The authors describe 2 efficiency (planned missing data) designs for measurement: the 3-form design and the 2-method measurement design. The 3-form design, a kind of matrix sampling, allows researchers to leverage limited resources to collect data for 33% more survey questions than can be answered by any 1 respondent. Power tables for estimating correlation effects illustrate the benefit of this design. The 2-method measurement design involves a relatively cheap, less valid measure of a construct and an expensive, more valid measure of the same construct. The cost effectiveness of this design stems from the fact that few cases have both measures, and many cases have just the cheap measure. With 3 brief simulations involving structural equation models, the authors show that compared with the same-cost complete cases design, a 2-method measurement design yields lower standard errors and a higher effective sample size for testing important study parameters. With a large cost differential between cheap and expensive measures and small effect sizes, the benefits of the design can be enormous. Strategies for using these 2 designs are suggested.

This chapter describes a general approach to handling missing data in psychological research. It provides a theoretical background in readable, nontechnical fashion. Our overall goal was to give practical, usable advice, rather than to give a detailed statistical treatment of issues surrounding analysis of incomplete data. We give an overview of the older, unacceptable methods for handling incomplete data, so that readers will know what approaches to avoid; although analysis of complete cases is sometimes an acceptable solution, we argue that pairwise deletion and mean substitution should be avoided. With respect to newer, acceptable methods, we give a general overview, including a brief discussion of the full information maximum likelihood structural equation modeling procedures (such as Amos, Mx, LISREL 8.5, and Mplus), but focus primarily on multiple imputation as a general solution. We give specific guidelines for making use of state‐of‐the‐art multiple imputation software and step‐by‐step instructions for using multiple imputation with Schafer's (1997) NORM program. Empirical examples of exploratory and data quality analyses and a substantive illustration involving multiple linear regression demonstrate the use of multiple imputation in practice. The chapter concludes with a discussion of some practical issues that often arise in connection with the analysis of incomplete data.

No abstract

The main objective of this study was to evaluate the effects of the introduction of educational videogames into the classroom, on learning, motivation, and classroom dynamics. These effects were studied using a sample of 1274 students from economically disadvantaged schools in Chile. The videogames were specifically designed to address the educational goals of the first and second years of school, for basic mathematics and reading comprehension. The sample was divided into experimental groups (EG), internal control groups (IC) and external control groups (EC). Students in the EG groups, used the experimental video games during an average of 30 h over a 3-month period. They were evaluated on their acquisition of reading comprehension, spelling, and mathematical skills, and on their motivation to use video games. Teachers' expectations of change due to the use of video games, their technological transfer, and handling of classroom dynamics, were assessed through ad hoc tests and classroom observations. The results show significant differences between the EG and IC groups in relation to the EC group in Math, Reading Comprehension and Spelling, but no significant differences in these aspects were found between the EG and the IC groups. Teacher reports and classroom observations confirm an improvement in motivation to learn, and a positive technological transfer of the experimental tool. Although further studies regarding the effects of learning through videogame use are imperative, positive effects on motivation and classroom dynamics, indicate that the introduction of educational video games can be a useful tool in promoting learning within the classroom. #

The developmental correlates of diffuse support for the polity and civic commitments were explored in a survey of 1,052 students (mean age ϭ 14.96 years) from African American, Arab American, European American, and Latino American backgrounds. Results of structural equation modeling revealed that regardless of their age, gender, or ethnic background, youth were more likely to believe that America was a just society and to commit to democratic goals if they felt a sense of community connectedness, especially if they felt that their teachers practiced a democratic ethic at school. Discussion focuses on the civic purposes of education in inculcating a sense of identification with the polity in younger generations.

Adolescents' beliefs about the legitimacy of parental authority and obligation to obey were examined in 568 Chilean adolescents (11-14 years old at Wave 1), followed once a year for 4 years. Adolescents' beliefs about parental legitimacy and obligation to obey declined with age. The steepest decline occurred during early adolescence, particularly in the personal domain. Adolescents who were uninvolved in problem behavior and perceived their parents to be supportive or high in monitoring at Wave 1 were more likely to endorse parental legitimacy and obligation to obey over time. There was little evidence that parenting or problem behavior moderated the normative decline in adolescents' beliefs about parental authority. Findings concerning individual differences in adolescents' endorsement of parental authority are highlighted in this study.

he assessment of change over time is fundamental to answering important research questions in the social sciences, including the study of psychological T and social development, the process of learning, and the behavior of individuals in organizations. If researchers have panel data (repeated measurements taken on a relatively large group of individuals on a small number of occasions), if the phenomenon of interest changes systematically rather than fluctuating randomly, and if the variable of interest is measured on a continuous scale, then growth curve analysis is an appropriate and powerful method for drawing correct inferences about change.This strategy is based on fitting a model to the repeated measures that allows for the description of systematic interindividual differences in intraindividual change. The individual growth modeling framework uses a hierarchical model to represent simultaneously individual status as a function of time (the Level 1 model, in random coefficient terminology) and interindividual differences in true change (the Level 2 model). Typically, the simplest forms of these models include parameters that describe individual growth, population average change, and the heterogeneity around the average change. If interindividual differences in change are present, covariates can be added to the model to predict such variability One of the most popular approaches to estimating the model parameters is to use mean and covariance structure analysis, as implemented in a variety of structural equation modeling (SEM) software packages, such as LISREL, AMOS, or EQS. A key feature of these structural equation models is the capacity to describe the relation of manifest (observed) indicators to the underlying latent construct that is assumed to drive the responses on these indicators. What is noteworthy is that this feature has been ignored in the SEM parameterization

tatistical procedures for handling missing data are becoming increasingly common in a wide range of social research. Schafer's (1997) NORM software S for multiple imputation has been available for some time as a stand-alone Microsoft Windows application, and several articles and chapters have been written describing its use (Schafer