Institutional Repository of Vilnius University
Lietuvos nedarbo lygio bei ekonominių rodiklių analizė laike /
Abstract
dc:descriptionThis study analyzes the development of Lithuania's unemployment rate and other economic indicators from 2007–2023. The aim is to construct time series models using ARIMA and regression with ARIMA errors methods to forecast future values. Comparing the models based on the accuracy metrics MAE, RMSE and MAAPE, we find that regression with ARIMA erros method produces more accurate forecasts for indicators such as GDP per capita, household spending, capital, exports, imports and GDP expenditure method. However, the ARIMA method better predicted inflation, wages and government spending. Results for the unemployment rate vary, according to MAE and MAAPE metrics, regression with ARIMA errors performed better, while according to RMSE, ARIMA was slightly more accurate. Conducting outlier analysis with different critical values reveals the same results for all indicators.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Seiliūtė, Margarita,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD210643643&prefLang=en_US