In this paper, we explore the application of hidden Markov model (HMM) in the modeling of agricultural price data. Normal hidden Markov model is fitted and compared with univariate autoregressive moving average (ARMA) model. The parameters of the model are estimated using EM algorithm and the sequence of hidden states are obtained based on the best fitted model.
{"title":"Modeling of Agricultural Price Data Using Hidden Markov Model","authors":"George Joshni, Thomas Seemon","doi":"10.12785/IJCTS/060103","DOIUrl":"https://doi.org/10.12785/IJCTS/060103","url":null,"abstract":"In this paper, we explore the application of hidden Markov model (HMM) in the modeling of agricultural price data. Normal hidden Markov model is fitted and compared with univariate autoregressive moving average (ARMA) model. The parameters of the model are estimated using EM algorithm and the sequence of hidden states are obtained based on the best fitted model.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116617648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
For modelling the directional spectra of ocean waves, Cartwright introduced a power-of-cosine circular distribution, (cf. Cartwright, D. E. (1963), “The use of directional spectra in studying the output of a wave recorder on a moving ship, In Ocean Wave Spectra”, pages 203—218, Prentice Hall, New Jersey). Some distributional properties of the Cartwright’s power-of-cosine circular distribution will be discussed in this paper. Based on these properties, some characterizations of this distribution will be given using the truncated moment, order statistics and record values.
{"title":"On the Cartwright Power-of-Cosine Circular Distribution CPC- Some Distributional Properties and Characterizations","authors":"M. Shakil, M. Ahsanullah, K. Golam","doi":"10.12785/IJCTS/060109","DOIUrl":"https://doi.org/10.12785/IJCTS/060109","url":null,"abstract":"For modelling the directional spectra of ocean waves, Cartwright introduced a power-of-cosine circular distribution, (cf. Cartwright, D. E. (1963), “The use of directional spectra in studying the output of a wave recorder on a moving ship, In Ocean Wave Spectra”, pages 203—218, Prentice Hall, New Jersey). Some distributional properties of the Cartwright’s power-of-cosine circular distribution will be discussed in this paper. Based on these properties, some characterizations of this distribution will be given using the truncated moment, order statistics and record values.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123918443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A new median ranked set sampling procedure for positively skew distributions (NMRSSS) is proposed and used to estimate population mean. The estimators based on the proposed scheme are compared with the estimators based on ranked set sampling (RSS), median ranked set sampling (MRSS) and new median ranked set sampling (NMRSS) procedures. It is shown that the relative precisions of the estimators based on NMRSSS are higher than the estimators based on RSS, MRSS and NMRSS procedures.
{"title":"New Median Ranked Set Sampling for Skew Distributions","authors":"Kushary Debashis, B. Kibria, Bhoj Dinesh S.","doi":"10.12785/IJCTS/060102","DOIUrl":"https://doi.org/10.12785/IJCTS/060102","url":null,"abstract":"A new median ranked set sampling procedure for positively skew distributions (NMRSSS) is proposed and used to estimate population mean. The estimators based on the proposed scheme are compared with the estimators based on ranked set sampling (RSS), median ranked set sampling (MRSS) and new median ranked set sampling (NMRSS) procedures. It is shown that the relative precisions of the estimators based on NMRSSS are higher than the estimators based on RSS, MRSS and NMRSS procedures.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127736707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The time to failure of a product is considered as a quality characteristic of following Log-Logistic distribution (β = 3). Control limits are evaluated for the time to failure. Life time data are compared with the control limits to judge the quality performance of the product.
{"title":"Time Control Chart – Log Logistic Distribution","authors":"B. Sriram, A. Suhasini, Kantam Rrl","doi":"10.12785/IJCTS/060111","DOIUrl":"https://doi.org/10.12785/IJCTS/060111","url":null,"abstract":"The time to failure of a product is considered as a quality characteristic of following Log-Logistic distribution (β = 3). Control limits are evaluated for the time to failure. Life time data are compared with the control limits to judge the quality performance of the product.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115707777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we have proposed two logproduct -type estimators and a new estimator for estimation of finite population mean under measurement error by using auxiliary information. The expressions for Bias and mean squared error of proposed estimators are evaluated up to first order of approximation. Based on theoretical results obtained, a numerical study by generating Normal population using R programming language is also included to compare the efficiency of proposed estimators with other relevant estimators.
{"title":"Estimation of Finite Population Mean Under Measurement Error","authors":"S. Rajesh, Mishra Prabhakar, Khare Supriya","doi":"10.12785/IJCTS/060108","DOIUrl":"https://doi.org/10.12785/IJCTS/060108","url":null,"abstract":"In this paper, we have proposed two logproduct -type estimators and a new estimator for estimation of finite population mean under measurement error by using auxiliary information. The expressions for Bias and mean squared error of proposed estimators are evaluated up to first order of approximation. Based on theoretical results obtained, a numerical study by generating Normal population using R programming language is also included to compare the efficiency of proposed estimators with other relevant estimators.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122281231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Software usage has been dealing major parts in all the activities of individuals as well as organizations. Software users expecting the good and reliable software. There are many approaches in Software reliability studies probabilistic and nonprobabilistic approaches. Zhang and Pham (2000) defined third two environmental factors for studying the reliability of software and categorized them into five groups. Later they proposed to use information about three principal components extracted from ten environmental factors. It causes loss of information about the remaining twenty-two factors, two more environmental factors have been recommended as significant factors in a subsequent literature for studying the reliability of software. This paper proposes a methodology to use the information about all the thirty-four factors through principal components reducing the volume of information with less amount of loss of information. Information gained from the different stages of PCs is compared with Shannon Information measure.
{"title":"Naive Principal Component Analysis in Software Reliability Studies","authors":"A. Loganathan, Muthuraj R Jeromia","doi":"10.12785/IJCTS/060104","DOIUrl":"https://doi.org/10.12785/IJCTS/060104","url":null,"abstract":"Software usage has been dealing major parts in all the activities of individuals as well as organizations. Software users expecting the good and reliable software. There are many approaches in Software reliability studies probabilistic and nonprobabilistic approaches. Zhang and Pham (2000) defined third two environmental factors for studying the reliability of software and categorized them into five groups. Later they proposed to use information about three principal components extracted from ten environmental factors. It causes loss of information about the remaining twenty-two factors, two more environmental factors have been recommended as significant factors in a subsequent literature for studying the reliability of software. This paper proposes a methodology to use the information about all the thirty-four factors through principal components reducing the volume of information with less amount of loss of information. Information gained from the different stages of PCs is compared with Shannon Information measure.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129621821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, exponential ratio and product type estimators for population mean of study character using known population proportion of auxiliary attribute in the presence of non-response have been proposed. The expressions for the mean square error of the proposed estimators have been obtained. The proposed estimators have been compared with the relevant estimators. The empirical studies have been done to demonstrate the efficiency of the proposed estimators over other relevant estimator.
{"title":"Estimation of Population Mean Using Auxiliary Attribute in The Presence Of Non-Response","authors":"K. Kamlesh, K. Anupam","doi":"10.12785/IJCTS/060106","DOIUrl":"https://doi.org/10.12785/IJCTS/060106","url":null,"abstract":"In this paper, exponential ratio and product type estimators for population mean of study character using known population proportion of auxiliary attribute in the presence of non-response have been proposed. The expressions for the mean square error of the proposed estimators have been obtained. The proposed estimators have been compared with the relevant estimators. The empirical studies have been done to demonstrate the efficiency of the proposed estimators over other relevant estimator.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126699711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The study of a multicompnent system with k identical components which are independent to each other is considered in the present work. The components of the system have series structure with two dependent elements that are exposed to a common random stress. Here, strength vectors follow bivariate generalized Rayleigh distribution and a common random stress follow generalized Rayleigh distribution. The s-out-of-k system is said to function if atleast s out of k(1 ≤ s ≤ k) strength variables exceed the random stress. The estimation of system reliability is studied using maximum likelihood and Bayesian approaches. The maximum likelihood estimates are derived under simple random sampling and ranked set sampling schemes. The approximate Bayes estimates for system reliability are obtained using Lindley's approximation technique. Simulation study is conducted to study the performance of the estimators of reliability using mean squares error criteria.
{"title":"Estimation of Multicomponent System Reliability for a Bivariate Generalized Rayleigh Distribution","authors":"Parameshwar v.Pandit, Joshi Shubhashree","doi":"10.12785/IJCTS/060107","DOIUrl":"https://doi.org/10.12785/IJCTS/060107","url":null,"abstract":"The study of a multicompnent system with k identical components which are independent to each other is considered in the present work. The components of the system have series structure with two dependent elements that are exposed to a common random stress. Here, strength vectors follow bivariate generalized Rayleigh distribution and a common random stress follow generalized Rayleigh distribution. The s-out-of-k system is said to function if atleast s out of k(1 ≤ s ≤ k) strength variables exceed the random stress. The estimation of system reliability is studied using maximum likelihood and Bayesian approaches. The maximum likelihood estimates are derived under simple random sampling and ranked set sampling schemes. The approximate Bayes estimates for system reliability are obtained using Lindley's approximation technique. Simulation study is conducted to study the performance of the estimators of reliability using mean squares error criteria.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116458443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, a generalization of generalized gamma distribution(GGGD) ,which includes the three-parameter generalized gamma distribution, two-parameter Weibull and gamma distributions, and exponential distribution as special cases, has been suggested and studied. The hazard rate function and the stochastic ordering of the distribution have been discussed. Maximum likelihood estimation has been discussed for estimation of parameters. Applications of the proposed distribution have been discussed with two real lifetime datasets and the goodness of fit shows quite satisfactory over generalized gamma, gamma, Weibull, and exponential distributions.
{"title":"A Generalization of Generalized Gamma Distribution","authors":"S. Rama, Shukla Kamlesh Kumar","doi":"10.12785/IJCTS/060105","DOIUrl":"https://doi.org/10.12785/IJCTS/060105","url":null,"abstract":"In this paper, a generalization of generalized gamma distribution(GGGD) ,which includes the three-parameter generalized gamma distribution, two-parameter Weibull and gamma distributions, and exponential distribution as special cases, has been suggested and studied. The hazard rate function and the stochastic ordering of the distribution have been discussed. Maximum likelihood estimation has been discussed for estimation of parameters. Applications of the proposed distribution have been discussed with two real lifetime datasets and the goodness of fit shows quite satisfactory over generalized gamma, gamma, Weibull, and exponential distributions.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124332724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Classification of objects is an important problem that has received the attention of several researchers in Data Mining. Necessity for classification of an object into one of the predefined classes arises in several domains of research which include market research, document classification, diagnosing the presence of disease etc. A widely studied and applied popular classifying method which has attracted many data mining researchers is k-nearest neighbor algorithm. It is a distance based algorithm in which classification of an object is done on the basis of the memberships of its neighboring objects. The main problem one faces in the application classification is deciding a suitable value for the neighborhood parameter. In this paper, a method similar to classification in which the number of neighbors to be used in the classification process is determined by the distribution of distances between units in the training set has been proposed. Performance of the proposed method has been studied using simulated multivariate normal data sets as well as some benchmark data sets.
{"title":"Quantiles based Neighborhood Method of Classification","authors":"S. Sampath, S. Suresh","doi":"10.12785/IJCTS/060101","DOIUrl":"https://doi.org/10.12785/IJCTS/060101","url":null,"abstract":"Classification of objects is an important problem that has received the attention of several researchers in Data Mining. Necessity for classification of an object into one of the predefined classes arises in several domains of research which include market research, document classification, diagnosing the presence of disease etc. A widely studied and applied popular classifying method which has attracted many data mining researchers is k-nearest neighbor algorithm. It is a distance based algorithm in which classification of an object is done on the basis of the memberships of its neighboring objects. The main problem one faces in the application classification is deciding a suitable value for the neighborhood parameter. In this paper, a method similar to classification in which the number of neighbors to be used in the classification process is determined by the distribution of distances between units in the training set has been proposed. Performance of the proposed method has been studied using simulated multivariate normal data sets as well as some benchmark data sets.","PeriodicalId":373764,"journal":{"name":"International Journal of Computational and Theoretical Statistics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128235713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：