scholarly journals Generalized inductive item tree analysis

2020 ◽  
Author(s):  
Ali Ünlü ◽  
Martin Schrepp
Keyword(s):  
Binary Data ◽  
Data Matrix ◽  
Polytomous Items ◽  
Current Form ◽  
Tree Analysis ◽  
Test Items ◽  
Negative Item ◽  
Positive Item ◽  
Exploratory Data ◽  
Item Scores

Inductive item tree analysis is an established method of Boolean analysis of questionnaires. By exploratory data analysis, from a binary data matrix, the method extracts logical implications between dichotomous test items based on their positive item scores. For example, assume that we have the problems i and j of a test that can be solved or failed by subjects. With inductive item tree analysis, an implication between the items i and j can be uncovered, which has the interpretation "If a subject is able to solve item i, then this subject is also able to solve item j". Hence, in the current form of the method, (a) solely dichotomous items are considered, and (b) conclusions are drawn from only positive item scores. In this paper, we provide extensions to these restrictions. First, as remedy for (b), we focus on the dichotomous formulation of the inductive item tree analysis algorithm and describe a procedure of how to extend the dichotomous variant to also include negative item scores. Second, to address (a), we further extend our approach to the general case of polytomous items, when more than two answer categories are possible. Thus, we introduce extensions of inductive item tree analysis that can deal with nominal polytomous and ordinal polytomous answer scales. To show their usefulness, the dichotomous and polytomous extensions proposed in this paper are illustrated with empirical data and in a simulation study.

scholarly journals Symmetric Metric Learning with Adaptive Margin for Recommendation

2020 ◽  
Vol 34 (04) ◽  
pp. 4634-4641
Author(s):  
Mingming Li ◽  
Shuai Zhang ◽  
Fuqing Zhu ◽  
Wanhui Qian ◽  
Liangjun Zang ◽  
...  
Keyword(s):  
Recommender Systems ◽  
Metric Space ◽  
State Of The Art ◽  
Metric Learning ◽  
Current User ◽  
Experimental Results ◽  
Negative Item ◽  
Positive Item ◽  
User Centric ◽  
The Impact

Metric learning based methods have attracted extensive interests in recommender systems. Current methods take the user-centric way in metric space to ensure the distance between user and negative item to be larger than that between the current user and positive item by a fixed margin. While they ignore the relations among positive item and negative item. As a result, these two items might be positioned closely, leading to incorrect results. Meanwhile, different users usually have different preferences, the fixed margin used in those methods can not be adaptive to various user biases, and thus decreases the performance as well. To address these two problems, a novel Symmetic Metric Learning with adaptive margin (SML) is proposed. In addition to the current user-centric metric, it symmetically introduces a positive item-centric metric which maintains closer distance from positive items to user, and push the negative items away from the positive items at the same time. Moreover, the dynamically adaptive margins are well trained to mitigate the impact of bias. Experimental results on three public recommendation datasets demonstrate that SML produces a competitive performance compared with several state-of-the-art methods.

Differential Responding to Positive and Negative Items: The Case of a Negative Item in a Questionnaire for Course and Faculty Evaluation

2001 ◽  
Vol 88 (2) ◽  
pp. 497-500 ◽  
Author(s):  
Ali Mohamed Ibrahim
Keyword(s):  
Teacher Evaluation ◽  
Rating Scales ◽  
Faculty Evaluation ◽  
Random Responding ◽  
Self Rating ◽  
Factor Analytic ◽  
Negative Item ◽  
Response Sets ◽  
Two Factors ◽  
Positive Item

Previous factor-analytic studies of self-rating scales have yielded a factor on which negatively worded items loaded separately. The present study investigated the existence for such a factor in a questionnaire for course and teacher evaluation which included one negative item. The questionnaire was administered in 1,095 university classes Two factors emerged, an exclusively positive-item factor and another factor on which the single negative item and one positive item loaded It was suggested that both items of Factor 2 were ambiguous and may identify tendencies such as acquiescence, random responding, and response sets.

scholarly journals Using AFLP Markers for the Analysis of the Genetic Diversity of Apricot Cultivars in Tunisia

2008 ◽  
Vol 133 (2) ◽  
pp. 204-212 ◽  
Author(s):  
Lamia Krichen ◽  
Joao M.S. Martins ◽  
Patrick Lambert ◽  
Abderrazzak Daaloul ◽  
Neila Trifi-Farah ◽  
...  
Keyword(s):  
Binary Data ◽  
Genetic Basis ◽  
Geographic Origin ◽  
Morphological Diversity ◽  
Prunus Armeniaca ◽  
Data Matrix ◽  
Polymorphic Markers ◽  
Wide Range ◽  
Ward Clustering ◽  
High Level

Apricot (Prunus armeniaca L.) culture is present in a wide range of areas and microclimates in Tunisia. Each of them contains several specific cultivars and shows a high level of morphological diversity. To characterize the related diversity, surveys were performed in the four main apricot cultivation areas, where 31 cultivars representing apricot landraces were sampled. DNA was extracted and amplified with five different EcoRI–MseI AFLP primer combinations. Autoradiographs revealed 203 polymorphic markers in a total of 295 detected fragments. A set of redundant marker patterns was identified and deleted from the binary data matrix, data analysis being performed on a total of 167 polymorphic markers. In a dendrogram calculated by the Ward clustering technique, two major groups were identified, separating nine cultivars from the other 22. Three subgroups have been revealed in each of the main groups. The groups and subgroups identified on the genetic basis are closely related to the geographic origin of the cultivars. Analysis of the actual repartition suggested at least the introduction of two independent gene funds in the northern and central prospected areas, followed by a local diversification and then a dissemination phase. Their interaction occurred at least in the two sites of Testour and Sbikha.

scholarly journals A new approach to computerized adaptive testing

2017 ◽  
Vol 10 (3) ◽  
pp. 33-45 ◽  
Author(s):  
L.S. Kuravsky ◽  
S.L. Artemenkov ◽  
G.A. Yuryev ◽  
E.L. Grigorenko
Keyword(s):  
Markov Processes ◽  
Computerized Adaptive Testing ◽  
Model Identification ◽  
Testing Procedure ◽  
Adaptive Testing ◽  
Observation Data ◽  
Polytomous Items ◽  
Discrete State ◽  
New Approach ◽  
Test Items

A new approach to computerized adaptive testing is presented on the basis of discrete-state discrete-time Markov processes. This approach is based on an extension of the G. Rasch model used in the Item Response Theory (IRT) and has decisive advantages over the adaptive IRT testing. This approach has a number of competitive advantages: takes into account all the observed history of performing test items that includes the distribution of successful and unsuccessful item solutions; incorporates time spent on performing test items; forecasts results in the future behavior of the subjects; allows for self-learning and changing subject abilities during a testing procedure; contains easily available model identification procedure based on simply accessible observation data. Markov processes and the adaptive transitions between the items remain hidden for the subjects who have access to the items only and do not know all the intrinsic mathematical details of a testing procedure. The developed model of adaptive testing is easily generalized for the case of polytomous items and multidimensional items and model structures.

Evaluating the Magnitude of Differential Item Functioning in Polytomous Items

1996 ◽  
Vol 21 (3) ◽  
pp. 187-201 ◽  
Author(s):  
Rebecca Zwick ◽  
Dorothy T. Thayer
Keyword(s):  
Hypothesis Testing ◽  
Differential Item Functioning ◽  
Standard Error ◽  
Simulated Data ◽  
Ordinal Scale ◽  
Polytomous Items ◽  
Testing Procedures ◽  
Test Items ◽  
Item Functioning ◽  
Error Formulas

Several recent studies have investigated the application of statistical inference procedures to the analysis of differential item functioning (DIF) in polytomous test items that are scored on an ordinal scale. Mantel’s extension of the Mantel-Haenszel test is one of several hypothesis-testing methods for this purpose. The development of descriptive statistics for characterizing DIF in polytomous test items has received less attention. As a step in this direction, two possible standard error formulas for the polytomous DIF index proposed by Dorans and Schmitt were derived. These standard errors, as well as associated hypothesis-testing procedures, were evaluated though application to simulated data. The standard error that performed better is based on Mantel’s hypergeometric model. The alternative standard error, based on a multinomial model, tended to yield values that were too small.

scholarly journals A Note on the D-Scoring Method Adapted for Polytomous Test Items

2018 ◽  
Vol 79 (3) ◽  
pp. 545-557 ◽  
Author(s):  
Dimiter M. Dimitrov ◽  
Yong Luo
Keyword(s):  
Item Response ◽  
Psychological Assessment ◽  
Response Model ◽  
Response Functions ◽  
Graded Response Model ◽  
Unified Framework ◽  
Polytomous Items ◽  
Scoring Method ◽  
Test Items ◽  
Graded Response

An approach to scoring tests with binary items, referred to as D-scoring method, was previously developed as a classical analog to basic models in item response theory (IRT) for binary items. As some tests include polytomous items, this study offers an approach to D-scoring of such items and parallels the results with those obtained under the graded response model (GRM) for ordered polytomous items in the framework of IRT. The proposed design of using D-scoring with “virtual” binary items generated from polytomous items provides (a) ability scores that are consistent with their GRM counterparts and (b) item category response functions analogous to those obtained under the GRM. This approach provides a unified framework for D-scoring and psychometric analysis of tests with binary and/or polytomous items that can be efficient in different scenarios of educational and psychological assessment.

Virulence in populations of Puccinia graminis f.sp. tritici in Canada from 1952 to 1998: a non-parametric analysis

2001 ◽  
Vol 79 (5) ◽  
pp. 556-569
Author(s):  
D E Harder ◽  
B R Baum ◽  
B D McCallum
Keyword(s):  
Parametric Analysis ◽  
Binary Data ◽  
Infection Type ◽  
Single Gene ◽  
Data Matrix ◽  
Puccinia Graminis ◽  
Heterogeneous Database ◽  
Pacific Population ◽  
The Pacific ◽  
Non Parametric

Six hundred and twenty six isolates of Puccinia graminis f.sp. tritici that were collected and stored between 1952 and 1998 were identified using 32 single-gene differential wheat lines. These pathotypes represented isolates from field surveys, nursery collections, and from greenhouse experiments. Infection type data was converted to a binary data matrix with a 0 (resistant) or 1 (susceptible) numeral assigned to each isolate for each differential line. The Gower coefficient of similarity was determined for every pair of isolates, then they were clustered using the non-parametric cluster analysis MODECLUS. Eight significantly different clusters were obtained from an overall heterogeneous database of 405 unique pathotypes representing all regions of Canada. For further analysis, isolates obtained only from field survey collections were selected and divided by region of collection into Pacific (45 pathotypes), prairie (191 pathotypes), and eastern Canadian (83 pathotypes) populations. The Pacific population, which was both sexually and asexually reproducing, consisted of two clusters. The prairie population, strictly asexually reproducing, consisted of nine clusters, and the eastern population, which may be partially sexually reproducing, had three clusters. The Pacific population was shown to be significantly different from the prairie and eastern populations, while the prairie and eastern populations were less distinct. The pathotype composition of the regional clusters, reliability of cluster segregation using non-parametric analysis, and usefulness of the data to contribute to a revised nomenclature of P. graminis f.sp. tritici, are evaluated.Key words: stem rust, black rust, wheat, specific virulence.

Effects of affective-semantic mode of item presentation in balanced self-report scales: biased construct validity of the Zung Self-rating Depression Scale

1996 ◽  
Vol 26 (6) ◽  
pp. 1161-1168 ◽  
Author(s):  
C. K. W. Schotte ◽  
M. Maes ◽  
R. Cluydts ◽  
P. Cosyns
Keyword(s):  
Construct Validity ◽  
Depressive Symptomatology ◽  
Depression Scale ◽  
Self Report ◽  
Factor Analyses ◽  
Self Rating ◽  
Negative Item ◽  
Analytical Research ◽  
Item Presentation ◽  
Item Scores

SynopsisThe widely applied procedure of balancing self-report instruments by including positively and negatively keyed items is exemplified by the Zung Self-rating Depression Scale (SDS). Investigation of the influence of the symptom-positive and symptom-negative item modes on the SDS in a depressed population resulted in two major findings. First, the reversed scoring of the symptom-negative items resulted in higher mean item scores. Secondly, factor analyses of the SDS in the present study and in previous research revealed that the semantic modes of item presentation were represented in the factor structure of the SDS. These findings were confirmed by analyses with the State–Trait Anxiety Inventory (STAI) and by previous factor analytical research with balanced instruments and were interpreted within the framework of the theory of Positive and Negative Affect. The present data cast doubts on the construct validity of the SDS as a measure of depressive symptomatology due to the presence of the negatively keyed items and suggest reconsideration of the use of balanced instruments for minimization of the acquiescence response set.

scholarly journals On Equivalence of Quantum Liouville Equation and Metric Compatibility Condition, a Ricci Flow Approach

2016 ◽  
Author(s):  
Manouchehr Amiri
Keyword(s):  
Density Matrix ◽  
Liouville Equation ◽  
Ricci Flow ◽  
Compatibility Condition ◽  
Binary Data ◽  
Data Matrix ◽  
Field Equations ◽  
Metric Tensor ◽  
Curved Manifolds ◽  
Physical Measurements

In this paper after introducing a model of binary data matrix for physical measurements of an evolving system (of particles), we develop a Hilbert space as an ambient space to derive induced metric tensor on embedded parametric manifold identified by associated joint probabilities of particles observables (parameters). Parameter manifold assumed as space-like hypersurface evolving along time axis, an approach that resembles 3+1 formalism of ADM and numerical relativity. We show the relation of endowed metric with related density matrix. Identification of system density matrix by this metric tensor, leads to the equivalence of quantum Liouville equation and metric compatibility condition ∇0gij = 0 while covariant derivative of metric tensor has been calculated respect to Wick rotated time coordinate. After deriving a formula for expected energy of the particles and imposing the normalized Ricci flow as governing dynamics, we prove the equality of this expected energy with local scalar curvature of related manifold. Consistency of these results with Einstein tensor, field equations and Einstein-Hilbert action has been verified. Given examples clarify the compatibility of the results with well-known principles. This model provides a background for geometrization of quantum mechanics compatible with curved manifolds and information geometry.

Sign in / Sign up

Export Citation Format

Share Document