Charles M. Tudd, Eliot R. Smith, and Louise H. Kidder. Research methods in social relations. Harcourt Brace Jovanovich College Publishers. Sixth Edition  Home/Search   Document Not in Database   Summary   Related Articles   Check

....hypotheses. Some examples of product abstractions are data flow graphs and control flow graphs. In our study, we use graphs based on dependency links between data and subroutines in high level software design. 5) Define measures. A measure is defined for capturing some intuitive concept [31], e.g. size, complexity, cohesion, coupling, such as those used in the experimental hypotheses. In our study, we define measures for cohesion and coupling based on dependency links among data and subroutines in highlevel software design. The definition of sound measures requires that they be ....

C.M. Judd, E.R. Smith, and L.H. Kidder, "Research,, Methods in Social Relations. Harcourt Brace Jovanovich College Publishers, 1991.

....be directly measured. They require some concrete representations that approximate what is meant when speaking about them. In social science, the abstract concepts (in our case, the basic attributes) are called constructs and the concrete representations we are looking for are called variables [Judd91]. For any construct, there can be many different ways to measure it, that is more corresponding variables. Once a variable has been identified, the sequence of steps to measure the variable (expressed as a number or a rank) is its operational definition. The degree to which the constructs of ....

C. M. Judd, E. R. Smith, and L. H. Kidder, Research Methods in Social Relations, Sixth edition, Harcourt Brace Jovanovich College Publishers, 1991.

....skills needed for the study. To control for differences in skills and experience, the students were randomly grouped into eight teams of three students per team. To ensure the teams were comparable with respect to the ability of their members, the following two step procedure (known as blocking [17]) was used to assign students to teams: Each student s level of experience was characterized. We used questionnaires and performed interviews. We asked the students about their previous working experience, their student status (part time or full time) their computer science degree (B.S. ....

.... Implementing the correction, including design changes, code modifications, and regression testing Validity The study s validity can be analyzed from two perspectives: internal (What threats to the conclusions can we draw from the study ) and external (How generalizable are these results ) [17]. With respect to internal validity, we can say that subjects were classified according to their ability and assigned randomly to form equivalent teams. Therefore, we are less likely to obtain biased results due to differences in ability across teams. However, performing a formal controlled ....

Judd, C.M., Smith, E.R., and Kidder, L.H. Research Methods in Social Relations. Harcourt Brace Jovanovich College Publishers, 1991.

....We consider it to be a case study because it is one specific instance of the observed phenomena. Central to this technique is an extended series of repeated observations to establish credibility [18] In this way, the method is similar to the ones used in Astronomy and the social sciences [8]. Finally, a theory is built using these observations (e.g. with grounded theory [5] to make predictions (hypotheses) that are tested with future studies. Our strategy for understanding the problem of parallel changes is to look at the problem from a number of different angles and viewpoints in ....

Charles M. Judd, Eliot R. Smith, and Louise H. Kidder. Research Methods in Social Relations. Harcourt Brace Jovanovich College Publishers, 1991.

....hypotheses. Some examples of product abstractions are data flow graphs and control flow graphs. In our study, we use graphs based on dependency links between data and subroutines in high level software design. 5. Define measures. A measure is defined for capturing some intuitive concept [JSK91], e.g. size, complexity, cohesion, coupling) such as those used in the experimental hypotheses. In our study, we define measures for cohesion and coupling based on dependency links among data and subroutines in high level software design. The definition of sound measures requires that they be ....

C. M. Judd, E. R. Smith and L. H. Kidder. Research, Methods in Social Relations. Harcourt Brace Jovanovich College Publishers. 1991.

....Validity This section discusses the various threats to validity for this study. 4.7.1 Threats to Internal Validity We explored the following threats to internal validity to assess their possible interference. These are: mortality (non random subject loss) maturation effect and history effects [17]: 1. Mortality Two subjects did not completely participate in the experiment. We therefore decided not to include the data points of these subjects but this biases the design of the experiment given the small number of subjects used. 2. Maturation effects This is the effect of processes taking ....

....and Perspectivebased Reading. As we did not control the domain order and did not use control groups we were not able to evaluate the learning effect. 3. History History refers to any effect induced by interrupting the experiment for periods of time and relevant for the examined hypothesis [17]. Since there was a gap of one day between the two days of the experiment, improvement that appears due to the technique may be attrib uted to other events that took place in between. We instructed the subjects not to talk with each other and not to do anything that could have an influence on ....

Charles M. Judd, Eliot R. Smith, Louise H. Kidder, Research Methods in Social Relations, Harcourt Brace Jovanovich College Publishers, 1986.

....We consider it to be a case study because it is one specific instance of the observed phenomena. Central to this technique is an extended series of repeated observations to establish credibility [18] In this way, the method is similar to the ones used in Astronomy and the social sciences [8]. Finally, a theory is built using these observations (e.g. with grounded theory [5] to make predictions (hypotheses) that are tested with future studies. Our strategy for understanding the problem of parallel changes is to look at the problem from a number of different angles and viewpoints in ....

Charles M. Judd, Eliot R. Smith, and Louise H. Kidder. Research Methods in Social Relations. Harcourt Brace Jovanovich College Publishers, 1991.

No context found.

Charles M. Tudd, Eliot R. Smith, and Louise H. Kidder. Research methods in social relations. Harcourt Brace Jovanovich College Publishers. Sixth Edition

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC