A Comparison of Procedures for Estimating Person Reliability Parameters in the Graded Response Model

Person reliability parameters (PRPs) model temporary changes in individuals’ attribute level perceptions when responding to self‐report items (higher levels of PRPs represent less fluctuation). PRPs could be useful in measuring careless responding and traitedness. However, it is unclear how well current procedures for estimating PRPs can recover parameter estimates. This study assesses these procedures in terms of mean error (ME), average absolute difference (AAD), and reliability using simulated data with known values. Several prior distributions for PRPs were compared across a number of conditions. Overall, our results revealed little differences between using the χ or lognormal distributions as priors for estimated PRPs. Both distributions produced estimates with reasonable levels of ME; however, the AAD of the estimates was high. AAD did improve slightly as the number of items increased, suggesting that increasing the number of items would ameliorate this problem. Similarly, a larger number of items were necessary to produce reasonable levels of reliability. Based on our results, several conclusions are drawn and implications for future research are discussed.     

The “pinpointing effect” vs. the “diffusion effect” of peer influence

Classroom teachers are learning to employ the peer group to “shape up” dissidents. However, singling out a child may produce undesirable side effects such as emotional behavior, resentment, etc. Can the same result be obtained by rewarding the class for ignoring the target behavior of everyone in the room? Twelve subjects were selected from six middle school classes, two from each class. Each entire class was rewarded for increased ignoring of the target behavior (whispering): in the three P (pinpointed) classes, for ignoring the whispering of Designated (target) subjects; in the three D (diffusion) classes, for ignoring whispering by all class members. The results indicate that a peer group can decrease reinforcement of a disruptive behavior and thereby decelerate it in a singled-out child (Pinpointing Effect) or a behavior emitted by any child in class (Diffusion Effect) with equal effectiveness. However, patterns in the data suggest that peers ignored P-Designated subjects most, D subjects next most, and P-Undesignated subjects the least and that this pattern of ignoring was mirrored in the pattern of deceleration of the target behaviors in the three groups. These patterns suggest that the Pinpointing Effect may be stronger than the Diffusion Effect, but further study is needed.