Adaptive Elastic Net with Distance Correlation on the Grouping Effect and Robust of High Dimensional Stock Market Price

Stock market is found in many financial studies. Nonetheless, many of these literatures do not consider on the highly correlated stock market price. In particular, the studies on variable selection, grouping effects and robust dedicated to high dimension stock market price can be considered as scarce. Penalized linear regression using elastic net is one of the recognized methods to perform variable selection. However, the lack of consistency in variable selection may reduce the model performance. Hence, adaptive elastic net with distance correlation (AEDC) is proposed in this study and compared against elastic net, adaptive elastic net with elastic weight and adaptive elastic net with ridge weight. AEDC had lower mean squared error when the alpha increases from 0.05 to 0.95. Thus, the proposed method has successfully contributed to encouraging grouping effects between the highly correlated variables and also has an improved model performance in the presence of robustness.

Download Full-text

Non-transformed Principal Component Technique on Weekly Construction Stock Market Price

MATEMATIKA ◽

10.11113/matematika.v35.n2.1112 ◽

2019 ◽

Vol 35 (2) ◽

pp. 139-147

Author(s):

Yusrina Andu ◽

Muhammad Hisyam Lee ◽

Zakariya Yahya Algamal

Keyword(s):

Stock Market ◽

Mean Squared Error ◽

Market Price ◽

Principal Component ◽

Construction Sector ◽

Market Prices ◽

Component Technique ◽

Squared Error ◽

The Mean ◽

Explained Variance

The fast-growing urbanization has contributed to the construction sector becoming one of the major sectors traded in the world stock market. In general, non-stationarity is highly related to most of the stock market price pattern. Even though stationarity transformation is a common approach, yet this may prompt to originality loss of the data. Hence, the non-transformation technique using a generalized dynamic principal component (GDPC) were considered for this study. Comparison of GDPC was performed with two transformed principal component techniques. This is pertinent as to observe a larger perspective of both techniques. Thus, the latest weekly two-years observations of nine constructions stock market price from seven different countries were applied. The data was tested for stationarity before performing the analysis. As a result, the mean squared error in the non-transformed technique shows eight lowest values. Similarly, eight construction stock market prices had the highest percentage of explained variance. In conclusion, a non-transformed technique can also present a better resultoutcome without the stationarity transformation.

Download Full-text

Variable selection via the adaptive elastic net: mathematics success of the students in Singapore and Turkey

Volume 1, Issue 1 - Journal of Applied Microeconometrics ◽

10.53753/jame.1.1.04 ◽

2021 ◽

Vol 1 (1) ◽

pp. 41-55

Author(s):

Kadriye Hilal Topal

Keyword(s):

Variable Selection ◽

Communication Technologies ◽

Elastic Net ◽

Quality Of Education ◽

Information Communication Technologies ◽

Information Communication ◽

Regression Methods ◽

Adaptive Elastic Net ◽

Mathematics Success

The quality of education is crucial for its competitiveness in the developing world. International tests are organized at regular intervals to measure the quality of education and to see the place in the ranking of countries. The surveys on these examinations have provided a large number of variables that can be effective on the scores of the tests, including family, teacher, school and course equipment and information communication technologies, etc. The important question is which variables are relevant for the students' achievement in these tests. We investigated the barriers of mathematics success of Turkish students in the TIMSS exam and compared their status with Singaporean students who took part in at top of the ranking in the exam. For this, we employed the adaptive elastic net which is one of the regularized regression methods to dataset and compared their prediction accuracy according to three different alpha levels [0.1; 0.5; 0.9] to determine the model that has high variable selection ability with optimal prediction. The adaptive elastic net with the alpha level [0.9] was selected as superior to others. As the findings, a technology-oriented education system can help to success of the students in Turkey and the countries having similar experiences in international tests.

Download Full-text