Hybrid Methodology Of Panel Data Analysis Used On Borsa Istanbul Stocks

Dönmez S., Özaydın Ö.

8 th International Conference on Advances in Statistics, Gazimagusa, Kıbrıs (Kktc), 16 - 18 Mayıs 2022

  • Yayın Türü: Bildiri / Yayınlanmadı
  • Basıldığı Şehir: Gazimagusa
  • Basıldığı Ülke: Kıbrıs (Kktc)
  • Eskişehir Osmangazi Üniversitesi Adresli: Evet

Özet

We used a hybrid methodology of linear regression on panel data and panel data clustering on stocks of Borsa Istanbul. Our aim was to check the efficiency of the panel data clustering in terms of linear regression used on panel data. Providing convincing results from this study would yield the necessary groundwork to forecast the stock movements based on panel data clustering. In our understanding, the base model necessary for forecasting stock movements is the one linked to the one we provide results from. Our model we develop in this study is Platonic in the sense that it describes the general principle of the stock movements. The results we obtained from our model demonstrated the effectiveness of the methodology as it provided high predictivity of stock movements up to %94.