMA, rainfall, AICCite this Article Md. Binyamin, Md. Takrib Hossain, Sayed Mohibul Hossen. Seasonal ARIMA Modeling and Forecasting of Rainfall in Rajshahi District, Bangladesh. Research & Reviews: Journal of Statistics. 2017; 6(2): 8–20p.
       
      PubDate: 2017-08-19
      Issue No: Vol. 6 (2017)
       
  • Clustering of Pre-monsoon Precipitation of Bangladesh—A Ward’s
           Hierarchical Agglomerative Clustering Approach
    • Authors: Md. Habibur Rahman
      Abstract: In this study, the Ward’s hierarchical agglomerative clustering algorithm applies to predict the homogeneous regions and years on the basis of pre-monsoon precipitation of Bangladesh. The thirty-four locations and the years 1973 to 2014 for pre-monsoon precipitation are presented by cluster dendrogram. The cluster results found six homogeneous clusters for the precipitations of 34 locations and eight homogeneous clusters for the precipitations of 42 years in Bangladesh. Keywords: Euclidean distance, dendrogram, precipitationCite this Article Md. Habibur Rahman. Clustering of Pre-monsoon Precipitation of Bangladesh—A Ward’s Hierarchical Agglomerative Clustering Approach. Research & Reviews: Journal of Statistics. 2017; 6(2): 1–7p.
       
      PubDate: 2017-07-26
      Issue No: Vol. 6 (2017)
       
  • Optimization of Job-Shop Scheduling Problem for Calculating Makspan using
           Modified TLBO Method
    • Authors: M.S. Kagthara, M.G. Bhatt
      Abstract: The paper presents the method for optimization of job shop scheduling problem, the mathematical model developed in the recent article has been used for optimization of makspan. TLBO (teaching–learning based optimization) is advanced method of optimization which is used for optimization with some modification. Here discrete generation has been created for the solution of job shop scheduling problem. The results are compared with benchmark problems and GT algorithm is also used for comparisons.   Keywords: Job-Shop Scheduling, TLBO method, Makspan, GT algorithmCite this Article Kagthara MS, Bhatt MG. Optimization of Job-Shop Scheduling problem for calculating makspan using modified TLBO method. Research & Reviews: Journal of Statistics. 2017; 6(1): 33–37p. 
      PubDate: 2017-05-12
      Issue No: Vol. 6 (2017)
       
  • A Law of Iterated Logarithm for Delayed Random Sums
    • Authors: Gooty Divanji
      Abstract: Let be a sequence of independent identically distributed random variables with a common distribution function F and let , n ³ 1. When F belongs to the domain of attraction of a stable law with index a, 0 < a < 2, Chover's form of the law of the iterated logarithm has been obtained for delayed random sums.   MSC 2000 Subject Classification: 60F15 Keywords: Delayed sums, Delayed random sums, Law of iterated logarithm, Domain of attraction, Stable LawCite this Article Gooty Divanji. A Law of Iterated Logarithm for Delayed Random Sums. Research & Reviews: Journal of Statistics. 2017; 6(1): 24–32p. 
      PubDate: 2017-05-12
      Issue No: Vol. 6 (2017)
       
  • Measuring Risk Attitudes and Time Preference in Rotating Saving Credit
           Associations
    • Authors: Indu Choudhary
      Abstract: A rotating saving credit association, popularly known as ‘Rosca’, is a financial mechanism functioning over a fixed period of time. It involves formation of a group of people contributing fixed amounts of money to a pre-determined pool every period. Each participant either through draw of lots or bidding is entitled to the rosca pot in a given round. The rosca cycle ends when each person in the group has received the pot. The uniqueness of rosca as a financial instrument lies in its dual role of a saving and a credit instrument. This paper analyzes the role of risk attitudes and time preferences in discount bidding roscas. The data for the study comes from roscas organized in two urbanized villages of the national capital territory of Delhi. Using a risk-time preference experiment on rosca participants, the paper employs non-linear least squares estimation to elicit risk and time preference parameters for participants of discount bidding roscas in the sample. Keywords: Roscas, risk, time preference, experiments, non-linear Cite this Article Indu Choudhary. Measuring Risk Attitudes and Time Preference in Rotating Saving Credit Associations. Research & Reviews: Journal of Statistics. 2017; 6(1): 18–23p. 
      PubDate: 2017-05-12
      Issue No: Vol. 6 (2017)
       
  • The Causes of Smoking and Smoking Related Factors in Santosh a Rural Area
           in Tangail District, Bangladesh: A Case Study
    • Authors: Md. Binyamin, Md. Ramjan Ali, Shayla Naznin, Md. Soyebur Rahman
      Abstract: This study was conducted to identify the causes of smoking and starting age of smoking. To assess these factors, both bivariate and univariate analyses were performed. Bivariate analysis shows that educational qualification and from where you bought the first cigarette, educational qualification and smoking is harmful for health, occupation and smoking is addiction are highly significant. Bivariate analysis shows that monthly income and daily cost for smoking, occupation and smoking is harmful for health, occupation and smoking increases death risk are significant. Bivariate analysis shows that the habits of smoking whose occupation is service holder, small shopkeeper, businessman, day laborer and agriculture is more than whose occupation is students and they think smoking is harmful for health. Keywords: Smoking, tobacco, rural area, Tangail district, BangladeshCite this Article Md. Binyamin, Md. Ramjan Ali, Shayla Naznin, et al. The Causes of Smoking and Smoking Related Factors in Santosh a Rural Area in Tangail District, Bangladesh: A Case Study. Research & Reviews: Journal of Statistics. 2017; 6(1): 5–17p.
       
      PubDate: 2017-04-11
      Issue No: Vol. 6 (2017)
       
  • The Binormal ROC Curve and it’s Area Under the Curve (AUC): Made
           Simple
    • Authors: Ehtesham Hussain
      Abstract: In the field of biomedical diagnostic tests, receiver operating characteristic (ROC) curve and its summary measure has become the standard tools for this purpose and their use becoming increasingly common in other fields such as, biosciences, geosciences, experimental psychology, psychology, atmospheric sciences, finance, machine leering and sociology. Focusing on biomedical field, frequently a plot made of sensitivity (True positive rate; TPR) and (One-minus specificity; False positive rate; FPR) as the threshold to ranges overall possible values, such plot is called an ROC curve. Assessment of the performance of diagnosis test can be achieved by: (a) ROC curve, (b) Area under curve (AUC). Among practitioners most widely used is the, binormal ROC curve, which is a theoretical and a classical model. However, the expressions for ROC curve and AUC are not transparent because of appearance of certain integrals, which make its computations cumbersome for practitioners. In this note, we investigate some easy approximations, useful for practitioners available in the literature to cope with these mathematical difficulties. Keywords: Area under curve (AUC), binormal ROC curve, distribution function, sensitivity, specificityCite this Article Ehtesham Hussain. The Binormal ROC Curve and it’s Area Under the Curve (AUC): Made Simple. Research & Reviews: Journal of Statistics. 2017; 6(1): 1–4p.
       
      PubDate: 2017-04-11
      Issue No: Vol. 6 (2017)
       
 
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
 
Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs
Your IP address: 54.81.131.189
 
About JournalTOCs
API
Help
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-2016