A Longitudinal Nonparametric Classification Method for Assessing Change in Latent Attributes Over Time

<p>This study proposed a longitudinal Hamming distance discrimination (Long-HDD) method to improve the application of longitudinal cognitive diagnosis in practical teaching by introducing a simple computation and less time-consuming nonparametric classification method—HDD—into longitudinal diagnostic data processing. Compared with the HDD, the proposed method represents correlation or dependence between adjacent time points of the same student using Hamming distance in anticipation of using information from the previous time point to improve the classification accuracy at the current time point. A simulation study was conducted to explore the performance of the proposed method in longitudinal diagnostic data analysis and to compare the performance of the proposed method with the HDD and a parametric longitudinal diagnostic classification model. The findings suggest that (1) the Long-HDD can provide high classification accuracy in longitudinal diagnostic data analysis; (2) compared with the parametric model, the Long-HDD is almost unaffected by sample size and performs better than the parametric model in small sample sizes; and (3) the Long-HDD consumes much less computing time than the parametric model. Overall, the Long-HDD is well suited to analyzing longitudinal diagnostic data and can provide speedy diagnostic feedback due to its convenient computation, which is especially significant in small-scale assessments at the classroom and school levels.</p>

A Longitudinal Nonparametric Classification Method for Assessing Change in Latent Attributes Over Time

<p>This study proposed a longitudinal Hamming distance discrimination (Long-HDD) method to improve the application of longitudinal cognitive diagnosis in practical teaching by introducing a simple computation and less time-consuming nonparametric classification method—HDD—into longitudinal diagnostic data processing. Compared with the HDD, the proposed method represents correlation or dependence between adjacent time points of the same student using Hamming distance in anticipation of using information from the previous time point to improve the classification accuracy at the current time point. A simulation study was conducted to explore the performance of the proposed method in longitudinal diagnostic data analysis and to compare the performance of the proposed method with the HDD and a parametric longitudinal diagnostic classification model. The findings suggest that (1) the Long-HDD can provide high classification accuracy in longitudinal diagnostic data analysis; (2) compared with the parametric model, the Long-HDD is almost unaffected by sample size and performs better than the parametric model in small sample sizes; and (3) the Long-HDD consumes much less computing time than the parametric model. Overall, the Long-HDD is well suited to analyzing longitudinal diagnostic data and can provide speedy diagnostic feedback due to its convenient computation, which is especially significant in small-scale assessments at the classroom and school levels.</p>

ANALISIS PERBANDINGAN KINERJA CART KONVENSIONAL, BAGGING DAN RANDOM FOREST PADA KLASIFIKASI OBJEK: HASIL DARI DUA SIMULASI

The conventional CART method is a nonparametric classification method built on categorical response data. Bagging is one of the popular ensemble methods whereas, Random Forests (RF) is one of the relatively new ensemble methods in the decision tree that is the development of the Bagging method. Unlike Bagging, Random Forest was developed with the idea of adding layers to the random resampling process in Bagging. Therefore, not only randomly sampled sample data to form a classification tree, but also independent variables are randomly selected and newly selected as the best divider when determining the sorting of trees, which is expected to produce more accurate predictions. Based on the above, the authors are interested to study the three methods by comparing the accuracy of classification on binary and non-binary simulation data to understand the effect of the number of sample sizes, the correlation between independent variables, the presence or absence of certain distribution patterns to the accuracy generated classification method. results of the research on simulation data show that the Random Forest ensemble method can improve the accuracy of classification.

The k conditional nearest neighbor algorithm for classification and class probability estimation

The k nearest neighbor (kNN) approach is a simple and effective nonparametric algorithm for classification. One of the drawbacks of kNN is that the method can only give coarse estimates of class probabilities, particularly for low values of k. To avoid this drawback, we propose a new nonparametric classification method based on nearest neighbors conditional on each class: the proposed approach calculates the distance between a new instance and the kth nearest neighbor from each class, estimates posterior probabilities of class memberships using the distances, and assigns the instance to the class with the largest posterior. We prove that the proposed approach converges to the Bayes classifier as the size of the training data increases. Further, we extend the proposed approach to an ensemble method. Experiments on benchmark data sets show that both the proposed approach and the ensemble version of the proposed approach on average outperform kNN, weighted kNN, probabilistic kNN and two similar algorithms (LMkNN and MLM-kHNN) in terms of the error rate. A simulation shows that kCNN may be useful for estimating posterior probabilities when the class distributions overlap.