Machine learning predicts upper secondary education dropout as early as the end of primary school.

Education plays a pivotal role in alleviating poverty, driving economic growth, and empowering individuals, thereby significantly influencing societal and personal development. However, the persistent issue of school dropout poses a significant challenge, with its effects extending beyond the individual. While previous research has employed machine learning for dropout classification, these studies often suffer from a short-term focus, relying on data collected only a few years into the study period. This study expanded the modeling horizon by utilizing a 13-year longitudinal dataset, encompassing data from kindergarten to Grade 9. Our methodology incorporated a comprehensive range of parameters, including students' academic and cognitive skills, motivation, behavior, well-being, and officially recorded dropout data. The machine learning models developed in this study demonstrated notable classification ability, achieving a mean area under the curve (AUC) of 0.61 with data up to Grade 6 and an improved AUC of 0.65 with data up to Grade 9. Further data collection and independent correlational and causal analyses are crucial. In future iterations, such models may have the potential to proactively support educators' processes and existing protocols for identifying at-risk students, thereby potentially aiding in the reinvention of student retention and success strategies and ultimately contributing to improved educational outcomes.

Developmental profiles of arithmetic fluency skills from grades 1 to 9 and their early identification.

The aim of the present study was to examine the kinds of developmental profiles of arithmetic fluency skills that can be identified across Grades 1-9 (ages 7-16) in a large Finnish sample (n = 2,518). The study also examined whether membership in the developmental profiles could be predicted using a comprehensive set of kindergarten-age factors, including information on cognitive skills; motivational, parental, and home environment factors; and gender. Four profiles of arithmetic fluency skills development were identified using a factor mixture model: persistent arithmetic difficulties (12.23%), precocious onset (50.24%), delayed onset (36.96%), and precocious onset with a Grade 7 drop (.06%). The Cholesky models predicting membership in the three largest profiles suggested that overall, the strongest kindergarten-age predictors were cognitive skills (especially counting, number concepts, spatial relations, rapid automatized naming [RAN], phonological awareness, and letter knowledge), but motivational, parental, and home environment factors were also significant. Membership in the profile with precocious onset was predicted by most of the kindergarten-age measures, suggesting that the strengths in early skills, as well as motivational, parental, and home environment factors, are reflected in the advanced start in arithmetic development at school. The profiles with delayed onset and persistent difficulties were similar in most kindergarten-age measures but differed in task avoidance and four cognitive skills (letter knowledge, counting, number concepts, and RAN), suggesting that these factors predict differential development over the longer term. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Developmental profiles of reading fluency and reading comprehension from grades 1 to 9 and their early identification.

This study examined developmental profiles of reading fluency and reading comprehension in Grades 1 to 9 (ages 7 to 15) in a large Finnish sample (N = 2,518). In addition, early predictors of the profiles were analyzed with respect to kindergarten cognitive skills (phonological awareness, letter knowledge, rapid automized naming [RAN], number counting, word reading, vocabulary, and listening comprehension), parental factors (level of education, reading difficulties), and gender. Four different profiles of reading fluency and reading comprehension development were identified using latent profile analysis. These comprised one profile with persistent reading difficulties across the grades, one with early poor reading skills but with a resolving tendency, one with average reading skills, and one with good readers who started with very high reading fluency but scored average over time. Of the kindergarten measures, parental reading difficulties, being male, low paternal level of education, slow RAN, difficulty in reading easy words, and low scores in phonological skills, letter knowledge, number counting, and vocabulary predicted reading difficulties. The children belonging to the profile with the resolving tendency showed an increased rate of family risk and multiple cognitive deficits but managed to resolve their reading difficulties. Being female, and good number counting and vocabulary skills predicted a tendency to resolve early reading difficulties. The results confirm the previous findings on the early predictors of reading difficulties and add to the literature by identifying skills that predict resolving patterns. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Longitudinal Effects of the Home Learning Environment and Parental Difficulties on Reading and Math Development Across Grades 1-9.

This study focuses on parental reading and mathematical difficulties, the home literacy environment, and the home numeracy environment as well as their predictive role in Finnish children's reading and mathematical development through Grades 1-9. We examined if parental reading and mathematical difficulties directly predict children's academic performance and/or if they are mediated by the home learning environment. Mothers (n = 1590) and fathers (n = 1507) reported on their reading and mathematical difficulties as well as on the home environment (shared reading, teaching literacy, and numeracy) when their children were in kindergarten. Tests for reading fluency, reading comprehension, and arithmetic fluency were administered to children in Grades 1, 2, 3, 4, 7, and 9. Parental reading difficulties predicted children's reading fluency, whereas parental mathematical difficulties predicted their reading comprehension and arithmetic fluency. Familial risk was associated with neither formal nor informal home environment factors, whereas maternal education had a significant relationship with both, with higher levels of education among mothers predicting less time spent on teaching activities and more time spent on shared reading. In addition, shared reading was significantly associated with the development of reading comprehension up to Grades 3 and 4, whereas other components of the home learning environment were not associated with any assessed skills. Our study highlights that taken together, familial risk, parental education, and the home learning environment form a complex pattern of associations with children's mathematical and reading skills.

Longitudinal Stability of Reading Difficulties: Examining the Effects of Measurement Error, Cut-Offs, and Buffer Zones in Identification.

This study examined the stability of reading difficulties (RD) from grades 2 to 6 and focused on the effects of measurement error and cut-off selection in the identification of RD and its stability with the use of simulations. It addressed methodological limitations of prior studies by (a) applying a model-based simulation analysis to examine the effects of measurement error and cut-offs in the identification of RD, (b) analyzing a non-English and larger sample, and (c) examining RD in both reading fluency and reading comprehension. Reading fluency and reading comprehension of 1,432 Finnish-speaking children were assessed in grades 2 and 6. In addition to the use of single cut-off points on observed data, we used a simulation approach based on an estimated structural equation model (SEM) in order to examine the effect of measurement error on RD identification stability. We also examined the effect of single cut-offs by using a simulation-based buffer zone. Our results showed that measurement error affects the identification of RD over time. The use of a simulation-based buffer zone could control both the effects of measurement error and the arbitrariness of single cut-offs and lead to more accurate classification into RD groups, especially for those with scores close to the cut-offs. However, even after controlling for measurement error and using buffer zones, RD was not stable over time for all children, but both resolving and late-emerging groups existed. The findings suggest that reading development needs to be followed closely beyond the early grades and that reading instruction should be planned according to individual needs at specific time points. There is a clear need for further consideration of the mechanisms underlying the stability and instability of RD.

Reading outcomes of children with delayed early vocabulary: A follow-up from age 2-16.

BACKGROUND: Delays in expressive vocabulary have been associated with lower outcomes in reading. AIM: The aim is to conduct a long-term follow-up study to investigate if early expressive vocabulary delay (late talking) predicts reading development in participants age 16 and under. We examine further if the prediction is different in the presence of family risk for dyslexia (FR) and early receptive vocabulary delay. METHODS: Expressive and receptive vocabulary skills were assessed at the age of 2-2.5 years, and reading skills in Grades 2, 3, 8 and 9 (age 8-16). The longitudinal sample consisted of 200 Finnish-speaking children, of which 108 had FR for dyslexia and 92 came from families without reading difficulties. We compared the reading development of five subgroups: 1) FR and no vocabulary delay; 2) FR and late talkers, 3) FR, late talkers and co-existing receptive vocabulary delay; 4) no FR and late talkers; and 5) no FR and no vocabulary delay. RESULTS: The group with FR and expressive and receptive vocabulary delay had difficulties in reading comprehension, but not in reading fluency. The late talkers without receptive vocabulary difficulties tended to become typical readers. CONCLUSIONS AND IMPLICATIONS: Delays in early vocabulary can lead to a reading comprehension deficit, with the specification that expressive vocabulary deficit alone can alleviate in time, whereas the combined deficit is a stronger risk marker.