Econometrics

Dans cet article, nous étudions la façon dont la «value-relevance» des données comptables évolue en fonction du mois au cours duquel la valeur de marché a été observée. Pour cela nous estimons un modèle de résultat résiduel à partir de deux échantillons d'entreprises côtées en Allemagne et en France. Nous identifions de fortes divergences entre les deux échantillons. En France, les données comptables sont fortement reliées à la valeur de marché lors de la publication des résultats annuels en Février ou Mars; alors qu'en Allemagne, les données comptables ont une importance tout au long de l'année fiscale. Nous nommons ces deux effets, «forecast relevance» et «coincident relevance» respectivement. Cette divergence ayant disparu dès que les IFRS ont été adoptées en France, nos résultats montrent l'importance des rapports financiers intermédiaires étendus.

This study discovered market determinants of credit default swap (CDS) spreads in the North American oil and gas industry. Due to the limited theoretical background on market sources of CDS price fluctuations, we chose to alleviate model uncertainty and possible misspecification issues using Bayesian model averaging. This robust framework allowed us to aggregate results from a vast number of linear panel models estimated over the 2017–2020 period. We identified oil price volatility, major shifts in the OPEC+ supply policy, natural gas prices and industrial metal prices as the most robust determinants of CDS spreads. We show that following the onset of the COVID-19 pandemic, oil prices ceased to be a notably important determinant of credit risk, as factors indirectly related to oil prices, such as global and sectoral uncertainty, financial conditions and the macroeconomic stance became more influential. Additionally, we show that the CDS spreads of shale companies are determined by s...

Dynamiczne modele czynnikowe (DFM) umozliwiają uzyskanie syntetycznej informacji o ksztaltowaniu sie zmienności duzego zbioru danych. Celem niniejszego opracowania jest sprawdzenie jakości krotkookresowych prognoz inflacji CPI oraz inflacji bazowej w Polsce (z wylączeniem cen energii i zywności), sporządzonych za pomocą modeli DFM. W badaniu wykorzystano 182 szeregi czasowe o czestotliwości miesiecznej, obejmujące obserwacje zmiennych makroekonomicznych od 1999 do 2009 r. Otrzymane rezultaty wskazują, ze efektywne korzystanie z duzego zbioru danych moze obnizyc bledy poza probe prognoz inflacji, szczegolnie dla dluzszych horyzontow prognozy. Podobne wyniki dla inflacji uzyskano we wcześniejszych badaniach.

Bayesian VAR (BVAR) models offer a practical solution to the parameter proliferation concerns as they allow to introduce a priori information on seasonality and persistence of inflation in a multivariate framework. We investigate alternative prior specifications in the case of time series with a clear seasonal pattern. In the empirical part we forecast the monthly headline inflation in the Polish economy over the period 2011-2014 employing two popular BVAR frameworks: a steady-state reduced-form BVAR and just-identified structural BVAR model. To evaluate the forecast performance we use the pseudo realtime vintages of timely information from consumer and financial markets. We compare different models in terms of both point and density forecasts. Using formal testing procedure for density-based scores we provide the empirical evidence of superiority of the steady-state BVAR specifications with tight seasonal priors.

In this paper, we extend comparative value relevance research by examining patterns in the value relevance of accounting numbers as a function of the month in which market values are observed. We stimate the residual income model on a sample of stock-exchange listed companies from Germany and France and find dramatically divergent patterns of fit. In France, accounting numbers have strong relevance for market valuation after publication of annual reports in February or March. In Germany, accounting numbers have stronger relevance during the fiscal year. We term the two effects forecast and coincident relevance, respectively. We argue that the divergence in patterns of fit may be a result of limited interim reporting in France before adoption of IFRS.

We analyse the short-term dynamics of Polish economy with a prominent state-dependent pricing mechanism of Dotsey, King and Wolman (1999). We compare macroeconomic evidence of price rigidity in a small-scale DSGE model with a state-dependent Phillips curve (SDPC) derived by Bakhshi, Khan and Rudolf (2007) to a benchmark model including hybrid New-Keynesian Phillips Curve (NHPC) of Gali and Gertler (1999). To analyse monetary policy transmission mechanism we estimate both models with Bayesian techniques and focus on the comparison of distribution of price vintages, a degree of price stickiness, values of parameters in Phillips curve equations, and impulse responses to macroeconomic shocks. The estimated state-dependent pricing model generates a median duration of prices about 4 quarters compared to 8 quarters in a time-dependent model. In the state-dependent pricing model it takes more time to dampen inflation dynamics after a monetary policy relative to a time-dependent counterpart....

This year the conference was held in post-industrial interiors of Hotel Focus in ód. The meeting gave the opportunity to present papers on well diversi ed topics starting from methodological aspects of nancial modelling and macroeconomic forecasting to general re ections on 30 years of nancial liberalisation. Professor W adys aw Milo acted the Chair of Programme Committee and Piotr Wdowi ski (Assoc. Professor) was the Chair of Organization Committee. The other academics from the Chair of Econometrics, University of ód , were very active in conference preparations with dr Mariusz Górajski and dr Grzegorz Szafra ski coordinating the works of Organization Committee and Programme Committee, respectively, acting as conference secretaries. The conference was held under the patronage of the two prominent Polish institutions: National Bank of Poland (Narodowy Bank Polski) and Polish Financial Supervision Authority (Komisja Nadzoru Finansowego). The organizers also acknowledge the nancial support from: ód Marshall Of ce, Faculty of Economics and Sociology at University of ód , CERFiN and Timberlake Consultants. The media partnership of this event was provided by Obserwator Finansowy (economics web portal) and TVP ód (television). Herewith we thank our sponsors and partners for ongoing support of our scienti c events. They helped us to organise the event to the goodwill of all academic society. The participants were representing ten domestic and nine foreign institutions, both of academic and nancial background. The participants came from 15 different universities and 4 institutions including three central banks (National Bank of Poland, European Central Bank, Bank of Finland) and one commercial bank. They had the opportunity to take part in one invited lecture, four invited sessions and six contributed sessions. The participants presented the following topics, which were discussed after their presentations:

We investigate commonality and heterogeneity of inflationary processes in ten Central andEastern European (CEE) countries over the period 2001–2013. The research is important forthe analysis of monetary policy as it helps understand the origin of price formation from both sectoral and country perspective. With a multi-level factor model we decompose productlevel inflation rates into the CEE region-wide, sector, country, country-sector, and idiosyncratic components. The outcomes indicate that CEE region-wide and country specific components are more persistent than sector and product-level components, which is in line with similar studies for core EU countries. Regional factors explain about 17% of variance in monthly price changes, which is more than any other factors (below 10% each). This result is at odds with the assumptions of many sectoral DSGE models and empirical evidence on the importance of sectoral price shocks in developed economies. The difference may be related to the c...