Influence diagnostics

Influential observations are ones that significantly affect the values of the parameter estimates, their standard errors, and the predicted values. One statistic used to detect influential observations has already been presented, the HAT matrix. An obvious way to detect these observations is to remove an observation one at a time and examine how the recalculated parameter estimates compare to their original values. This is the row deletion approach to influence diagnostics and on first glance it would appear that this process requires n-iter-ations—a numerically intensive procedure. Statisticians, however, have derived equations that directly reflect the influence of the ith observation without iteration. One useful diagnostic is DFFITS... 

Table 2.9 Influence diagnostics for the regression model presented in Table 2.8.

Research and development of influence diagnostics for nonlinear models have not received as much attention as for the linear model. One obvious approach to determine the influence an observation has on the data would be to delete the ith observation, refit the model,... 

Similar to the linear regression case, influence diagnostics for linear mixed models can be developed using case deletion. These extensions include Cook s distance, DFFITs, COVRATIO, and PRESS residuals. For example, a linear mixed effects extension to DFFITS is... 

Available space is insufficient to permit demonstrating the partial plots for the example. However, Table 9 lists the leverages and the four influence diagnostics associated with individual observations... 

Anderson JM et al. (2003) CT-guided lung biopsy factors influencing diagnostic yield and complication rate. Clin Radiol 58 791-797... 

Effectiveness of diagnostic tools provided by the card designer influences diagnostic time. ... 

The results of over 1 year of continuous, on-line acoustic emission (AE) structural surveillance of high temperature / high pressure steam headers, gained on 2 M-scale 600MW supercritical multifuel ENEL power units in normal operation, are presented in the paper. The influence of background noise, the correlation between plant operating conditions (steady load, load variations, startup / shutdown transients) and AE activity and the diagnostic evaluation of recorded AE events are also discussed. 

Active devices intended to emit ionizing radiation and intended for diagnostic and therapeutic interventional radiology including devices which control or monitor such devices, or which directly influence their performance, are in Class lib. 

In Chapter 8.5, B. Veyssiere exposes the state of knowledge in detonations. Particular features of the complex multidimensional structure of detonations are presented in relation with the recent results obtained either by nonintrusive optical diagnostics or numerical simulations from high performance calculations. The role of transverse waves in detonation propagation, the existence of correlations between the characteristic dimension of the cellular structure and the critical conditions for detonation initiation and detonation transmission, and the influence of the nonmonotonous heat release process behind the front are examined. Recent developments in the study of spinning detonations are also discussed. 

---