This study examines the economic impact of the Russia-Ukraine conflict on India from January 2021 to April 2024. Utilizing a multiple linear regression model, we evaluate how three key economic indicators—rupee value, consumer price index (CPI), and foreign exchange reserves—affect India’s trade performance. Due to its heavy reliance on imports such as fertilizers, jewelry, natural gas, diamonds, and edible oils, India has been significantly affected by global supply chain disruptions and rising costs induced by the conflict. In the most recent fiscal year, the country’s import expenditure is anticipated to surpass USD 600 billion, potentially escalating
inflation and widening the current account deficit. Ukraine’s primary trading partner in the Asia-Pacific region is India, with bilateral trade estimated at USD 2.5 billion in the financial year 2020-21, while India’s trade with Russia during the same period stood at approximately USD 8.1 billion.

KEYWORDS: Multiple regression model, Consumer price index, Current account deficit, Russia and Ukraine war.

Early retirement has many causes according to economic and sociological literature. These causes may be the preference for leisure, financial and health conditions, and social environment. In our paper, we aim to specify and estimate an econometric model to assess the early retirement decision-making process for aged workers. We specify a worker's utility function from which we derive worker's probability to retire earlier that depends on her health stock, estate value and preference for future. We also estimate an health production and an health consumption functions that are key factors in the individual's decision to retire earlier. Thus, we show that our model disentangles between three groups of workers: (i) those who are more likely to choose early retirement, (ii) those who are more likely not to choose early retirement and (iii) those who are uncertain about early retirement.We also show that our predicted early retirement probability is a good predictor of early retirement as it is causal for observed early retirement.

Keywords: Early retirement, Grossmann Model, Space-state model.
JEL Classification: C32, C51, I12, J26.

appropriate for the analysis of lifetime data. It has been shown to be superior to various competing one-parameter distributions in several studies. However, to date, no appropriate goodness-of-fit tests for the Akash distribution have been constructed. This paper employs the biased transformation methodology proposed by Raschke [17] to adapt several goodness-of-fit tests, based on the empirical distribution function, for use with the Akash distribution. We undertake a simulation experiment that demonstrates that these (modified) tests perform well in the context of the Akash distribution, in terms of both low size distortion, and desirable power against
a range of alternatives. We find that the biased transformation Anderson-Darling test dominates the other tests that are considered.

KEYWORDS: Akash distribution, goodness-of-fit testing, bias, empirical distribution function, lifetime data.

This paper examines whether state COVID-19 vaccination mandates for healthcare workers reduced broader pandemic burdens in the United States. Using a monthly state panel from 2021–2022 (42 states; 1,008 state-month observations), we study log COVID-19 cases and log hospital admissions, controlling for unemployment and mask mandates, while absorbing time-invariant state factors and common monthly shocks. Difference-in-Differences estimates in a static two-way fixed effects framework do not show a robust post-adoption decline: once state and month fixed effects are included, the mandate coefficient becomes small and statistically indistinguishable from zero. Event Study estimates similarly show no immediate break at adoption and no stable, significant post-period decline for cases, while patterns for admissions suggest that treated states were already on worsening trajectories, which is consistent with endogenous policy timing and strong outcome persistence. Hence, a Dynamic Difference Generalized Method of Moments model was employed with lagged dependent variables and internal instruments that explicitly accounts for epidemic momentum. In preferred specifications, mandates are associated with statistically significant reductions in both outcomes: for cases, ? = ?0.862 (SE = 0.255, p < 0.01), and for hospital admissions, ? = ?2.883 (SE = 1.274, p < 0.05). The results support the policy relevance of healthcare worker mandates as a tool for lowering transmission and easing hospital strain once epidemic persistence is modeled. Methodologically, the paper underscores that in wave-driven settings where policy adoption responds to worsening conditions, static two-way fixed effects models may be best interpreted as diagnostics, and credible inference may require dynamic panel approaches that explicitly address persistence and endogenous timing.

KEYWORDS: Difference-in-Differences, Event Study, Difference Generalized Method of Moments, Panel data, Public health, Epidemiology, Regulation.

In this article we consider the hypothesis test problem of the mean vector of two multivariate random variables. In the case of high-dimension and small sample size, the Hotelling’s T2 test is no longer applicable because of the singularity of the sample covariance matrix.We propose a procedure to divide the high-dimensional variables into multiple groups, and construct a grouped Hotelling test statistic which averages the T2 statistics of each group. Numerical simulations and real data analysis show the good performance of the test in identifying the difference between the two population means.

KEYWORDS: Grouped Hotelling’s T2 test, High-dimensional data, Mixed ?2 distribution, Small sample size.