An Evaluation of DIF Tests in Multistage Tests for Continuous Covariates

Multistage tests are a widely used and efficient type of test presentation that aims to provide accurate ability estimates while keeping the test relatively short. Multistage tests typically rely on the psychometric framework of item response theory. Violations of item response models and other assumptions underlying a multistage test, such as differential item functioning, can lead to inaccurate ability estimates and unfair measurements. There is a practical need for methods to detect problematic model violations to avoid these issues. This study compares and evaluates three methods for the detection of differential item functioning with regard to continuous person covariates in data from multistage tests: a linear logistic regression test and two adaptations of a recently proposed score-based DIF test. While all tests show a satisfactory Type I error rate, the score-based tests show greater power against three types of DIF effects.

An Evaluation of DIF Tests in Multistage Tests for Continuous Covariates

Multistage tests are a widely used and efficient type of test presentation that aims to provide accurate ability estimates while keeping the test relatively short. Multistage tests typically rely on the psychometric framework of item response theory. Violations of item response models and other assumptions underlying a multistage test, such as differential item functioning, can lead to inaccurate ability estimates and unfair measurements. There is a practical need for methods to detect problematic model violations to avoid these issues. This study compares and evaluates three methods for the detection of differential item functioning with regard to continuous person covariates in data from multistage tests: a linear logistic regression test and two adaptations of a recently proposed score-based DIF test. While all tests show a satisfactory Type I error rate, the score-based tests show greater power against three types of DIF effects.

A Quantitative Approach for the Estimation of the Fouling Rate on the Stationary Parts of a Multistage Test Compressor

Gas turbine particle ingestion may lead to the deposition of contaminants in the compressor section, inducing the performance losses of the whole engine. The economic losses derived from this issue push great interest in the investigation of such a phenomenon from a numerical and experimental standpoint. This paper describes a quantitative approach to predict particle deposition on the vanes of an axial compressor starting from the flow field obtained employing CFD simulations. The results are then compared to the experiments performed on the Allison 250 C18 compressor unit subject to particle ingestion under controlled conditions. The results derived from the experimental and numerical investigations are presented, providing insight into the mass deposited on the vanes and the corresponding zones most affected by the particle deposition issue. The numerical model showed good agreement in the estimation of the predicted values of the deposited mass and the corresponding patterns through the compressor stages. The low-complexity approach proposed here, helps the designer to predict the contamination of the stationary rows starting from a simple set of single-phase numerical results. Furthermore, with the implementation of this approach into the design path, the designer could reduce the impact of fouling, looking at the effects of their solutions under the fouling-reduction light.

Flexibility at the Price of Volatility: Concurrent Calibration in Multistage Tests in Practice Using a 2PL Model

Multistage test (MST) designs promise efficient student ability estimates, an indispensable asset for individual diagnostics in high-stakes educational assessments. In high-stakes testing, annually changing test forms are required because publicly known test items impair accurate student ability estimation, and items of bad model fit must be continually replaced to guarantee test quality. This requires a large and continually refreshed item pool as the basis for high-stakes MST. In practice, the calibration of newly developed items to feed annually changing tests is highly resource intensive. Piloting based on a representative sample of students is often not feasible, given that, for schools, participation in actual high-stakes assessments already requires considerable organizational effort. Hence, under practical constraints, the calibration of newly developed items may take place on the go in the form of a concurrent calibration in MST designs. Based on a simulation approach this paper focuses on the performance of Rasch vs. 2PL modeling in retrieving item parameters when items are for practical reasons non-optimally placed in multistage tests. Overall, the results suggest that the 2PL model performs worse in retrieving item parameters compared to the Rasch model when there is non-optimal item assembly in the MST; especially in retrieving parameters at the margins. The higher flexibility of 2PL modeling, where item discrimination is allowed to vary, seems to come at the cost of increased volatility in parameter estimation. Although the overall bias may be modest, single items can be affected by severe biases when using a 2PL model for item calibration in the context of non-optimal item placement.

Pengaruh Metode Latihan Melalui Pendekatan Holistik Terhadap Peningkatan Kemampuan Aerobik Pemaib Sepakbola FIK UNM.

Aerobic Ability FIK UNM football players are still not maximal. This study aims to determine the effect of training methods through a holistic approach to increasing the aerobic ability of FIK UNM football players. This research is an experimental research, the research design used is “One Group Pretest-Posttest”. The population of this study were all football players at FIK UNM and the sampling technique used purposive sampling, with a total sample of 20 football players at FIK UNM. The instrument used for data collection on aerobic ability in this study was the multistage test. The data analysis technique used the t test with a significant level of 5%. Based on the results of the research and discussion, the results of the analysis of the t test for the effect of the training method through a holistic approach to increasing the aerobic ability of FIK UNM football players obtained tcount (17.688)> ttable (1.83). Thus it can be concluded that there is an effect of training methods through a holistic approach that is positive and significant on the aerobic ability of FIK UNM football players. Based on the difference in the average results (mean difference) from the pretest and posttest, it can be seen that the percentage increase in the aerobic ability of FIK UNM football players is 15.66%.

Deposition Pattern Analysis On a Fouled Multistage Test Compressor

Compressor fouling is one of the main causes of gas turbine performance degradation. Microsized particles adhere to the blade surfaces increasing the surface roughness and modifying the airfoil shape. In the present work, the contamination of the Allison 250 C18 multistage compressor engine with four sorts of micrometric dust has been provided. The tests were performed changing the relative humidity at the compressor inlet and the unit rotational speed. After each test, a photographic inspection of the internal fouled parts has been realized and the digital pictures have been analyzed employing an image processing package. The deposits build-up of stator vanes and rotor blades have been postprocessed and the most affected regions of each compressor stage have been highlighted. Besides, a numerical simulation of the machine has been performed. The numerical flow field has been used to highlight the blade regions which show the most favorable conditions for particle deposition. A theoretical model has been applied to the flow field to simulate the particle deposition. The combination of the deposition model with the results of the CFD simulations gives the chance to better understand the experimentally-founded deposition patterns. Those results have been finally compared to the pictures of the patterns. The possibility to detect and measure the deposition patterns on a rotating test rig and the comparison with models and experiments gave the possibility to assess in detail the particle deposition phenomenon on a multistage axial compressor flow path.

ASSESSMENT OF THE WASHING EFFECTIVENESS OF ON-PURPOSE DESIGNED ECO-FRIENDLY CLEANER AGAINST SOOT DEPOSITS

The increment of the industrialization processes led to even more release of carbonaceous particulate into the environment. These airborne contaminants are produced by endothermic machines, coal combustion, heating systems, and production plants. Soot particles suspended into the air can overpass the inlet filters (if present) of gas turbines and deposit onto the internal parts of the compressor. This phenomenon, leading to the modification of the aerodynamic surface of the airfoils, is the main responsible for the gas turbine performance losses over time. This detrimental effect can be partially recovered by washing the compressor unit, frequently. In this work, the assessment of the washing effectiveness against soot deposits of an on-purpose designed eco-friendly cleaner is provided. The removal effectiveness of this water-based cleaner is related to the capability to collect soot particles from surfaces, limiting redeposit phenomena over the stages. The experimental investigation has been carried out by injecting soot particles, under controlled conditions, into a multistage test axial compressor. Using image post-processing techniques, carried out over the entire compressor flow path, a quantitative evaluation of the washing capability has been assessed. Compared with demineralized water, the cleaner was found to be effective if high cleaning performances are expected.