Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
2
2
2006
3
1
Comparison of Small Area Estimation Methods for Estimating Unemployment Rate
107
128
EN
Arman
Bidarbakhtnia
a_bidar@sci.org.ir
Roshanak
Aliakbari Saba
r_ aliakbari@sci.org.ir
Extended Abstract. In recent years, needs for small area estimations have been greatly increased for large surveys particularly household surveys in Sta tistical Centre of Iran (SCI), because of the costs and respondent burden. The lack of suitable auxiliary variables between two decennial housing and popula tion census is a challenge for SCI in using these methods.
In general, the small area estimators can be classified into three categories: direct estimators, indirect estimators, and their combination.
The direct estimators are those estimators using just data falling into small areas for estimating parameter of interest in small areas. The indirect estimators use data collected from both small areas of interest and other areas to estimate the parameters.
The small area estimators used in this paper are indirect estimators with a combination of direct and indirect estimators. Three wellknown small area estimators, i.e. synthetic estimator, composite estimator, and adjusted regression estimator are introduced and calculated under various conditions.
First, a linear systematic sample with a size of 15,400 was selected from active population in the 1996 Census at 0.95 confidence level and a 0.05 maximum relative error.
To calculate quality indices in order to assess small area estimators, 1000 sample were selected from the population. Sample size in each province (small area) is a random variable since it varies in each replication. Since the employment information has been collected in the 1996 Census, the true unemployment rate is known for each province.
The small area estimators use auxiliary variables from previous census or large scale surveys and because of the long intercensal period, auxiliary variables tend to be out of date. So, for evaluating the effect of outofdate auxiliary variables on performance of small area estimators, auxiliary variables of 1986 Census were used. For this purpose we have used suitable auxiliary variables from 1986 Census file in each province.
There are four quality measures for comparison of small area methods, including bias, mean squared error (MSE), average of relative errors (ARE), and average of squared errors (ASE).
Using these measures, four estimators are chosen as the selected methods:
p(CSyAv): Composite estimator with synthetic estimator and mean of group weights,
p(CAlAv): Composite estimator with synthetic alternative estimator and mean of group weights,
p(JSSy): JamesStein estimator with synthetic estimator, and
p(JSAl): JamesStein estimator with synthetic alternative estimator.
MSE charts show that if we assign a fixed value as a minimum sample size in each small area, we can always be assure to have acceptable MSEchr('39')s in using the above methods. Also p(JSAl) leads to smaller values of ARE and ASE, and in maximum relative error point of view, p(CAlAv) has smaller values than the other selected estimators.
designbased estimators, small area estimation, unemployment rate, poststratum.
http://jsri.srtc.ac.ir/article-1-152-en.html
http://jsri.srtc.ac.ir/article-1-152-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
2
2
2006
3
1
Admissible and Minimax Estimator of the Parameter $theta$ in a Binomial $Bin( n ,theta)$ distribution under Squared Log Error Loss Function in a Lower Bounded Parameter Space
129
140
EN
Mohammad
Jafari Jozani
m.j.jozani@srtc.ac.ir
Extended Abstract. The study of truncated parameter space in general is of interest for the following reasons:
1.They often occur in practice. In many cases certain parameter values can be excluded from the parameter space. Nearly all problems in practice have a truncated parameter space and it is most impossible to argue in practice that a parameter is not bounded.
In truncated parameter space, the commonly used estimators of $theta$ such as the maximum likelihood estimators are inadmissible. Even more characteristic is the fact that boundary rules are mostly inadmissible, where a boundary estimator is an estimator which takes, with positive probability for some ...[To continue please click here]
minimax estimation, restricted parameter space, squared log error loss, binomial distribution, lower bounded parameter space, twopoint prior.
http://jsri.srtc.ac.ir/article-1-153-en.html
http://jsri.srtc.ac.ir/article-1-153-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
2
2
2006
3
1
A New Approximation for the Null Distribution of the Likelihood Ratio Test Statistics for k Outliers in a Normal Sample
141
158
EN
Rahim
Mahmoudvand
r _ mahmodvand@yahoo.com
Hossein
Hassani
hassanih@cf.ac.uk
Usually when performing a statistical test or estimation procedure, we assume the data are all observations of i.i.d. random variables, often from a normal distribution. Sometimes, however, we notice in a sample one or more observations that stand out from the crowd. These observation(s) are commonly called outlier(s). Outlier tests are more formal procedures which have been developed for detecting outliers when a sample comes from a normal distribution (Thode, 2002). A lot of work has been done for testing outliers in a univariate sample, most of which corresponds to the normal and exponential distribution. Barnett and Lewis (1994) have presented a summary of tests for outliers and their critical values, many of which are specific to the detection of outliers in normal samples. The theoretical solution for the exact null distribution of the likelihood ratio... [To continue please click here]
Outlier, normal sample, likelihood ratio test, approximation.
http://jsri.srtc.ac.ir/article-1-156-en.html
http://jsri.srtc.ac.ir/article-1-156-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
2
2
2006
3
1
Socio-economic Differentials of Female Age at First Marriage: A study of Chuadanga District, Bangladesh
178
188
EN
Mizanur
Rahman
mmr_f@yahoo.com
This paper aims to investigate the main socioeconomic determinants of female age at first marriage in Chuadanga dis trict, Bangladesh, over the year 2005, and attempts to find some explanations for the differences in the age at marriage among socio economic characteristics. The findings of the multiple classification analysis (MCA) suggest that among all the variables analyzed in the study, education levels have a positive association with age at marriage. Age at marriage is increased with the level of husbandchr('39')s and wifechr('39')s education. The MCA also indicates that female educa tion has the strongest influence on age at marriage while husbandchr('39')s education is the second strongest determinant. The analysis reveals that the mean age at marriage of women is 16.77 years: 16.05 in ru ral areas and 18.22 in urban areas. It also shows that respondentchr('39')s occupation and religion have an important significant contribution to female age at first marriage.
cross tabulation, multiple classification analysis (MCA)
http://jsri.srtc.ac.ir/article-1-154-en.html
http://jsri.srtc.ac.ir/article-1-154-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
2
2
2006
3
1
A New S-test for Haplotype Analysis: Concordance and Discordance
187
196
EN
Mahnaz
Khattak
Shuhrat
Shah
Salahuddin
Salahuddin
salahuddin_90@hotmail.com
A new test of inheritance, S, is proposed, which uses information from affected as well as unaffected siblings in the fam ily. The siblings are analyzed in terms of similarities of haplotypes. The distribution of the proposed Stest is derived under the null hypothesis of random inheritance. Mean and variance are obtained for the distribution. The test is then applied to data sets published in the literature. The results suggest some sort of linkage between haplotypes and disease genes.
genetics, haplotypes, Stest.
http://jsri.srtc.ac.ir/article-1-157-en.html
http://jsri.srtc.ac.ir/article-1-157-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
2
2
2006
3
1
Spectral Estimation of Stationary Time Series: Recent Developments
198
219
EN
R.
Nematollahi
nematollahi@susc.ac.ir
Spectral analysis considers the problem of determining (the art of recovering) the spectral content (i.e., the distribution of power over frequency) of a stationary time series from a finite set of measurements, by means of either nonparametric or parametric techniques. This paper introduces the spectral analysis problem, motivates the definition of power spectral density functions, and reviews some important and new techniques in nonparametric and parametric spectral estimation. We also consider the problem in the context of multivariate time series.
spectral density, Capon's estimate, high resolution estimate, blockToeplitz matrix, windows.
http://jsri.srtc.ac.ir/article-1-155-en.html
http://jsri.srtc.ac.ir/article-1-155-en.pdf