This article discusses the development of a linear regression model for assessing business value in the oil and gas sector of Uzbekistan. The model integrates key economic and operational variables, such as global oil and gas prices, political stability, macroeconomic indicators, sales volumes, and others, including EBITDA and debt level. The study focuses on the statistical significance of variables and their impact on market value, thus providing a basis for strategic management and planning in the industry.

Purpose: This study aims to investigate the intricate relationship between the volume of exports (Y) and freight turnover on railways (X) through a paired linear regression model. The purpose is to discern the quantitative impact of railway freight turnover on a nation's export volumes and offer insights for policymakers and stakeholders in the transportation and trade sectors. Design/Methodology/Approach: A quantitative research design is employed, utilizing historical data spanning from 2000 to 2022. The chosen methodology involves the estimation of a paired linear regression model using the method of least squares. Statistical significance is tested through the coefficient of determination, Fisher's F-test, and an examination of heteroskedasticity. Elasticity analysis, rank correlation, and graphical assessments of residuals provide a comprehensive understanding of the relationship. Findings: The research reveals a strong and statistically significant positive correlation (r = 0.92) between export volumes and railway freight turnover. The regression model, validated through multiple tests, explains 84.72% of the variability in export volumes. Economic interpretation indicates that a one-unit increase in railway freight turnover leads to a substantial average increase of 1627720.728 units in export volumes. The absence of heteroskedasticity reinforces the robustness of the model.

OLS regressions have a set of assumption in order to have its point and interval estimates to be unbiased and efficient. Data missing not at random (MNAR) can pose serious estimations issues in the linear regression. In this study we evaluate the performance of OLS confidence interval estimates with MNAR data. We also suggest bootstrapping as a remedy for such data cases and compare the traditional confidence intervals against bootstrap ones. As we need to know the true parameters, we carry out a simulations study. Research results indicate that both approaches show similar results having similar intervals size. Given that bootstrap required a lot of computations, traditional methods is still recommended to be used even in case of MNAR