نشریه بررسی های آمار رسمی ایران
سال بیست و سوم شماره 2 (پیاپی 81، پاییز و زمستان 1391)

In recent years, we have been faced with increasing growing use of data mining and database and parallel to this, new science and technologies have been developed to make the best of these huge volumes of data in customer relationship management, optimized use of data is a competitive advance for companies and organization. And if so, they can deserve their old customers and acquire new ones. In this regard, the banking industry is one of those industries that deal with huge volume data of the customers. In this article, we have considered customers churn in Mehr finance and credit institution. In the first step of this thesis, the literature review results is reported and based on the review, different aspects of problem properties is investigated and then, the required data is gathered. The churn modeling of data is performed in a hybrid form: first, we have applied fuzzy modeling for classifying customers in 3 categories as Active, Moderate and weak. Then, we have made use of support vector machine for churn modeling. Numerical results of the problem model are compared with logical approach. Finally, based on these numerical results, we can conclude that the hybrid Fuzzy – SVM approach is a more exact and useful approach for churn prediction.

Telephone surveys are popular in developed countries since many years ago but this method has not been common in developing countries because of low telephone coverage, although, in recent years, with improving telephone coverage, the telephone interview is used as a data collection method in these countries. In telephone surveys, sampling units are selected from different frames of telephone numbers, thus, survey errors such as coverage errors and non response errors are adjusted with appropriate procedures. In telephone interviews, regardless sampling design, telephone is used just as one of tools of collecting data. In this paper, theories and methods of telephone surveys and techniques of telephone interviews are provided, furthermore, possibility of using telephone interview is examined in the household surveys of Statistical Center of Iran.

One of the most fundamental statistical studies which are carried out in most countries to assess the various social and economic programs is the study of the household budget survey. By this we can discover the distribution of household income and expenditure and economic changes of individuals and families during the life cycle. Information of the investment patterns of the households in different age groups and investigating its changes during different years are important economic issues at micro and macro data level that can analyze the economic behavior and investment pattern of households. This paper is a descriptive and statistical research based on the annual urban and rural Household Expenditure and Income Survey (HEIS) data during 1999- 2011 which evaluates the change of household investment and analyzes the change trends in construction and agriculture sectors. In this paper in addition to descriptive analysis of household's investment trends, the estimate of cohort investment pattern by using Dayton model1 is drawn. In this model, the household expenditure on investment sector decomposes into year, age, and cohort effects in which the possibility of investing the cohort investment pattern of life cycle is provided. Also, to determine the effective factors on household's investment, using logistic model, the effect of some household and head of household characteristics on household investment expenditure is discussed.

In sample surveys, we don’t have a single frame that fully covers the target population and is inexpensive to use. However, it is possible to use several frames that each one covers a part of the target population and these frames are also inexpensive to use. In this article, at first, concepts, advantages and disadvantages of using multiple frames are described and then various methods of parameters estimates have been proposed for estimating the parameters. Finally, these methods are compared using a Monte Carlo simulation study.

The most important indicator for measuring income inequality is the Gini index. The Gini index summarizes an entire income distribution and overall degree of income inequality but have little to say about information the distribution of income between the different classes of income and the Lorenz curve. For example, when asymmetric cases that the Gini indexes for two different Lorenz curves are identical using the Gini index of income inequality alone, it is not clear that the increases in income inequality have been due to the rich getting richer or the poor become poorer. Therefore, this indicator may not be characterized as all changes in income concentration. To solve this problem, there are methods and indicators. At first, in this paper has been discussed approaches of several researchers to solve this problem by the application of skewness of Lorentz curve and then proposed a skewness coefficient as the best representation of the changes in the extremes. As an application example, the income distribution of provinces in particular for two provinces Khuzestan and Hormozgan in 2008, stressing that the two provinces are the same Gini coefficient has been examined.

Mortality rates associated with other indicators of population health plays an important role in decision making in community health, which has been used extensively. Aging populations in developed and developing countries, with increasing mortality among adults, necessitate the need for better assessment of mortality in these ages. The registration procedure is the most appropriate method that can provide mortality statistics and is consistent with its dynamic nature. However, this approach has two major drawbacks: the lack of full coverage and undetermined amount of coverage. Accordingly, the aim of this study is to evaluate the completeness of adult death registration in Markazi and Booshehr provinces, using the Brass Growth Balance method. Results indicate that Completeness of adult death registration in Markazi province is 87/7 percent. This amount is 99/8 percent for male and 76/5 percent for female. But Completeness of adult death registration in Booshehr province is 80/9 percent. This amount is 91/3 percent for male in comparison with 70 percent for female. Considering this criterion that if the completeness of death registration is over 70 percent, then the death registration is at an acceptable quality level, death registration in these provinces, particularly for men, has an appropriate completeness. However, as research results show, mortality registration data for women encounters so many problem the completeness of women death registration percent ratio is 20 less in number than that of men.