This Master’s Thesis project investigates the causes of events that has led the Danish economy into financial recessions in recent economic history, from 1983 to present day. This period contains nine different recession periods of various length and severity. The recession periods used in this investiga-tion are determined by the OECD. The information from the in-depth analysis of historical recessions will form an inspirational base for the variable selection of a logistic regression model, with the pur-pose of developing a quantitative tool that can be input in a macroeconomic probability or risk model.
Based on this objective, the study first establishes a theoretical foundation for the identification of re-cessions and factors and the implementation of the empirical analysis. Having presented the theoretical framework, a review of the literature within the fields of recessions and logistic regression models is conducted, to investigate how recessions arise and which factors that can be found to have explanatory value for the regression model.
Then the thesis presents a framework for the implementation of a logistic regression based analysis. The model algorithm is from the Statistics and Data Analysis for Financial Engineering (Ruppert et al. 2015) textbook, and it is not, for mathematically sufficient readers, a complicated model, but it is a proven model and a workhorse model when it comes to doing regression analysis with a binary factorial response variable.
The logistic regression analysis allows us to form a model from a data set of macroeconomic relevant variables for the Danish economy. These variables have been selected from the key findings in the lit-erature on preceding Danish recessions and with input from my supervisor, Karl Hamenberg, Nordea’s Chief Strategist Andreas Østerheden and Nordea’s macro specialist Jan Størup. This provides the basis for the empirical analysis, which involves testing and performance evaluation, on Danish macroeco-nomic data from June 1983 to February 2020.
The performance of the model has proven to be, from a forecasting perspective, good enough to be considered viable input in a pool of macroeconomic analyses, when trying to predict an economic downturn like a recession. The unemployment rate, the MSCI Denmark index and the Yield Curve can be used as recession indicators for Denmark. It is emphasized that it cannot stand alone but, from an econometric viewpoint, it can be an indicator of the robustness of the current market environment, and the markets ability to handle a crisis like a pandemic or a country bankruptcy.
Several aspects of the thesis will form the basis of a discussion, including causality for findings, biases and applicability. Along with the results of the empirical analysis, the discussion will lead to proposals of topics for further research.
|Educations||MSc in Business Administration and Management Science, (Graduate Programme) Final Thesis|
|Number of pages||56|