Saturday, March 13, 2010

papers about quantitative methods

papers about: METHODOLOGICAL AND DATA ANALYTIC ADVANCES IN THE STUDY OF INTERPERSONAL RELATIONSHIPS == QUANTITATIVE METHODS USED TO EVALUATE ATTRIBUTES AND TO COMPARE BETWEEN PERSONS. (If you plan to innovate in the OnLine Dating & Social Networking Industry, these papers are all a "must read")

------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------

"A discussion by Gable and Reis concerning the importance of studying relationship phenomena using within_person methodologies in addition to the between_person methods that are commonly employed in relationships research today. Within_person methods involve sampling observations from an individual across multiple contexts, across multiple relationship partners, and/or across time. In addition to enumerating the benefits of such research, the authors also present a thoughtful discussion of the challenges that it involves. Finally, they examine data analytic approaches appropriate to analyzing data derived from this research paradigm." http://www.blackwell-synergy.com/doi/abs/10.1111/j.1475-6811.1999.tb00201.x

"NOW AND THEN, THEM AND US, THIS AND THAT: STUDYING RELATIONSHIPS ACROSS TIME, PARTNER, CONTEXT, AND PERSON. "
Abstract: Personal relationships are frequently studied using methods and analyses that reflect an interest in relationships as between_persons phenomena. Although informative, there is much to be learned from examining relational phenomena from a within_persons perspective. The present article reviews the application of within_persons approaches to both the conceptualization and investigation of relational phenomena. The benefits of studying variation in psychologically meaningful constructs across multiple relationships, across different contexts within a relationship, and across time are outlined. Moreover, combinations of between_persons and within_persons strategies that can examine how relational, contextual, and temporal variation differs across people are discussed. Methodological and statistical considerations important to such designs are also outlined, and their limitations are discussed.

------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------

"Haslam addresses issues involved in creating taxonomies of relationships, adapting methods that have been more commonly used in the fields of psychopathology, personality psychology, and behavior genetics. These taxometric methods are techniques that test between discrete and continuous models of latent variables. Arguing that these methods have great potential for the relationships field, Haslam describes three statistical techniques used to test the usefulness of taxonomies and to create new ones. A detailed example is employed to walk readers through the process of developing and testing taxonomies."
http://www.blackwell-synergy.com/doi/abs/10.1111/j.1475-6811.1999.tb00207.x

"TAXOMETRIC AND RELATED METHODS IN RELATIONSHIPS RESEARCH. "
Abstract: Research on personal relationships inescapably uses taxonomies for classifying people, relationships, and interpersonal processes and events, and often develops new ones. However, constructing a good taxonomy is no simple matter. Many existing classification methods have serious weaknesses, and they carry the risk of drawing taxonomic distinctions that are spurious. In addition, researchers frequently make unwarranted assumptions about the nature of the taxonomic categories that they employ in their work. This article introduces a family of quantitative methods for testing and generating taxonomies. Although they have seen little use to date outside of psychopathology, personality psychology, and behavioral genetics, these methods are versatile and readily adapted to the domain of personal relationships, where they offer many research possibilities. Three of the methods are illustrated in a study of elementary forms of relationships.
At page 522 " … The two taxometric procedures to be discussed are called the MAXCOV (maximum covariance) and MAMBAC (means above minus below a cut) procedures. These are the two procedures that have been most widely used in taxometric research to date. Both procedures require the use of several 'indicators' of the conjectured latent variable. These indicators can be any measures that are associated with this variable, such as personality scales, item ratings, physiological measurements, and so on. …."
At page 523 "…. Admixture or commingling analysis (the terms are essentially interchangeable) is an alternative way to detect categories, and to test between discrete and continuous models of latent variables. …."
At page 525 "The three quantitative methods described above will be illustrated in a study of a theory of elementary forms of relationship developed by Alan Fiske (1991). The theory proposes four cognitive models in terms of which relationships are represented, comprehended, evaluated, and constructed. The Communal Sharing model organizes relationships in terms of collective belonging or solidarity. Members of an in_group are treated as equivalent elements of a bounded set, and consequently individual distinctiveness is ignored. By contrast, the Authority Ranking model organizes relationships in asymmetrical terms. Parties to relationships governed by this model are hierarchically ordered, with higher_ranked individuals authorized to command, protect, dominate, and precede, and lower ranked individuals expected to defer, obey, and show loyalty and respect. The Equality Matching model organizes relationships with reference to their degree of balance or imbalance; it is manifested most distinctly in turn_taking, reci p r ocity, distributions of equal shares, democratic voting, and tit_for_tat retaliation. The Market Pricing model, finally, organizes relationships with reference to a common scale of ratio values such as money. Emphasis is on proportions; earning a wage based on hours worked, getting a good return on an investment of effort, or efficient use of time; and social transactions are reckoned as rational calculations of cost and benefit"
At page 533 " In conclusion, taxometric and admixture procedures offer the interested researcher some accessible quantitative methods for investigating fundamental questions in the study of personal relationships. Their versatility and promise have yet to be exploited in this domain, although they are increasingly appreciated in others, and they offer relationship researchers a chance to make innovative contributions."

------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------

"Griffin, Murray, and Gonzalez discuss the common practice in relationships research of computing difference or discrepancy scores to represent SIMILARITY OR DISSIMILARITY BETWEEN INDIVIDUALS. Although difference scores and their variants have great intuitive appeal, such scores involve numerous pitfalls when they are used in correlational research. In this article, the authors review the problems associated with difference score correlations using a descriptive and graphical approach rather than relying on formulas. They also describe three data analytic techniques that can be used as alternatives to difference score correlations."

http://www.blackwell-synergy.com/doi/abs/10.1111/j.1475-6811.1999.tb00206.x

"DIFFERENCE SCORE CORRELATIONS IN RELATIONSHIP RESEARCH: A CONCEPTUAL PRIMER."
Abstract: The practice of computing correlations between difference or discrepancy scores and an outcome variable is common in many areas of social science. Relationship researchers most commonly use difference scores to index the (dis)similarity of members of two_person relationships. Using an intuitive, graphical approach and avoiding formulas and pointing fingers, we illustrate problems with using difference score correlations in relationship research, suggest ways to ensure that difference score correlations are maximally informative, and briefly review alternatives to difference score correlations in studying similarity, accuracy, and related constructs.

------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------

"Gonzalez and Griffin also focus their attention on INTERDEPENDENT DYADIC DATA. Their article spotlights two ways of modeling correlations between couple members when the DYAD MEMBERS ARE DISTINGUISHABLE. First they discuss estimation of the overall WITHIN_PARTNER correlation (which is analogous to Kenny and Cook's actor effect) and the overall CROSS_PARTNER correlation (analogous to the partner effect) using both a PAIRWISE APPROACH and a STRUCTURAL EQUATION MODELING APPROACH. They then describe how these overall correlations can be decomposed into dyad_level effects and individual_level effects. The dyad_level effects address whether dyad members are similar to one another on two variables, and whether the degree of similarity between dyad members on one variable relates to the degree of similarity between them on the second variable. The individual_level correlation addresses whether, after taking into account the dyad's standing on the two variables, an individual's score on one variable relates to that person's score on the second variable."
http://www.blackwell-synergy.com/doi/abs/10.1111/j.1475-6811.1999.tb00203.x

"THE CORRELATIONAL ANALYSIS OF DYAD_LEVEL DATA IN THE DISTINGUISHABLE CASE. "
Abstract: Many theories of interpersonal relationships distinguish between individual_level processes and dyadic or group_level processes. This suggests that two_person relationships should be studied at the level of the dyad as well as at the level of the individual. We discuss correlational methods for dyads when each dyad contains two different types of individuals (e.g., a husband and wife, a mother and child, or an expert and a novice). In such dyadic interaction designs, the dyad members are said to be distinguishable. We present a method for computing the OVERALL CORRELATION FOR DISTINGUISHABLE DYADS, and we discuss a model for separating the dyad_level and individual_level components of such a correlation. The computational techniques and their interpretation are described using data from 98 heterosexual couples.

------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------

"Kenny and Cook present a detailed discussion of partner effects in dyadic research. Partner effects are one way of conceptualizing the interdependence that exists within dyads in that they occur when the characteristics of an individual affect the outcomes of his or her relationship partner. For example, not only may a person's attachment style affect his or her own relationship satisfaction (an actor effect) but that person's attachment style may also affect his or her partner's satisfaction (a partner effect). These investigators describe FOUR MODELS IN WHICH ACTOR AND PARTNER EFFECTS MAY PLAY DIFFERING ROLES IN DYADIC RELATIONSHIPS, and they also discuss how these two effects may interact with one another. After discussing partner effects at a conceptual level, the authors present an overview of several methods that can be used to estimate partner effects in dyadic research, giving considerable attention to the use of MULTILEVEL MODELING AS AN ESTIMATION METHOD."

http://www.blackwell-synergy.com/doi/abs/10.1111/j.1475-6811.1999.tb00202.x

"PARTNER EFFECTS IN RELATIONSHIP RESEARCH: CONCEPTUAL ISSUES, ANALYTIC DIFFICULTIES, AND ILLUSTRATIONS. "
Abstract: This article discusses the conceptual meaning of partner effects, which occur when one person is affected by the behavior or characteristics of his or her partner. We show that partner effects can be used to validate the presence of a relationship and can elaborate the particular nature of that relationship. We discuss possible moderation of partner effects and show that many theoretical variables in relationship research (e.g. SIMILARITY) can be viewed as the interactions of partner effects with other variables. We present three extended examples that illustrate the importance of partner effects.

------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------ ------
"METHODOLOGICAL AND DATA ANALYTIC ADVANCES IN THE STUDY OF INTERPERSONAL RELATIONSHIPS: INTRODUCTION TO THE SPECIAL ISSUE"

http://www.blackwell-synergy.com/doi/abs/10.1111/j.1475-6811.1999.tb00200.x

At page 413 says: "It is vital for the study of personal relationships, as for any scientific discipline, to develop methodologies that are specifically designed to address the questions posed by the discipline. The articles in this special issue represent an effort in that direction. Perhaps equally important is the need for individuals who are involved in relationships study to learn these new techniques and to apply them in their research. It is also important for investigators to challenge statisticians to create new analytic techniques when existing ones are inadequate. These tasks are left to you, the reader."

No comments:

Post a Comment