Vasiliki Stamouli

Mrs. Vasiliki Stamouli


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 February 2026 in Digital
Verified
Journal Article
Open access
PDF file
MARIA TSOLIAMARIA TSOLIA
MARIA TSOLIA
NZNikolaos C. Zygouris
Nikolaos C. Zygouris
SKSpyros Kamnis
Spyros Kamnis
SSStefanos K. Styliaras
Stefanos K. Styliaras
EBEleftheria Beazidou
Eleftheria Beazidou
VSVasiliki Stamouli
Vasiliki Stamouli
Early identification of reading difficulties enables timely classroom intervention; however, teachers often have limited time and restricted access to specialist assessment. This study explores a brief, teacher-friendly screening approach based on short oral reading recordings to support classroom decision-making. Oral reading samples were collected from 77 Greek primary school pupils (Grades 3–6) during a standardized reading task. Recordings were segmented into 7 s excerpts, converted into spectrogram images, and analyzed using a deep learning model to classify each excerpt as indicative of reading difficulties or not. To reflect realistic school implementation, model development followed an 80/20 participant-level split, with validation conducted on pupils not included in the training set. At the selected operating threshold, the model achieved approximately 84% overall accuracy and a balanced accuracy of 0.85. For practical applicability, a pupil-level indicator—representing the proportion of excerpts flagged as difficult—showed a strong association with expert judgments (r ≈ 0.74). These findings suggest that brief oral reading recordings can provide teachers with an interpretable screening signal to inform monitoring, prioritization, and early classroom support while underscoring the need for further validation under routine school conditions.

21 April 2026 in Education Sciences
Verified
Journal Article
Open access
PDF file
AVArgyro Velaora
Argyro Velaora
CTConstantinos Tsamadias
Constantinos Tsamadias
GSGeorge Stamoulis
George Stamoulis
Apostolos XenakisApostolos Xenakis
Apostolos Xenakis
Argyro ZisiadouArgyro Zisiadou
Argyro Zisiadou
VSVasiliki Stamouli
Vasiliki Stamouli
This study recognizes education as an investment and estimates the private rates of return to upper secondary education in Greece, overall, by type (general or vocational) and by gender. Earnings data were collected through primary research using stratified sampling from the private sector of the economy. The analysis is based on the Mincer method and is complemented by machine learning methods, including Support Vector Regression, Random Forests, and Extreme Gradient Boosting. The empirical analysis shows that investing in upper secondary education (general and vocational) is profitable. The private rates of return in upper general secondary education are higher than those in vocational education, and female graduates exhibit higher returns than male graduates. Machine learning models achieve modest improvements in predictive performance, as reflected in higher adj. R2 values and lower prediction errors. However, the estimated rates of return remain broadly consistent with those obtained from the Mincer method. This convergence suggests that the Mincer specification captures the core structural relationship between education and earnings, while machine learning models primarily enhance predictive accuracy without substantially altering the estimated economic returns. This finding highlights the robustness of the traditional econometric framework and clarifies the complementary role of machine learning techniques in empirical labor economics.

10 September 2026 in Econometrics
Verified
Journal Article
Open access
PDF file
AVArgyro Velaora
Argyro Velaora
CTConstantinos Tsamadias
Constantinos Tsamadias
GSGeorge Stamoulis
George Stamoulis
Apostolos XenakisApostolos Xenakis
Apostolos Xenakis
Argyro ZisiadouArgyro Zisiadou
Argyro Zisiadou
VSVasiliki Stamouli
Vasiliki Stamouli
Understanding earnings differences across general and vocational education is important for assessing labor-market outcomes among secondary education graduates. This study examines cross-sectional age–earnings profiles among full-time private-sector workers in Greece using survey data collected in 2020, with particular attention to differences between Gymnasium, General Lyceum (GEL), and Vocational Lyceum (EPAL) graduates. It also evaluates whether machine-learning methods provide additional predictive value beyond a conventional econometric benchmark using the same parsimonious age-related information set. Earnings are modeled using a quadratic OLS specification, Random Forest, and Gradient Boosting, with age and age squared used as predictors across all models. Predictive performance is assessed using R2, RMSE, and MAE, supplemented by repeated five-fold cross-validation and a cubic OLS robustness benchmark. The results indicate concave age–earnings profiles across educational groups, with higher earnings among upper secondary education graduates than Gymnasium graduates and higher earnings among GEL than among EPAL graduates. The predictive comparison shows that OLS remains a competitive benchmark, while machine-learning methods provide only modest and subgroup-dependent improvements. Overall, the findings show systematic cross-sectional earnings differences across educational levels and types, while the predictive advantages of machine-learning methods over the quadratic OLS benchmark remain modest.