Raghunath Arnab - Academia.edu (original) (raw)
Uploads
Papers by Raghunath Arnab
Statistica, Jun 30, 2014
In this paper, we use the idea of post-stratification based on the respondents' choice of a parti... more In this paper, we use the idea of post-stratification based on the respondents' choice of a particular randomization device in order to estimate the population proportion of a sensitive characteristic. The proposed idea gives full freedom to the respondents and is expected to result in greater cooperation from them as well as to provide some increase in the relative efficiency of the newly proposed estimator.
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
Model Assisted Statistics and Applications, 2015
Australian Journal of Statistics, 1987
ABSTRACT summaryIn this paper strategies based on a two-stage successive sampling scheme are prop... more ABSTRACT summaryIn this paper strategies based on a two-stage successive sampling scheme are proposed for estimating the ratio of the population totals of two characters on the most recent occasion.It is found that the proposed strategies perform better than the standard ratio when used in estimating the ratio of farmers' income to non-farmers' income. But when applied to the estimation of ratio of girth to height of teak trees, a loss in efficiency is observed.
Http Dx Doi Org 10 1080 03610926 2012 731130, Dec 1, 2014
In large-scale surveys, it is common to use a multistage sampling design, where the first-stage u... more In large-scale surveys, it is common to use a multistage sampling design, where the first-stage units are selected with varying probability without replacement and the second-stage units are selected according to the systematic sampling procedure. It is however well known that this sampling design makes it impossible to find unbiased estimate of the variance of the estimate of the population total. In this paper, a few methods of variance estimation in multistage sampling involving systematic sampling design have been proposed to overcome the problem discussed. The proposed variance estimators are compared with the few conventional methods, for example, Random group, Jackknife, as well as the method used by the Central Statistical Office (CSO) using the live data based on Household Income and Expenditure Survey (HIES) 2002/03, Botswana, collected by CSO. It is found that all the proposed methods and Jackknife method perform better than the method used by CSO.
Statistics Probability Letters, Mar 1, 2006
In this paper, the problem of estimation of variance has been considered when the missing data ha... more In this paper, the problem of estimation of variance has been considered when the missing data have been imputed with the ratio method of imputation. Two alternative variance estimators have been proposed. Relative efficiencies of the proposed estimators have been compared with the existing alternative Jackknife estimator proposed by Variance estimation under two-phase sampling with application to imputation for missing data. Biometrika 82, 453-460] through empirical study. Empirical investigation shows that the proposed estimators fare better than the Variance estimation under two-phase sampling with application to imputation for missing data. Biometrika 82, 453-460] estimator. r
Metrika, 1981
... References Bandopadhyaya, S., AK Chattopadhyaya, and S. Kundu : On estimation of population t... more ... References Bandopadhyaya, S., AK Chattopadhyaya, and S. Kundu : On estimation of population total. Sankhys Ser. C 39, 1977, 28-42. ... 3, 1952, 99-107. Rao, JNK, and K. Vi]ayan: On estimating the variance in sampling with probability proportional to aggregate size. Jour. ...
Sankhya, 1982
... Vl(bli) = 8U, Cx(bH, b,f) = 8tf). Page 9. 100 ARIJIT CHAUDHURI AND RAGHUNATH ARtfAB ... The a... more ... Vl(bli) = 8U, Cx(bH, b,f) = 8tf). Page 9. 100 ARIJIT CHAUDHURI AND RAGHUNATH ARtfAB ... The authors gratefully acknowledge several construc tive criticisms by Professor J. Roy that were helpful in preparing this paper. They also wish to thank Dr. Shibdas Bandyopadhyay ...
The generalized regression predictor (greg) is used for the estimation of a finite population tot... more The generalized regression predictor (greg) is used for the estimation of a finite population total when the study variable is well related to the auxiliary variable. Chaudhuri and Roy (1997) provided the lower bound of the mean square error (mse) of variance estimators belonging to a class of nonhomogeneous quadratic unbiased estimators. They also found the optimum variance estimator whose mean square error attains the lower bound. In the present paper, we have shown that the derivation of the lower bound in Chaudhuri and Roy (1997)'s paper is incorrect and their proposed optimal estimator does not attain the lower bound as originally claimed. An example is also provided which contradict the result of Chaudhuri and Roy (1997). Model assisted higher order calibration approach has been proposed to investigate the variance of the regression predictor.
We discovered there is a choice of weights that builds a bridge between the GREG proposed by and ... more We discovered there is a choice of weights that builds a bridge between the GREG proposed by and the linear regression estimator due to while using one auxiliary variable. It gives the same result as given in Singh (2003, 2004, 2006a, 2006b) and for unequal probability sampling by using two calibration constraints in the presence of one auxiliary variable. Thus, these approaches can be considered as alternative to each other while considering use of one auxiliary variable. The bridge developed here reconfirms that the sum of the calibrated weights should be equal to the sum of the design weights in a given sample. The approach by Singh (
Pakistan Journal of Statistics
The problems of estimating the population total in multi-character surveys in varying probability... more The problems of estimating the population total in multi-character surveys in varying probability sampling schemes when the measure of size is not well-related to the study variables have been considered by Rao (1966), Scott and Smith (1969) and Arnab (2001). In the present note, their results are extended for intra class correlation models and general sampling designs.
Communications in Statistics - Theory and Methods, 2015
Statistica, Jun 30, 2014
In this paper, we use the idea of post-stratification based on the respondents' choice of a parti... more In this paper, we use the idea of post-stratification based on the respondents' choice of a particular randomization device in order to estimate the population proportion of a sensitive characteristic. The proposed idea gives full freedom to the respondents and is expected to result in greater cooperation from them as well as to provide some increase in the relative efficiency of the newly proposed estimator.
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
A New Concept for Tuning Design Weights in Survey Sampling, 2016
Model Assisted Statistics and Applications, 2015
Australian Journal of Statistics, 1987
ABSTRACT summaryIn this paper strategies based on a two-stage successive sampling scheme are prop... more ABSTRACT summaryIn this paper strategies based on a two-stage successive sampling scheme are proposed for estimating the ratio of the population totals of two characters on the most recent occasion.It is found that the proposed strategies perform better than the standard ratio when used in estimating the ratio of farmers' income to non-farmers' income. But when applied to the estimation of ratio of girth to height of teak trees, a loss in efficiency is observed.
Http Dx Doi Org 10 1080 03610926 2012 731130, Dec 1, 2014
In large-scale surveys, it is common to use a multistage sampling design, where the first-stage u... more In large-scale surveys, it is common to use a multistage sampling design, where the first-stage units are selected with varying probability without replacement and the second-stage units are selected according to the systematic sampling procedure. It is however well known that this sampling design makes it impossible to find unbiased estimate of the variance of the estimate of the population total. In this paper, a few methods of variance estimation in multistage sampling involving systematic sampling design have been proposed to overcome the problem discussed. The proposed variance estimators are compared with the few conventional methods, for example, Random group, Jackknife, as well as the method used by the Central Statistical Office (CSO) using the live data based on Household Income and Expenditure Survey (HIES) 2002/03, Botswana, collected by CSO. It is found that all the proposed methods and Jackknife method perform better than the method used by CSO.
Statistics Probability Letters, Mar 1, 2006
In this paper, the problem of estimation of variance has been considered when the missing data ha... more In this paper, the problem of estimation of variance has been considered when the missing data have been imputed with the ratio method of imputation. Two alternative variance estimators have been proposed. Relative efficiencies of the proposed estimators have been compared with the existing alternative Jackknife estimator proposed by Variance estimation under two-phase sampling with application to imputation for missing data. Biometrika 82, 453-460] through empirical study. Empirical investigation shows that the proposed estimators fare better than the Variance estimation under two-phase sampling with application to imputation for missing data. Biometrika 82, 453-460] estimator. r
Metrika, 1981
... References Bandopadhyaya, S., AK Chattopadhyaya, and S. Kundu : On estimation of population t... more ... References Bandopadhyaya, S., AK Chattopadhyaya, and S. Kundu : On estimation of population total. Sankhys Ser. C 39, 1977, 28-42. ... 3, 1952, 99-107. Rao, JNK, and K. Vi]ayan: On estimating the variance in sampling with probability proportional to aggregate size. Jour. ...
Sankhya, 1982
... Vl(bli) = 8U, Cx(bH, b,f) = 8tf). Page 9. 100 ARIJIT CHAUDHURI AND RAGHUNATH ARtfAB ... The a... more ... Vl(bli) = 8U, Cx(bH, b,f) = 8tf). Page 9. 100 ARIJIT CHAUDHURI AND RAGHUNATH ARtfAB ... The authors gratefully acknowledge several construc tive criticisms by Professor J. Roy that were helpful in preparing this paper. They also wish to thank Dr. Shibdas Bandyopadhyay ...
The generalized regression predictor (greg) is used for the estimation of a finite population tot... more The generalized regression predictor (greg) is used for the estimation of a finite population total when the study variable is well related to the auxiliary variable. Chaudhuri and Roy (1997) provided the lower bound of the mean square error (mse) of variance estimators belonging to a class of nonhomogeneous quadratic unbiased estimators. They also found the optimum variance estimator whose mean square error attains the lower bound. In the present paper, we have shown that the derivation of the lower bound in Chaudhuri and Roy (1997)'s paper is incorrect and their proposed optimal estimator does not attain the lower bound as originally claimed. An example is also provided which contradict the result of Chaudhuri and Roy (1997). Model assisted higher order calibration approach has been proposed to investigate the variance of the regression predictor.
We discovered there is a choice of weights that builds a bridge between the GREG proposed by and ... more We discovered there is a choice of weights that builds a bridge between the GREG proposed by and the linear regression estimator due to while using one auxiliary variable. It gives the same result as given in Singh (2003, 2004, 2006a, 2006b) and for unequal probability sampling by using two calibration constraints in the presence of one auxiliary variable. Thus, these approaches can be considered as alternative to each other while considering use of one auxiliary variable. The bridge developed here reconfirms that the sum of the calibrated weights should be equal to the sum of the design weights in a given sample. The approach by Singh (
Pakistan Journal of Statistics
The problems of estimating the population total in multi-character surveys in varying probability... more The problems of estimating the population total in multi-character surveys in varying probability sampling schemes when the measure of size is not well-related to the study variables have been considered by Rao (1966), Scott and Smith (1969) and Arnab (2001). In the present note, their results are extended for intra class correlation models and general sampling designs.
Communications in Statistics - Theory and Methods, 2015