Dataset Information

A stochastic approximation expectation maximization algorithm for estimating Ramsay-curve three-parameter normal ogive model with non-normal latent trait distributions.

ABSTRACT: In the estimation of item response models, the normality of latent traits is frequently assumed. However, this assumption may be untenable in real testing. In contrast to the conventional three-parameter normal ogive (3PNO) model, a 3PNO model incorporating Ramsay-curve item response theory (RC-IRT), denoted as the RC-3PNO model, allows for flexible latent trait distributions. We propose a stochastic approximation expectation maximization (SAEM) algorithm to estimate the RC-3PNO model with non-normal latent trait distributions. The simulation studies of this work reveal that the SAEM algorithm produces more accurate item parameters for the RC-3PNO model than those of the 3PNO model, especially when the latent density is not normal, such as in the cases of a skewed or bimodal distribution. Three model selection criteria are used to select the optimal number of knots and the degree of the B-spline functions in the RC-3PNO model. A real data set from the PISA 2018 test is used to demonstrate the application of the proposed algorithm.

SUBMITTER: Cui Y

PROVIDER: S-EPMC9730697 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A stochastic approximation expectation maximization algorithm for estimating Ramsay-curve three-parameter normal ogive model with non-normal latent trait distributions.

Cui Yuzheng Y Lu Jing J Zhang Jiwei J Shi Ningzhong N Liu Jia J Meng Xiangbin X

Frontiers in psychology 20221124

In the estimation of item response models, the normality of latent traits is frequently assumed. However, this assumption may be untenable in real testing. In contrast to the conventional three-parameter normal ogive (3PNO) model, a 3PNO model incorporating Ramsay-curve item response theory (RC-IRT), denoted as the RC-3PNO model, allows for flexible latent trait distributions. We propose a stochastic approximation expectation maximization (SAEM) algorithm to estimate the RC-3PNO model with non-n ...[more]

PMID: 36506999

Similar Datasets

Project description:Single Particle Tracking (SPT) is a well known class of tools for studying the dynamics of biological macromolecules moving inside living cells. In this paper, we focus on the problem of localization and parameter estimation given a sequence of segmented images. In the standard paradigm, the location of the emitter inside each frame of a sequence of camera images is estimated using, for example, Gaussian fitting (GF), and these locations are linked to provide an estimate of the trajectory. Trajectories are then analyzed by using Mean Square Displacement (MSD) or Maximum Likelihood Estimation (MLE) techniques to determine motion parameters such as diffusion coefficients. However, the problems of localization and parameter estimation are clearly coupled. Motivated by this, we have created an Expectation Maximization (EM) based framework for simultaneous localization and parameter estimation. We demonstrate this framework through two representative methods, namely, Sequential Monte Carlo combined with Expectation Maximization (SMC-EM) and Unscented Kalman Filter combined with Expectation Maximization (U-EM). Using diffusion in two-dimensions as a prototypical example, we conduct quantitative investigations on localization and parameter estimation performance across a wide range of signal to background ratios and diffusion coefficients and compare our methods to the standard techniques based on GF-MSD/MLE. To demonstrate the flexibility of the EM based framework, we do comparisons using two different camera models, an ideal camera with Poisson distributed shot noise but no readout noise, and a camera with both shot noise and the pixel-dependent readout noise that is common to scientific complementary metal-oxide semiconductor (sCMOS) camera. Our results indicate our EM based methods outperform the standard techniques, especially at low signal levels. While U-EM and SMC-EM have similar accuracy, U-EM is significantly more computationally efficient, though the use of the Unscented Kalman Filter limits U-EM to lower diffusion rates.

Project description:BackgroundIn contrast to ordered subset expectation maximization (OSEM), block sequential regularized expectation maximization (BSREM) positron emission tomography (PET) reconstruction algorithms can run until full convergence while controlling image quality and noise. Recent studies with BSREM and 18F-FDG PET reported higher signal-to-noise ratios and higher standardized uptake values (SUV). In this study, we investigate the optimal regularization parameter (β) for clinical 68Ga-PSMA PET/MR reconstructions in the pelvic region applying time-of-flight (TOF) BSREM in comparison to TOF OSEM. Two-minute emission data from the pelvic region of 25 patients who underwent 68Ga-PSMA PET/MR were retrospectively reconstructed. Reference OSEM reconstructions had 28 subsets and 2 iterations. BSREM reconstructions were performed with 15 β values between 150 and 1200. Regions of interest (ROIs) were drawn around lesions and in uniform background. Background SUVmean (average) and SUVstd (standard deviation), and lesion SUVmax (average of 5 hottest voxels) were calculated. Differences were analyzed using the Wilcoxon matched pairs signed-rank test.ResultsA total of 40 lesions were identified in the pelvic region. Background noise (SUVstd) and lesions SUVmax decreased with increasing β. Image reconstructions with β values lower than 400 have higher (p < 0.01) background noise, compared to the reference OSEM reconstructions, and are therefore less useful. Lesions with low activity on images reconstructed with β values higher than 600 have a lower (p < 0.05) SUVmax compared to the reference. These reconstructions are likely visually appealing due to the lower background noise, but the lower SUVmax could possibly render small low-uptake lesions invisible.ConclusionsIn our study, we showed that PET images reconstructed with TOF BSREM in combination with the 68Ga-PSMA tracer result in lower background noise and higher SUVmax values in lesions compared to TOF OSEM. Our study indicates that a β value between 400 and 550 might be the optimal compromise between high SUVmax and low background noise.

Dataset Information

A stochastic approximation expectation maximization algorithm for estimating Ramsay-curve three-parameter normal ogive model with non-normal latent trait distributions.

Publications

A stochastic approximation expectation maximization algorithm for estimating Ramsay-curve three-parameter normal ogive model with non-normal latent trait distributions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets