Focusing on the econometric foundations of multi-dimensional panels, this book addresses the challenges posed by high-dimensional panel data sets in the era of big data. The theoretical section synthesizes existing knowledge while introducing new research findings. The empirical part highlights significant applications, blending surveys with original results that tackle econometric problems and propose practical solutions. This comprehensive approach offers valuable insights for researchers and practitioners navigating the complexities of modern data analysis.
The collection features seven classic essays alongside a new, insightful piece that explores the history of the subject. Each essay offers a unique perspective, enriching the reader's understanding and appreciation of the topic. This compilation serves both as a tribute to foundational works and as a contemporary analysis, making it a valuable resource for enthusiasts and scholars alike.
In the last decade, there has been a growing interest in time series analysis, particularly through non-parametric methods like spectral and cross-spectral analysis, which uncover patterns within individual time series and relationships between different series. The Box-Jenkins procedures for parametric estimation of autoregressive-moving average models have become standard tools in computer centers. This resurgence in time series analysis has led to numerous empirical studies focusing on optimal seasonal adjustments and the behavior of prices, production, and employment. More recently, Box-Jenkins methods have been essential in testing market efficiency, evaluating monetary and fiscal policies, and examining the impact of various assumptions on expectation formation. This volume includes a series of lectures on time series analysis presented during the winter semester of 1978/79 at the faculty of economics and statistics. It opens with M. Nerlove's introduction to unobserved components, followed by theoretical results illustrated with examples from the prices of steers, heifers, cows, milk, cattle, hog slaughter, industrial production, and male unemployment. Additionally, S. Heiler's study explores a mixed model that combines linear regression with a regular residual process for predicting economic outcomes when supplementary information is available.
