METHOD OF ESTIMATION FOR SAMPLING FROM INCOMPLETE FRAMES

The planning of any sample survey or census requires the existence of a sampling frame comprising a list of all the sampling units. But unfortunately there is hardly a situation in practice where the frame is available in the form the sampler desires to use. Most commonly some units of the target population are not listed in the frame, and the frame may contain units which do not belong to the target population. In this investigation a suitable method of estimation is proposed when sampling is done from such imperfect frames and a geographical ordering of the units can be established.     

Disadvantage and Discrimination Compounded: the experience of Pakistani and Bangladeshi parents of disabled children in the UK

This paper discusses a qualitative and quantitative study of the circumstances of 20 Pakistani and Bangladeshi families with one or more severely disabled children living in Birmingham, England. Parents and other adult carers were interviewed using a combination of structured questionnaires and a semi-structured interview schedule focusing on the families' material circumstances, their use of formal services, informal care arrangements, and aspects of the parents' social and psychological well-being. The study suggests that previous national surveys of disabled families may have under-estimated the extent of material disadvantage, while it confirms that health and social care professionals should not assume that Pakistani and Bangladeshi parents have recourse to high levels of extended family support. The combination of disadvantaged circumstances and difficulties in securing access to appropriate services, which are found for the majority of families with a disabled child, was particularly acute for these ethnic minority families, suggesting the additional dimension of institutional racism.     

Sampling with partial enumeration from bivariate populations

In multi-character surveys, determination of sample sizes for studying various characters poses a difficult problem. In some situations, instead of observing the same units for all the characters it may be desirable to have some units observed for all the characters whereas some extra units for each character are observed separately. Such type of sampling has been defined here as sampling with partial enumeration. In the present investigation the efficiency of sampling with partial enumeration has been examined as compared to the usual two phase sampling for the study of only two characters.     

Inferences Concerning Exponential Distributions in the Presence of Randomly Right Censored Data with Missing Censored Values

Inferences concerning exponential distributions are considered from a sampling theory viewpoint when the data are randomly right censored and the censored values are missing. Both one-sample and m-sample (m 2) problems are considered. Likelihood functions are obtained for situations in which the censoring mechanism is informative which leads to natural and intuitively appealing estimators of the unknown proportions of censored observations. For testing hypotheses about the unknown parameters, three well-known test statistics, namely, likelihood ratio test, score test, and Wald-type test are considered.     

A multivariate von mises distribution with applications to bioinformatics

Motivated by problems of modelling torsional angles in molecules, Singh, Hnizdo & Demchuk (2002) proposed a bivariate circular model which is a natural torus analogue of the bivariate normal distribution and a natural extension of the univariate von Mises distribution to the bivariate case. The authors present here a multivariate extension of the bivariate model of Singh, Hnizdo & Demchuk (2002). They study the conditional distributions and investigate the shapes of marginal distributions for a special case. The methods of moments and pseudo‐likelihood are considered for the estimation of parameters of the new distribution. The authors investigate the efficiency of the pseudo‐likelihood approach in three dimensions. They illustrate their methods with protein data of conformational angles     

Attitudes and behavioral intentions about abortion

This paper examines the extent to which there may be differences in attitudes toward abortion and intentions when one is faced with making an abortion decision for oneself. Data from a 1977 national survey were used. The results indicated that while such differences existed only on a limited scale in medically indicated situations of abortion, discretionary situations had a sizable proportion of respondents who would approve of abortion for others but would not opt for abortion themselves. The differences in attitudes and intentions were affected by sex, religious behaviors, ideological dimensions of fertility, sexual permissiveness, and freedom of expression.     

A modification of a continuous time model for first conception

The interval between marriage and the first conception leading to a live birth plays an important role in the determination of fertility components. Several probability models (Potter and Parker, 1964; Singh, 1961, 1964, 1967) based on varying sets of assumptions relating to this interval have been propounded in the recent past. All of them are based on the assumption that the females under study are susceptible to conception at the time of marriage. However, in certain situations, where some of the females already pregnant at the time of marriage report to have conceived within a short interval following marriage, this condition is not satisfied and these models become unsuitable. A probability distribution which is an inflated form of the continuous model proposed by Singh, for the time of the first conception leading to a live birth, is presented in this paper. It describes reasonably well the data on first conception times in the context of premarital conceptions. Simple expressions for the maximum likelihood estimators of the parameters involved in the model are obtained and a method for finding the asymptotic covariance matrix of the estimators is outlined. The model is applied to four sets of data.     

A forecasting and policy simulation oriented small macro-model for the Indian economy

The design of macro-models for the purposes of derivation of macroeconomic stabilization policies and obtaining forecasts is an important area of theoretical and empirical economic research. This is because such a stance presents an ideal blend of skillfully interweaving the essential theoretical ingredients of the contemporary macroeconomic paradigms with specific structural features of the country under reference. The use of macro-models enables the policy makers to build alternative policy evidences and thus this approach proves to be far superior to the alternative approaches based on intuitive or judgmental criteria. It is against this background that a macro-model for the Indian economy is estimated in an error-correction framework. Based on it, some policy options are evaluated. ECM and time varying parameter based forecasts are obtained for inflation and growth for the Indian economy for the year 2004–2005.