scispace - formally typeset
Search or ask a question

Showing papers in "Sociological Methods & Research in 1981"


Journal ArticleDOI
TL;DR: In spite of the fact that chain referral sampling has been widely used in qualitative sociological research, especially in the study of deviant behavior, the problems and techniques involved in its use have not been discussed.
Abstract: In spite of the fact that chain referral sampling has been widely used in qualitative sociological research, especially in the study of deviant behavior, the problems and techniques involved in its...

4,416 citations


Journal ArticleDOI
TL;DR: This article argued that the standardization of variables and scales should be separated from the habitual use of standardized coefficients, and that the use of standard coefficiencies should be distinguished from the use standardization coefficients.
Abstract: In comparative study, it is argued that (1) the standardization of variables and scales should be separated from the habitual use of standardized coefficients; (2) the use of standardized coefficie...

138 citations


Journal ArticleDOI
TL;DR: In this paper, a nonparametric technique is presented that is appropriate for comparing two social interaction matrices, either when both are obtained empirically, or when one is generated from some given theoretic model.
Abstract: A nonparametric technique is presented that is appropriate for comparing two social interaction matrices, either when both are obtained empirically, or when one is generated from some given theoret...

114 citations


Journal ArticleDOI
TL;DR: Two models of the diffusion of computer use and the use of more sophisticated social science methodology in applied settings are posited: Top-down diffusion involves the spread of sophisticated techniques from larger to smaller agencies, while grass-roots diffusion involvesThe gradual upgrading of methods used in a wider range of settings.
Abstract: Two models of the diffusion of computer use and the use of more sophisticated social science methodology in applied settings are posited: Top-down diffusion involves the spread of sophisticated techniques from larger to smaller agencies, while grass-roots diffusion involves the gradual upgrading of methods used in a wider range of settings. Possible examples of the role of microcomputers in fostering both types of diffusion in urban planning are described. The two models imply different kinds of computer training for professionals.

32 citations


Journal ArticleDOI
TL;DR: Using the logic developed by Goodman and Kruskal, multiple and partial analogs for their measure Tau are suggested in this paper, which may be useful and necessary for detailed causal and/or multiple analysis with nominal-level data.
Abstract: Using the logic developed by Goodman and Kruskal, multiple and partial analogs for their measure Tau are suggested. These measures may be of particular utility to survey researchers in situations where the Goodman and Kruskal lambda measures are either inappropriate or inapplicable. This measure has been shown to have a clear proportional reduction in error interpretation. These analogs should be useful and necessary for detailed causal and/or multiple analysis with nominal-level data.

30 citations


Journal ArticleDOI
TL;DR: Taagepera and Grofman as mentioned in this paper defined two families of indices which may be used to characterize the effective number of components in systems with unequal component sizes, and applied them for a variety of problems, including measurement of population and GNP concentrations, distinguishing between density and crowding, and reconciling differing student and faculty perceptions of average class size.
Abstract: Author(s): Taagepera, R; Grofman, B | Abstract: Two families of indices are defined which may be used to characterize the effective number of components in systems with unequal component sizes. A general formula is staled relating size, effective size, and effective number of components. Special cases of this formula are considered which yield formulae identical or closely related to a variety of other expressions including entropy, the Greehberg-Lieberson index of diversity (also known as the Rae-Taylor fractionalization index), the Herfindahl-Hirschman concentration index, the coefficient of variation, the ordinary mean, the weighted mean and the harmonic mean. Applications of these formulae are considered for a variety of problems, including measurement of population and GNP concentrations, distinguishing between density and crowding, and reconciling differing student and faculty perceptions of average class size. © 1981, SAGE Publications. All rights reserved.

28 citations


Journal ArticleDOI
TL;DR: Some of the blocks on further innovation, and some of the social choices to be faced, are suggested, and the vast social implications which they have are suggested.
Abstract: The technology on which microcomputers and allied developments are based is rapidly progressing, but the extent and directions in which development continues will be determined largely by social, not autonomously technical, factors. This technology can, within the next decade or two, advance to the point where an enormous range of new applications will be economically practicable. A wide variety of microcomputer applications are already underway in computation, automation, data management, and communication. This article surveys some of the more important of these, and suggests the vast social implications which they have. The applications themselves and their effects are, it is argued, at least partially subject to social control. The article suggests some of the blocks on further innovation, and some of the social choices to be faced.

20 citations


Journal ArticleDOI
TL;DR: In this paper, a method is described for interviewing a random sample of persons drawn from a large population so as to describe role-sets defining statuses in the population social structure.
Abstract: A method is described for interviewing a random sample of persons drawn from a large population so as to describe role-sets defining statuses in the population social structure. The key to the method is a connection between the concept of an at tor's network position in social structure and combinations of attributes that define statuses in the social structure. With data obtained in a survey interview with a randomly selected respondent, it is possible to describe the relational pattern defining his "ersatz network position" in the population social structure from which he has been drawn. Given ersatz network positions for a representative sample, it is possible to test hypotheses concerning satus/role-sets in terms of which the population is stratified.

18 citations


Journal ArticleDOI
TL;DR: The rationale for the general CDS design and its use of computer-assisted methods are reviewed, and those aspects of the CDS experience that may be relevant for other large-scale studies in the area of human services are emphasized.
Abstract: This article discusses the study objectives and survey methods associated with the California Disability Survey (CDS), a large-scale telephone study of the California household population. The CDS ...

15 citations


Journal ArticleDOI
TL;DR: In this article, the standard errors of estimates of gamma and Kendall's tau-b are estimated using Tukey's jackknife method and the results are compared with Kritzer's application of asymptotic theory.
Abstract: Standard errors of estimates of gamma and Kendall's tau-b are estimated using Tukey's jackknife method and the results are compared with Kritzer's application of asymptotic theory. The method is used to test the hypothesis that a pair of partial association coefficients are equal.

12 citations


Journal ArticleDOI
TL;DR: The potential offered by microcomputer technology to radically improve the effectiveness and productivity of team field research in anthropology is examined.
Abstract: This article examines the potential offered by microcomputer technology to radically improve the effectiveness and productivity of team field research in anthropology. Microcomputers can offer in situ storage, retrieval, and analysis of field data and information. A microcomputer system may function as both a stand alone device and as a terminal to a mainframe, time sharing computer. Drawing from pilot projects using microcomputers, the various dimensions of feedback, consequences for fieldwork strategies, and efficiency are explored.

Journal ArticleDOI
TL;DR: In this article, it was shown that the IPF algorithm can be used to estimate non-hierarchical log-linear models and also many nested loglinear models, and the equivalence between a particular class of nested models and the model of quasi-independence.
Abstract: The recent literature on-log-linear models incorrectly implies that the Iterative Proportional Fitting (IPF) algorithm and associated computer programs such as ECTA can only be used to estimate hierarchical (not nonhierarchical) log-linear models. While ECTA and similar programs are designed for the estimation of hierarchical models, it is shown here that the IPF algorithm (and existing computer programs such as ECTA) can be used to estimate any nonhierarchical model and also many nested log-linear models. The former result follows directly from the symmetry between qualitative/categorical indicator variables and appropriately defined “interaction variables.” The general approach for dichotomous variables is illustrated here using data from the study of “The American Soldier” by Stouffer et al. We also illustrate how the ECTA program can be used to estimate nested models, and show the equivalence between a particular class of nested models and the model of quasi-independence.

Journal ArticleDOI
TL;DR: Both response and non-response are found to be systematically biased, with unfortunate effects in combination, which may be typical of survey data in general; hence, more realistic error models and robust estimation methods are desirable.
Abstract: Exploratory data analysis (EDA) is used to study errors in self-reports of lest scores and grades from a survey sample of college students. Both response and non-response are found to be systematically biased, with unfortunate effects in combination. Errors are not normally distributed, and would be better modeled as contaminated distributions made up of two or more simple distributions. Errors are correlated with each other and with other variables, leading to spuriously inflated as well as deflated intervariable correlations. These findings may be typical of survey data in general; hence, more realistic error models and robust estimation methods are desirable.

Journal ArticleDOI
TL;DR: The feasibility of using microcomputers to simulate social systems by discussing some hardware and software as well as selection considerations the researcher should weigh before choosing a microprocessor-based system are considered.
Abstract: This article discloses and considers (1) the various advantages which accrue from employing computer simulation methodology to examine social systems; (2) the disadvantages and potential pitfalls encountered in the utilization of computer simulation techniques; and (3) the feasibility of using microcomputers to simulate social systems by discussing some hardware and software as well as selection considerations the researcher should weigh before choosing a microprocessor-based system.

Journal ArticleDOI
TL;DR: The introduction of microcomputers has significantly changed the calculational power/cost ratio inherent in computer technology and permits new structures of access, not only for sociologists, but for individuals in all walks of life.
Abstract: During the era of the mainframe computer, 1946-1976, sociologists wholeheartedly embraced computer technology as an adjunct to quantitative research methods. The nature of the technology and the resultant structure by which most sociologists gained access to computers lent itself to several undesirable side effects. However, the undeniable calculational power of the technology was enough to outweigh those disadvantages, at least for the mainstream of the discipline. The introduction of microcomputers has significantly changed the calculational power/cost ratio inherent in computer technology and permits new structures of access, not only for sociologists, but for individuals in all walks of life. Although this does not in and of itself offer a panacea for every criticism that has ever been raised concerning the usage of computers within sociology, several of the previous disadvantages of computer technology have now been technically eliminated, if not yet eliminated in practice.

Journal ArticleDOI
TL;DR: In this paper, a structural equation model for assessing the effects of group membership when observations are clustered by group is presented, and the model is compared to those from a naive regression model and a model subjected to a specification test.
Abstract: This article presents a structural equation model for assessing the effects of group membership when observations are clustered by group. Within a LISREL specification, the net similarity in outcomes between a pair of observations in the same cluster is generated by an unobservable which captures the group effect. Analogies to the conventional ANCOVA model are noted, and an application to the assessment of “neighborhood effects” in reports of “neighborhood quality” from the 1976 Annual Housing Survey is presented. Estimates from the unobservable variable model are compared to those from a naive regression model and the model subjected to a specification test. The pitfalls of proceeding with the naive model are discussed, and the potential for future work exploiting the clustering in large-scale social surveys is emphasized.

Journal ArticleDOI
TL;DR: The claim by Breiger and Pattison (1978) that the joint homomorphic reduction indicates the role structure common to two populations is shown to be incorrect as discussed by the authors, and the actual common role structure is defined and then calculated for the elites of two communities.
Abstract: The claim by Breiger and Pattison (1978) that the joint homomorphic reduction indicates the role structure common to two populations is shown to be incorrect. The actual common role structure is defined and then calculated for the elites of two communities. A new measure of the similarity of two role structures is also provided. The results show that, in contradiction to Breiger and Pattison's claims, the two community elite role structures do not share relative strength of ties and are, in fact, very different from one another.

Journal ArticleDOI
TL;DR: A microcomputer data base management system designed for the personal use of social science researchers is presented and major advantages of establishing a personal data base of literature include permanent storage of information, ease of finding stored information, and the manipulation of information for word processing and other applications.
Abstract: A microcomputer data base management system designed for the personal use of social science researchers is presented. Discussed are data base needs required for a body of social science literature, existing microcomputer hardware and data base management software, development of a microcomputer data base management program suitable for storage retrieval of a body of social science literature, and ways a data base can be useful. Major advantages of establishing a personal data base of literature include permanent storage of information, ease of finding stored information, and the manipulation of information for word processing and other applications.

Journal ArticleDOI
TL;DR: The Apple II/FIRST microcomputing system, while presently employed by us in social psychophysiological research, was developed for use in animal classical conditioning research and has the power and flexibility to be used in a wide variety of other laboratories.
Abstract: An Apple II/FIRST microcomputing system has been established to control social-psychophysiological experiments, colled analog and digital data, and extract dependent variable measures for the monitored physiological, reportable, and behavioral processes. The inexpensive Apple II microcomputer has been augmented by a hardware floating-point processor and an A/D converter chip. In addition, the FIRST software system is employed. FIRST is an interactive, high-level, structured programming language that is sufficiently fast that tedious machine-language programming is seldom needed for stimulus control and data acquisition. The Apple II/FIRST microcomputing system, while presently employed by us in social psychophysiological research, was developed for use in animal classical conditioning research (Scandrett and Gormezano, 1980). Clearly, the system has the power and flexibility to be used in a wide variety of other laboratories.

Journal ArticleDOI
TL;DR: In this article, the utility of heterogeneous versus homogeneous samples in comparative organizational research is appraised through a path analytic comparison of the relationships between organizational size, spatial, vertical and horizontal differentiation established with samples representing different degrees of homo-heterogeneity.
Abstract: The utility of heterogeneous versus homogeneous samples in comparative organizational research is appraised through a path analytic comparison of the relationships between organizational size, spatial, vertical and horizontal differentiation established with samples representing different degrees of homo-heterogeneity. A causal model is estimated on data of 115 business and government organizations. The estimated parameters of the model are compared to those of Blau and Schoenherr based on a homogeneous sample of employment agencies, and Mileti, Gillespie, and Haas's sample of mixed government agencies. The findings suggest the potential utility of increasing our use of heterogeneous samples in comparative organizational research.

Journal ArticleDOI
TL;DR: By the end of the decade, microcomputers will have changed the way social scientists do research, the way they teach courses, and the way their work in applied settings.
Abstract: Microcomputers are cheap, reliable, portable, computationally powerful, and easy to use. This profile makes them significantly different from mainframe computers and guarantees wide diffusion. Ry the end of the decade, microcomputers will have changed the way social scientists do research, the way they teach courses, and the way. they work in applied settings. Microcomputers also will create new topics for social analysis as the microcomputer revolution reaches diverse sectors of society. The articles in this.issue consider some of these implications of microcomputers. I acquired a microcomputer in 1978. Entranced by the interactive programming that a microcomputer offers, I created a word processor, matrix package, and statistical routines. By 1980 I had transferred 95% of all my research computations to the microcomputer. My editorship of Sociological Methods .and Research is conducted via the microcomputer, without secretarial help. I also use the microcomputer regularly in the classroom to display statistical principles and to demonstrate theoretical models. My experiences leave me an advocate of microcomputers, but one who has a storehouse of cautionary tales. The basis of the advocacy is simple: Microcomputers permit breathtaking increases in

Journal ArticleDOI
TL;DR: In this article, a method is developed to evaluate the effects of wife's income on family income inequality, and those effects are examined between 1967 and 1976 employing data from the Panel Study of Income Dynamics.
Abstract: In this article, a method is developed to evaluate the effects of wife's income on family income inequality, and those effects are examined between 1967 and 1976 employing data from the Panel Study of Income Dynamics. The coefficient of variation is employed as a measure of family income inequality. Results indicate that income inequality increased substantially between 1967 and 1976 for U.S. families, but this increase was not due to the effects of wife's income. There have been substantial differences in the effects of wife's income for black and white families. In general, a movement toward greater equality of earnings between husbands and wives would tend to promote less family income inequality.

Journal ArticleDOI
TL;DR: In this paper, it is argued that the use of descriptive features in the form of homomorphic images, in general, and the joint homomorphic image, in particular, defines the potentially more useful approach, primarily because homomorph images of the semigroup may be given relational referents in the generating blockmodel.
Abstract: Contrasting accounts of the common structure in the blockmodels for two community elites (Breiger and Pattison, 1978; McConaghy, 1980) are shown to follow from two distinct means of interpreting the semigroup representation of role structure in a single population. The two candidate sets of interpretative features for the semigroup are the homomorphisms which it admits and the equations by which it is defined. These alternative descriptions lead naturally to the respective constructions of thejoint homomorphic image (Boorman and White, 1976)and the common role structure semigroup (Bonacich, 1980; McConaghy, 1980) as representatives of common structure in two populations. It is argued that the use of descriptive features in the form of homomorphic images, in general, and the joint homomorphic image, in particular, defines the potentially more useful approach, primarily because homomorphic images of the semigroup may be given relational referents in the generating blockmodel.

Journal ArticleDOI
TL;DR: In this article, a multinomial logistic regression method is presented which allows the examination of similarity as a function of multiple independent variables and data on similarity of marijuana use among 1,367 adolescent dyads are analyzed Intensity of friendship bond is the only significant predictor of variability on similarity.
Abstract: Similarit between members of dyads has been studied for a variety of attributes, but not much is known about how similarity varies as a function of dyad charac teristics One reason for this is the existence of methodological problems that have restricted the analy ses of similarity. In this article, a multinomial logistic regression method is presented which allows the examination of similarity as a function of multiple independent variables. As an applic ation of the method, data on similarity of marijuana use among 1,367 adolescent frienciship dyads are analyzed Intensity of friendship bond is the only significant predictor of variability on similarity.

Journal ArticleDOI
TL;DR: In this paper, the authors argue that homomorphic images are the better candidate, and that consequently the joint homomorphic reduction is the better representative of common role structure, and they conclude that the common structure semigroup versus joint homomorph reduction controversy results from disagreement regarding the best of congruence classes and homomorphic image, respectively.
Abstract: attison claims that the common structure semigroup versus joint homomorphic reduction controversy results from disagreement regarding the best of &dquo;two candidate descriptive features of a semigroup&dquo;: congruence classes and homomorphic images, respectively. She proceeds to argue that homomorphic images are the better candidate, and that consequently the joint homomorphic reduction is the better representative of common role structure.

Journal ArticleDOI
TL;DR: Bloom (1979) discussed a new mathematical model that has considerable potential for facilitating program evaluations based on analyses of recidivism data, but overlooked a rich literature in other fields, such as survival analysis and reliability theory, dealing both with his particular model and the general type of process of which Recidivism may be considered an example.
Abstract: Bloom (1979) discussed a new mathematical model that has considerable potential for facilitating program evaluations based on analyses of recidivism data. However, he overlooked a rich literature in other fields, such as survival analysis and reliability theory, dealing both with his particular model and the general type of process of which recidivism may be considered an example. Use of results from that literature could have streamlined his discussion. More fundamentally, Bloom did not carry his consideration of the behavioral mechanisms underlying his data to the point where his particular model specification, and no others, followed as a logical necessity. This limits the generalizability of his approach. One possible formulation of underlying relationships leading directly to Bloom's model is suggested.