Dropout Model Research Articles

A Multinomial and Predictive Analysis of Factors Associated with University Dropout

The phenomenon of dropout, by its complexity and educational and social impact, has been extensively studied to understand the specific causes. In this line of research, the purpose of this study was to analyze explanatory and predictive models of student dropout from university studies at the Instituto Tecnológico de Costa Rica (TEC), based on many variables recorded in the institutional system indicators. The first stage of the analysis considered multinomial regression models to identify the influence of these variables on the dropout. In the second analysis, six machine learning algorithms were evaluated in order to find a model that would predict student dropout. Data analysis showed that the probability of dropping out is related to sociodemographic variables, study program, academic history, scholarship and other benefits, and performance after first semester. In addition, the best predictor of dropout algorithm was the “random forest”, a probability of 0.83 to predict the dropout correctly and to capture 34% of the actual student dropout. These results are the first step toward building a more robust predictive model of dropout, which will contribute to preventive decision making in this university.

A bidimensional finite mixture model for longitudinal data subject to dropout.

In longitudinal studies, subjects may be lost to follow up and, thus, present incomplete response sequences. When the mechanism underlying the dropout is nonignorable, we need to account for dependence between the longitudinal and the dropout process. We propose to model such a dependence through discrete latent effects, which are outcome-specific and account for heterogeneity in the univariate profiles. Dependence between profiles is introduced by using a probability matrix to describe the corresponding joint distribution. In this way, we separately model dependence within each outcome and dependence between outcomes. The major feature of this proposal, when compared with standard finite mixture models, is that it allows the nonignorable dropout model to properly nest its ignorable counterpart. We also discuss the use of an index of (local) sensitivity to nonignorability to investigate the effects that assumptions about the dropout process may have on model parameter estimates. The proposal is illustrated via the analysis of data from a longitudinal study on the dynamics of cognitive functioning in the elderly.

Dropout Model Evaluation in MOOCs

The field of learning analytics needs to adopt a more rigorous approach for predictive model evaluation that matches the complex practice of model-building. In this work, we present a procedure to statistically test hypotheses about model performance which goes beyond the state-of-the-practice in the community to analyze both algorithms and feature extraction methods from raw data. We apply this method to a series of algorithms and feature sets derived from a large sample of Massive Open Online Courses (MOOCs). While a complete comparison of all potential modeling approaches is beyond the scope of this paper, we show that this approach reveals a large gap in dropout prediction performance between forum-, assignment-, and clickstream-based feature extraction methods, where the latter is significantly better than the former two, which are in turn indistinguishable from one another. This work has methodological implications for evaluating predictive or AI-based models of student success, and practical implications for the design and targeting of at-risk student models and interventions.

Biased Dropout and Crossmap Dropout: Learning towards effective Dropout regularization in convolutional neural network

Training a deep neural network with a large number of parameters often leads to overfitting problem. Recently, Dropout has been introduced as a simple, yet effective regularization approach to combat overfitting in such models. Although Dropout has shown remarkable results on many deep neural network cases, its actual effect on CNN has not been thoroughly explored. Moreover, training a Dropout model will significantly increase the training time as it takes longer time to converge than a non-Dropout model with the same architecture. To deal with these issues, we address Biased Dropout and Crossmap Dropout, two novel approaches of Dropout extension based on the behavior of hidden units in CNN model. Biased Dropout divides the hidden units in a certain layer into two groups based on their magnitude and applies different Dropout rate to each group appropriately. Hidden units with higher activation value, which give more contributions to the network final performance, will be retained by a lower Dropout rate, while units with lower activation value will be exposed to a higher Dropout rate to compensate the previous part. The second approach is Crossmap Dropout, which is an extension of the regular Dropout in convolution layer. Each feature map in a convolution layer has a strong correlation between each other, particularly in every identical pixel location in each feature map. Crossmap Dropout tries to maintain this important correlation yet at the same time break the correlation between each adjacent pixel with respect to all feature maps by applying the same Dropout mask to all feature maps, so that all pixels or units in equivalent positions in each feature map will be either dropped or active during training. Our experiment with various benchmark datasets shows that our approaches provide better generalization than the regular Dropout. Moreover, our Biased Dropout takes faster time to converge during training phase, suggesting that assigning noise appropriately in hidden units can lead to an effective regularization.

An application of the theory of planned behavior to student retention

Although student integration theory, a sociologically-based model, has been the dominant explanation for student drop-out from colleges for over 40 years, it has received only mixed empirical support in residential colleges and less in non-residential colleges. Psychological theories of active choice and behavior change offer an alternative explanation for drop-out. In research at a non-residential UK university, structural equation modeling was used in two separate studies to compare a model of student dropout based on student integration theory with a psychological model based on the theory of planned behavior (TPB). In the first study (N = 633), a model including TPB variables and two key student integration theory variables (academic integration, and social integration) showed good fit to the data, Although all three TPB variables predicted intention to quit, neither of the two student integration theory variables did so. The TPB variables explained over 60% of the variance in student's intention to voluntarily withdraw from college before completing their studies, and intention to withdraw was associated with actual dropout behavior. In the second study (N = 180), using alternative measures of student integration theory factors, a model including both student integration theory and TPB variables had acceptable fit, and over 70% of the variance in intention to quit was explained. But only the TPB variables predicted intention to quit significantly. The benefits of adopting a process-based psychological explanation to student retention are discussed.

Cluster analysis for repeated data with dropout: Sensitivity analysis using a distal event

ABSTRACTDegeneration of the aortic wall becomes life-threatening when the risk of rupture increases. Cluster analysis on repeated measures of the diameter of the artery revealed two subgroups of patients included in a surveillance program. These results were obtained under the assumption of missingness at random. In this article, we study the vulnerability of the cluster analysis results – the estimated trajectories and the posterior membership probabilities – by applying different missing-data models for non-ignorable dropout, as proposed by Muthen et al. (2011) to the growth of the diameter of the artery.

Factors Affecting Adult Student Dropout Rates in the Korean Cyber-University Degree Programs

Few empirical studies of adult distance learners’ decisions to drop out of degree programs have used large enough sample sizes to generalize the findings or data sets drawn from multiple online programs that address various subjects. Accordingly, in this study, we used a large administrative data set drawn from multiple online degree programs to investigate meaningful factors (derived from a conceptual model for adult dropout) affecting adult distance learners’ decisions to drop out of online degree programs in a cyber-university. The findings indicate that adult students who have a low level of basic scholastic aptitude, the studying motive to go on to graduate school, more physical constraints, less learner-content interaction, frequent learner-instructor interaction, low level of satisfaction, and low GPA are more likely to drop out of degree programs. Surprisingly, this study found that learner-instructor interaction has a significant, but negative, effect on student persistence.

Testing a path-analytic model of adult dropout in online degree programs

Using large samples from multiple online degree programs, this study aimed to empirically identify the direct and indirect relationships between major adult dropout factors (i.e., basic scholastic aptitude, physical constraints, interaction with course content, satisfaction, and GPA) and provide educational practitioners with insights that will enable them to indirectly handle uncontrollable adult dropout factors based on the empirical evidence. To achieve these purposes, we formulated and empirically tested a hypothesized path model encompassing multiple hypotheses derived from related literature. We found that the physical constraints variable has statistically significant direct and indirect relationships through interactions with course content, satisfaction, and GPA with adult students’ dropout decisions, and the basic scholastic aptitude variable has an indirect relationship with dropout decisions through interactions with course content and GPA. This paper concludes by discussing the implications of our findings for educational practitioners in online degree programs.

Event-Based State Estimation of Hidden Markov Models Through a Gilbert–Elliott Channel

In this note, the problem of event-based state estimation for a finite-state hidden Markov model under a generic stochastic event-triggering condition and an unreliable communication channel is investigated. The effect of packet dropout is characterized with a Gilbert–Elliott process. Utilizing the change of probability measure approach, the packet dropout model and the event-triggered measurement information available to the estimator, analytical expressions for the conditional probability distributions of the states are obtained, based on which the optimal event-based state estimates can be further calculated, together with a closed-form expression of the average sensor-to-estimator communication rate. The effectiveness of the proposed results is illustrated by an application to a wireless automated machine health monitoring problem.

Dropouts and Budgets: A Test of a Dropout Reduction Model among Students in Israeli Higher Education

<p style="text-align:justify">This article deals with the problem of student dropout during the first year in a higher education institution. To date, no model on a budget has been developed and tested to prevent dropout among Engineering Students. This case study was conducted among first-year students taking evening classes in two practical engineering colleges in Israel. There are three dimensions of the dropout reduction model: social support, institutional support and personal commitment. The results of the intervention had a positive effect on all three dimensions.</p>

Abstract P198: Racial Disparities in Cardiovascular Outcomes in REGARDS Persist After Using Inverse Probability Weighting to Account for Missing Data

Introduction: When data are missing, analysts often choose to perform ‘complete case’ analysis, restricting statistical analysis to those participants with all necessary fields completed. However, this analysis is subject to selection bias if those participants excluded are somehow inherently different from those included. One approach to address the potential selection bias is inverse probability weighting, where participants with complete data are weighted to reflect the original population. We compare estimated racial disparities in hypertension and left ventricular hypertrophy using complete cases to those estimates from inverse probability weighted analysis. Methods: The REasons for Geographic and Racial Differences in Stroke (REGARDS) study enrolled 30,183 participants aged 45+ between 2003 and 2007 to study racial and geographic differences in stroke and cardiovascular health. When the second in-home visits were conducted, 18% (5542) of participants had died and 23% (7071) of participants had withdrawn. For the baseline population, the probabilities of being a complete case are estimated through logistic regression models using baseline characteristics. These predicted probabilities are inverted to create the weights used in statistical analysis, such that the complete participants are weighted to represent the enrolled population. Through logistic regression, we estimate the association between race and hypertension and left ventricular hypertrophy at the second in-home visit for complete data and compare these results to the results from inverse probability weighted analysis. All models are adjusted for sex, age and region. Results: The logistic models for dropout and death have low and moderate predictive abilities (c-statistics 0.602 and 0.811, respectively). For incident hypertension, the estimated odds ratio comparing blacks to whites differs little between the complete case (1.87 (1.66, 2.10)) and the weighted (1.83 (1.61, 2.09)) analysis. For left ventricular hypertrophy, the estimated odds ratio comparing blacks to whites changes little from the complete case analysis (1.54 (1.32, 1.79)) to the weighted analysis (1.45 (1.21, 1.74)). Discussion: Estimated racial inequalities in the odds of incident hypertension and left ventricular hypertrophy were similar in the complete case and inverse probability weighting analyses, indicating little evidence of selection bias in the estimation of racial inequalities for these outcomes.

An Imputation Model for Dropouts in Unemployment Data

Abstract Incomplete unemployment data is a fundamental problem when evaluating labour market policies in several countries. Many unemployment spells end for unknown reasons; in the Swedish Public Employment Service’s register as many as 20 percent. This leads to an ambiguity regarding destination states (employment, unemployment, retired, etc.). According to complete combined administrative data, the employment rate among dropouts was close to 50 for the years 1992 to 2006, but from 2007 the employment rate has dropped to 40 or less. This article explores an imputation approach. We investigate imputation models estimated both on survey data from 2005/2006 and on complete combined administrative data from 2005/2006 and 2011/2012. The models are evaluated in terms of their ability to make correct predictions. The models have relatively high predictive power.

Applying predictive analytics in identifying students at risk: A case study

In this paper, a case study is presented of an institutional modelling project whereby the most appropriate learning algorithm for the prediction of students dropping out before or in the second year of study was identified and deployed. This second-year dropout model was applied at programme level using pre-university information and first semester data derived from the Higher Education Data Analyzer (HEDA) management information reporting and decision support environment at the Cape Peninsula University of Technology. An open source platform, namely Konstanz Information Miner (KNIME), was used to perform the predictive modelling. The results from the model were used in HEDA automatically to recognize students with a high probability of dropping out by the second year of study. Being able to identify such students will enable universities, and in particular programme owners, to implement targeted intervention strategies to assist the students at risk and improve success rates.

Local influence diagnostics for incomplete overdispersed longitudinal counts

ABSTRACTWe develop local influence diagnostics to detect influential subjects when generalized linear mixed models are fitted to incomplete longitudinal overdispersed count data. The focus is on the influence stemming from the dropout model specification. In particular, the effect of small perturbations around an MAR specification are examined. The method is applied to data from a longitudinal clinical trial in epileptic patients. The effect on models allowing for overdispersion is contrasted with that on models that do not.

Relationships between Risk Attitude, Academic Performance, and the Likelihood of Drop-outs

Regression analysis is used to explore the relationship between students’ risk attitudes and academic performance indicators: current academic achievement and the likelihood of dropping out. Using empirical data on students of a highly selective Russian university, we reveal a considerable positive correlation between risk acceptance and the likelihood of being expelled. We believe that conventional student integration and drop-out models could also consider such individual student characteristic as risk attitude. Normally, it did not use to be regarded as a factor influencing the likelihood of student departure. Risk attitude as an individual student characteristic can be involved in the process of academic integration, affecting its progress. More risk-averse students remain underintegrated in the academic environment, which is fraught with dropping out.

Stressors and Turning Points in High School and Dropout

High school dropout is commonly seen as the result of a long-term process of failure and disengagement. As useful as it is, this view has obscured the heterogeneity of pathways leading to dropout. Research suggests, for instance, that some students leave school not as a result of protracted difficulties but in response to situations that emerge late in their schooling careers, such as health problems or severe peer victimization. Conversely, others with a history of early difficulties persevere when their circumstances improve during high school. Thus, an adequate understanding of why and when students drop out requires a consideration of both long-term vulnerabilities and proximal disruptive events and contingencies. The goal of this review is to integrate long-term and immediate determinants of dropout by proposing a stress process, life course model of dropout. This model is also helpful for understanding how the determinants of dropout vary across socioeconomic conditions and geographical and historical contexts.

EuroForMix: An open source software based on a continuous model to evaluate STR DNA profiles from a mixture of contributors with artefacts

We have released a software named EuroForMix to analyze STR DNA profiles in a user-friendly graphical user interface. The software implements a model to explain the allelic peak height on a continuous scale in order to carry out weight-of-evidence calculations for profiles which could be from a mixture of contributors. Through a properly parameterized model we are able to do inference on mixture proportions, the peak height properties, stutter proportion and degradation. In addition, EuroForMix includes models for allele drop-out, allele drop-in and sub-population structure. EuroForMix supports two inference approaches for likelihood ratio calculations. The first approach uses maximum likelihood estimation of the unknown parameters. The second approach is Bayesian based which requires prior distributions to be specified for the parameters involved. The user may specify any number of known and unknown contributors in the model, however we find that there is a practical computing time limit which restricts the model to a maximum of four unknown contributors.EuroForMix is the first freely open source, continuous model (accommodating peak height, stutter, drop-in, drop-out, population substructure and degradation), to be reported in the literature. It therefore serves an important purpose to act as an unrestricted platform to compare different solutions that are available. The implementation of the continuous model used in the software showed close to identical results to the R-package DNAmixtures, which requires a HUGIN Expert license to be used. An additional feature in EuroForMix is the ability for the user to adapt the Bayesian inference framework by incorporating their own prior information.

Bayesian informative dropout model for longitudinal binary data with random effects using conditional and joint modeling approaches.

Dropouts are common in longitudinal study. If the dropout probability depends on the missing observations at or after dropout, this type of dropout is called informative (or nonignorable) dropout (ID). Failure to accommodate such dropout mechanism into the model will bias the parameter estimates. We propose a conditional autoregressive model for longitudinal binary data with an ID model such that the probabilities of positive outcomes as well as the drop-out indicator in each occasion are logit linear in some covariates and outcomes. This model adopting a marginal model for outcomes and a conditional model for dropouts is called a selection model. To allow for the heterogeneity and clustering effects, the outcome model is extended to incorporate mixture and random effects. Lastly, the model is further extended to a novel model that models the outcome and dropout jointly such that their dependency is formulated through an odds ratio function. Parameters are estimated by a Bayesian approach implemented using the user-friendly Bayesian software WinBUGS. A methadone clinic dataset is analyzed to illustrate the proposed models. Result shows that the treatment time effect is still significant but weaker after allowing for an ID process in the data. Finally the effect of drop-out on parameter estimates is evaluated through simulation studies.

Drop-out model optimization on degraded DNA samples

Two statistical models have been developed to interpret locus drop-out resulting from degraded DNA samples. These models are based on an experimental dataset of 600 genotyping experiments. The first model presents the probability of locus drop-out against the average peak height with a lower and upper confidence interval. For a given peak height average, the probability of drop-out can be quite wide. This probability decreases rapidly when the profile quality increases. For the second model, we have fitted the probability of locus drop-out against the number of base pairs with a lower and upper confidence interval. The probability of drop-out is increasing along with the number of base pairs. Despite DNA degradation effects, the drop-out probability does not get higher than 0.5.

Student Dropout Predictive Model Using Data Mining Techniques

Data mining allows discover hidden information in large amounts of data, which is very difficult to visualize with traditional process. This topic of computer science permits manipulation and classification of huge amounts of data. C4.5 and ID3 decision tree, for example, have been proven to be efficient for specific prediction cases. This article shows the construction of a predictive model of student dropout, characterizing students at the University Simon Bolivar in order to predict the probability that a student drop out his/her an academic program, by means of two data mining techniques and comparison of results. To create the model was used WEKA that allows multiple and efficient tools for data processing