نشریه بررسی های آمار رسمی ایران
سال نوزدهم شماره 1 (پیاپی 72، بهار و تابستان 1387)

Lorenz curve is an important tool to measure income inequality. Many indices are defined based on Lorenz curve to measure the inequality; Gini coefficient is one of them.In this paper, we introduce Lorenz curve and Gini coefficient and we estimate the unknown parameters of income probability distribution by the maximum likelihood method. Functional forms of the Lorenz curve are estimated via two methods and the best functional form is introduced.Finally, we estimate the Lorenz curve and the Gini coefficient based on the data of household income and expenditure survey of Iran 2005.

Household income and expenditure survey is one of the most important statistical surveys in Iran. It has many applications in economic planning and decision makings, such as studying the household consumption pattern, studying the trend of changes in goods and service consumption, assessing the economic policies and calculation of regional and national accounts. Obviously, because of various applications of this survey in government’s planning and decision making its data quality is very important. Precision is one of the essential components of data quality. To determine precision of the data, sampling and non-sampling variances should be estimated.Numerous estimators could be defined due to the fact that a variety of information is collected in the survey. In this paper, some basic estimators are considered. Furthermore, sampling and non-sampling variances are computed using the response error model for the results of two methods of information collection. The precisions of the methods are compared.

Ranked set sampling is used in situations in which measurement of the variable of interest is difficult or expensive, but it can be easily ranked in small sets. In this method the sample is divided into equal-sized sub-samples and the members of each sub-sample are ranked, separately. The rth order statistic of rthsub-sample is measured and recorded. This can also be done by an auxiliary variable by which the ranking is performed. Thus, the marginal distribution of the variables of interest corresponding to order statistics of the sub-samples will be the same as the distribution of concomitants of the order statistics of auxiliary information.Samawi and Muttak (1996, Biometr J, 38, 753-764) proposed a ratio type estimator in ranked set sampling scheme and applied it to estimate the ratio. Kadilar et al. (2007, Stat. papers, 50, 301-309) used the proposed estimator to estimate the population mean in ranked set sampling. Also Samawi et al. (2004, Comm. Statist. Theory Methods, 33, 1801-1819) used the same estimator for quantile estimation. Some comparison of these estimators with the corresponding estimators in simple random sampling scheme is studied by the above authors. However, no comparison study is done to compare the ratio estimator by other types of estimators, specially the regression estimator in ranked set sampling. In this paper the proposed ratio estimator of population mean is considered to have a general precision comparison between the ratio estimator and other types of estimators of population mean in ranked set sampling.

Reviewing Iran's foreign trade statistics in the last years and comparing them to the existing international standards demonstrates some problems in producing the data, such as, incomplete country reports on foreign trade in United Nation Statistical Division's data base, repeated requests of UNSD for timely provision of statistics on foreign trade, incoherence of the statistics with international standards, lags in time series, statistics not provided in various types of standard classifications, etc., which results in damages to the statistical credit of the country on one side, and improper evaluation of the country’s international economic status, on the other side.The main purpose of this paper is to investigate the causes of inconsistency in foreign trade statistics of Iran in order to find out the strengths and weaknesses of the data in comparison to the international standards of data collection. To this end, the standards and recommendations of relevant international organizations are introduced and studied, and Iran's status is analyzed with respect to these standards. Finally, some recommendations are proposed to deal with the existing problems.

In two recent decades, with the changes that have taken place in social and economic situation of societies, using the female labor force has been introduced as one of the fundamental topics in the area of development. Social and economic changes in the two recent decades in Iran have influenced women’s participation based on which we assess and analyze women’s status in Iran’s labor market in this paper using the census data.Estimates show that women’s economic participation has substantially varied during the time period 1996-2006 and has decreased from 9.1 percent in 1996 to 12.4 percent in 2006. Nevertheless, estimates denote a substantial difference between men’s and women’s participation rate and unemployment, and Iran’s labor market has sexual inequality regarding participation, employment, job variety, and employment vertical levels, in favor of men.

A type of survey called “repeated survey” or “sampling over time” which is repeated continuously during time periods is common in many statistical systems. Such surveys are often performed in one of the forms of repeated cross-sectional, rotation, or panel surveys. Panel survey is a method in which a “fixed sample” is contacted during different waves. In panel survey, there is another type of non-response in addition to item non-response called “wave non-response”. Wave non-response occurs when one or more waves of the panel data are missing for a unit for which information has been provided for at least one wave.When repeating observations on units over time, estimate of parameters change between waves are very important. Therefore, neither can we introduce the variability of the estimates of change by imputing solely based on cross-sectional information, nor would we like to decrease the variability of the change estimates by imputing using information of one sample unit. Clearly, the imputation techniques used in the subsequent waves of a panel survey are needed to incorporate the information collected in previous waves, among which “Little-Su imputation” can be named as a useful method. In this paper, types of panel surveys and “wave non-response” are studied, and “basic Little-Su” and “nearest neighbor” imputation methods are introduced. Finally, the effects of application of Little-Su imputation on efficiency and absolute bias of the statistic of interest are assessed by simulating a three-wave panel survey, and the method is compared to the nearest neighbor imputation (with respect to sample size effect, wave non-response rate, and correlations between waves). The results of this simulation study show that most of the times the “Little-Su” method gives more reliable estimates than the nearest neighbor imputation method.

Missing data is a common problem in survey based research. There are many packages that compensate for missing data but few can easily compensate for missing longitudinal data. WinBUGS compensates for missing data using multiple imputation, and is able to incorporate longitudinal structure using random effects. We demonstrate the superiority of longitudinal imputation over cross-sectional imputation using WinBUGS. We use example data from the Australian Longitudinal Study on Woman’s Health. We give a SAS macro that uses WinBUGS to analyze longitudinal models with missing covariate data, and demonstrate its use in a longitudinal study of terminal cancer patients and their carers.