It has generally been assumed that increases in the concrete outcomes of a procedure will result ... more It has generally been assumed that increases in the concrete outcomes of a procedure will result in judgments of greater procedural and distributive fairness, but research on this topic has been inconsistent. Using a classic procedural justice paradigm (Walker, LaTour, Lind, &. Thibaut, 1974), the experiment tested the effects of four levels of outcome. Forty-eight male and female undergraduates were led to believe that their team had been wrongfully charged with cheating in a business simulation game. An adversary adjudication was held, purportedly to resolve the charge. The outcome of the adjudication was confiscation of all, two thirds, one third, or none of the subject's monetary winnings from the game. Both procedural and distributive fairness measures showed dear nonlinear outcome effects. The relationship between outcomes and both fairness measures showed some evidence of being nonmonotonic as well: A two-thirds loss resulted in less favorable reactions than did a total loss. Ratings on other scales suggest that the nonlinear effects are due to beliefs that the judge did not fully consider the evidence in the two-thirds loss and one-third loss conditions. The discussion focuses on the theoretical implications of the findings for procedural justice and social exchange processes and the practical implications for conflict resolution procedure.
Process control, the capacity to influence the content of a conflict resolution hearing, has been... more Process control, the capacity to influence the content of a conflict resolution hearing, has been found repeatedly to affect disputants' judgments of the fairness of conflict resolution procedures, but never has there been an unambiguous test of the effect in nonbinding procedures. It was hypothesized that disputants experiencing nonbinding conflict resolution procedures, as well as those experiencing binding conflict resolution, would judge as more fair procedures high in disputant process control. One hundred nineteen undergraduate males and females were placed in apparent conflict with other suhjects. The procedure used to resolve the conflict was either high or low in disputant process control and was either binding or nonbinding. The outcome of the conflict resolution procedure was either favorable or unfavordblc to the subject. High disputant process control procedures were judged more fair than low disputant process control procedures regardless of whether the decision was binding, confirming the hypothesis. The results support new applications of procedural fairness theory and research and encourage testing of process control-like variables in nonlegal settings.
Applications of item response theory to several problems that are difficult or impossible to solv... more Applications of item response theory to several problems that are difficult or impossible to solve by traditional methods are descnbed It is noted that one important assumption (unidimensionahty) of most item response theories is unlikely to be satisfied by actual data sets A procedure, termed modified parallel analysis, is proposed for determining when violations of this assumption are too severe to allow satisfactory parameter estimation Several Monte Carlo simulation expenments are conducted to evaluate modified parallel analysis The procedure is found to detect violations of unidimensionahty that interfere with parameter estimation An example of the use of modified parallel analysis is presented Lloyd Humphreys for comments on an earlier draft of this article, and to Charles Davis for pointing out the importance of examining the properties of modified parallel analysis when latent variables are not normally distributed
Applications of item response theory to several problems that are difficult or impossible to solv... more Applications of item response theory to several problems that are difficult or impossible to solve by traditional methods are descnbed It is noted that one important assumption (unidimensionahty) of most item response theories is unlikely to be satisfied by actual data sets A procedure, termed modified parallel analysis, is proposed for determining when violations of this assumption are too severe to allow satisfactory parameter estimation Several Monte Carlo simulation expenments are conducted to evaluate modified parallel analysis The procedure is found to detect violations of unidimensionahty that interfere with parameter estimation An example of the use of modified parallel analysis is presented Lloyd Humphreys for comments on an earlier draft of this article, and to Charles Davis for pointing out the importance of examining the properties of modified parallel analysis when latent variables are not normally distributed
This monte carlo study assessed the accuracy of simultaneous estimation of item and person parame... more This monte carlo study assessed the accuracy of simultaneous estimation of item and person parameters in item response theory. Item responses were simulated using the two-and three-parameter logistic models. Samples of 200, 500, 1,000, and 2,000 simulated examinees and tests of 15, 30, and 60 items were generated. Item and person parameters were then estimated using the appropriate model. The root mean squared error between recovered and actual item characteristic curves served as the principal measure of estimation accuracy for items. The accuracy of estimates of ability was as-
It has generally been assumed that increases in the concrete outcomes of a procedure will result ... more It has generally been assumed that increases in the concrete outcomes of a procedure will result in judgments of greater procedural and distributive fairness, but research on this topic has been inconsistent. Using a classic procedural justice paradigm (Walker, LaTour, Lind, &. Thibaut, 1974), the experiment tested the effects of four levels of outcome. Forty-eight male and female undergraduates were led to believe that their team had been wrongfully charged with cheating in a business simulation game. An adversary adjudication was held, purportedly to resolve the charge. The outcome of the adjudication was confiscation of all, two thirds, one third, or none of the subject's monetary winnings from the game. Both procedural and distributive fairness measures showed dear nonlinear outcome effects. The relationship between outcomes and both fairness measures showed some evidence of being nonmonotonic as well: A two-thirds loss resulted in less favorable reactions than did a total loss. Ratings on other scales suggest that the nonlinear effects are due to beliefs that the judge did not fully consider the evidence in the two-thirds loss and one-third loss conditions. The discussion focuses on the theoretical implications of the findings for procedural justice and social exchange processes and the practical implications for conflict resolution procedure.
Process control, the capacity to influence the content of a conflict resolution hearing, has been... more Process control, the capacity to influence the content of a conflict resolution hearing, has been found repeatedly to affect disputants' judgments of the fairness of conflict resolution procedures, but never has there been an unambiguous test of the effect in nonbinding procedures. It was hypothesized that disputants experiencing nonbinding conflict resolution procedures, as well as those experiencing binding conflict resolution, would judge as more fair procedures high in disputant process control. One hundred nineteen undergraduate males and females were placed in apparent conflict with other suhjects. The procedure used to resolve the conflict was either high or low in disputant process control and was either binding or nonbinding. The outcome of the conflict resolution procedure was either favorable or unfavordblc to the subject. High disputant process control procedures were judged more fair than low disputant process control procedures regardless of whether the decision was binding, confirming the hypothesis. The results support new applications of procedural fairness theory and research and encourage testing of process control-like variables in nonlegal settings.
Applications of item response theory to several problems that are difficult or impossible to solv... more Applications of item response theory to several problems that are difficult or impossible to solve by traditional methods are descnbed It is noted that one important assumption (unidimensionahty) of most item response theories is unlikely to be satisfied by actual data sets A procedure, termed modified parallel analysis, is proposed for determining when violations of this assumption are too severe to allow satisfactory parameter estimation Several Monte Carlo simulation expenments are conducted to evaluate modified parallel analysis The procedure is found to detect violations of unidimensionahty that interfere with parameter estimation An example of the use of modified parallel analysis is presented Lloyd Humphreys for comments on an earlier draft of this article, and to Charles Davis for pointing out the importance of examining the properties of modified parallel analysis when latent variables are not normally distributed
Applications of item response theory to several problems that are difficult or impossible to solv... more Applications of item response theory to several problems that are difficult or impossible to solve by traditional methods are descnbed It is noted that one important assumption (unidimensionahty) of most item response theories is unlikely to be satisfied by actual data sets A procedure, termed modified parallel analysis, is proposed for determining when violations of this assumption are too severe to allow satisfactory parameter estimation Several Monte Carlo simulation expenments are conducted to evaluate modified parallel analysis The procedure is found to detect violations of unidimensionahty that interfere with parameter estimation An example of the use of modified parallel analysis is presented Lloyd Humphreys for comments on an earlier draft of this article, and to Charles Davis for pointing out the importance of examining the properties of modified parallel analysis when latent variables are not normally distributed
This monte carlo study assessed the accuracy of simultaneous estimation of item and person parame... more This monte carlo study assessed the accuracy of simultaneous estimation of item and person parameters in item response theory. Item responses were simulated using the two-and three-parameter logistic models. Samples of 200, 500, 1,000, and 2,000 simulated examinees and tests of 15, 30, and 60 items were generated. Item and person parameters were then estimated using the appropriate model. The root mean squared error between recovered and actual item characteristic curves served as the principal measure of estimation accuracy for items. The accuracy of estimates of ability was as-
Uploads
Papers by Robin Lissak