Search

This paper is concerned with the phenomenon of cohabitation among college students and focuses on characteristics of students who have cohabited in comparison with those who have not. Data were gathered in interviews with a random sample of 291 students at Arizona State University in 1971-72. The data indicated that 29 percent of the males and 18 per cent of the females were currently cohabiting or had cohabited. Family characteristics examined failed to differentiate between cohabiters and noncohabiters. Personal characteristics which tended to distinguish the two groups were in the areas of religion, life style, and drug use. Cohabiters, compared to noncohabiters, were less apt to attend church, were more likely to identify with a liberal life style, and more apt to be drug users. [ABSTRACT FROM AUTHOR]

This paper studies the design effect of counting rules, for linking deaths to housing units where they are enumerated in the survey, on the sampling variance of dual system and single system estimators of death registration completeness. It investigates estimators based on conventional rules that uniquely link each death to a single housing unit as well as estimators based on multiplicity rules which permit deaths to be linked to more than one housing unit. Sampling variance formulas are derived containing parameters that reflect the efficiency of the counting rule. Estimates of these parameters for different counting rules are compared utilizing information that was collected in a mortality survey experiment. Finally, the design of a national death registration test is considered and the sample size implications of different counting rules are compared. [ABSTRACT FROM AUTHOR]

This paper presents an approach to the following problem involving uncertainty: the choice of sample design for the estimation of parameters which are not identified prior to the sample selection. More specificly, the author suggests the use of 'contingency planning' as developed in the realm of military systems analysis, to supplement the use of standard sample survey theory. [ABSTRACT FROM AUTHOR]

This paper offers a look at patterns in methods of social inquiry or research as of September 1950. Apart from pure economics and some political science, the social sciences today proceed, like the natural sciences, at least partly inductively. All the inquiries use some statistical methods as against purely literary statements. This is not due to sheer perversity or exhibitionism, but to scientific necessity--the necessity, in short, of summarizing the main general trends among a wide variety of observed findings. The chief substitute of the social sciences for experiment is statistical strategy. Both in the natural and the realistic social sciences, the narrower and the more intensive the study and the less the variability of behaviour under study, the less statistics need come into it. Variability is reduced by experimenting under laboratory conditions and thus isolating the factors, but the alternative strategy is statistical and isolates the factors at issue by selection of numerically stable conditions or by control of variations. A further common feature of the social research pattern and the feature which, in spite of its great importance, has escaped attention is that of comprehensiveness. The lack of attention to this rule of discipline has been due largely to the inordinate attention bestowed upon the practical devices for random sampling.

The article discusses field work and survey respondents as sources of error in research projects. The goal of the article is to evaluate sources of error, the possible scope of its magnitude and to evaluate interviewer influence in marketing research. Interviewing errors are primarily classified into two categories; errors in selecting respondents, and errors in collecting data. The nonresponse group is discussed as a possible source of bias. Refusal to respond, not-at-home and efforts to control nonresponse bias are covered.

The article discusses the marketing research technique of the continuing consumer panel. The author points out that this research method is in its infancy because several of the aspects of this method are yet to be standardized. For example, there is no relative to the number of co-operators that should be used, there is no standard for the method of selecting the co-operators, and there is no standard for the frequency or reporting, among others. There are also several advantages to the use of this type of research methodology, including that detailed information can be obtained on a broad group as well as more specified group and a product life cycle can be tracked against the amount of money used in putting them over. A study using this method is also described.

The article discusses the uses of consumer panels, including their use in planning for a war economy. The author points out the functions of the consumer panel, such as the collection of recent data that may be forgotten if reported later in an interview, minimizing biased information, and reporting the information in a way convenient to the respondent and the researcher. Furthermore, the types of consumer panels used are examined and the importance of obtaining a cross section is noted. Lastly, the author shows how consumer panels can identify consumption shifts during war-time and how they can help in planning for a post-war economy.

The article addresses stratification in sampling and the expected results when stratification is implemented. The article discusses the process of sampling, how stratification works within a sampling population, and presents three types of sampling: selected as representative, random, and cross sections. The article discusses judgment sampling, self-selected samples, random samples, and disproportionate samples. Interval selection, adjustments, the effect of errors, and tabulation are also addressed. The author notes the value of stratification in sampling as it applies to market and business research.

Explores factors associated with the sampling procedures in the field studies of organizations. Development of information on organizational life using a method of data cumulation; Selection of the representative sample; Permission from organizations to engage in research; Participation of employees to the research; Difference between data pooling and literature reviews.

Using data from the 1970 National Fertility Study, the trend in the initiation of contraception prior to the first pregnancy is examined. This trend is of interest because of its relationship to the tempo of family-building. Using data from a recent marriage cohort, it is shown that use before the first pregnancy is related to age at marriage, age at termination of first pregnancy and the probability of having a premarital conception. For women first married during the decade of the 1960's, there was a substantial increase in the proportion using contraception before the first pregnancy. This trend is found among both white Catholics and white non-Catholics, but not among blacks. An examination of the specific method used by women using contraception before the first pregnancy reveals a shift from reliance on the traditional methods of diaphragm, condom and douche by the earlier birth cohorts to the use of the pill by the more recent cohorts. An appendix examines the reliability of various measures of the interval of first use of contraception. [ABSTRACT FROM AUTHOR]

A study was made of the factors that affected the casefinding of internal migrations in Liberia using the Chandrasekar-Deming dual enumeration and tabulation methods. The results of this work suggest that the recording and not recording of a migration is not a random occurrence but is associated with a particular enumeration system, origin and destination of the migration, and the migrant's age, sex, and location of current residence. [ABSTRACT FROM AUTHOR]

Multiple decrement life table technique is used to analyze the oral contraceptive use in a sample of once married women in Metropolitan Toronto. The overall pattern in the Canadian data is found to be essentially similar to that found in the U. S. Continuation rates show differences by cause of decrement. Two types of rates, net and absolute, are presented, and the relationship between single decrement continuation rates and total continuation rates is examined. Some problems of clinical versus retrospective sample survey data in studies of contraceptive effectiveness are commented on. [ABSTRACT FROM AUTHOR]

The article discusses that survey research methods provide the only means to collect and analyze information for a wide range of purposes of both scholarly research and policy making for nation-building. This notion is recognized by scholars, government officials, and commercial interests in the developing countries. It also provides an overview of the major issues involved in conducting a survey or a research in the developing countries. The analysis of materials has three types of bias including sampling, measurement, and interviewer bias.