Please see my homepage for further information.
Vegard Høghaug Larsen is an Associate Professor of Data Science and Economics at the BI Norwegian Business School, and a manager of the research centre Simula@BI. He holds a Master of Science in Economics from the Norwegian University of Science and Technology (NTNU), and obtained his Phd in Economics from BI Norwegian Business School in 2017.
He works in the intersection of economics and data science where he use methods from machine learning and natural language processing to answer questions related to the transmission of economic shocks, how agents form their expectations, and how we can measure unobserved concepts such as sentiment, uncertainty and climate risk.
Larsen has previously held a position as senior researcher at Norges Bank.
This paper examines how news coverage of the European Central Bank (ECB) affects consumer inflation expectations in the four largest euro area countries. Utilizing a unique dataset of multilingual European news articles, we measure the impact of ECB-related inflation news on inflation expectations. Our results indicate that German and Italian consumers are more attentive to this news, whereas in Spain and France, we observe no significant response. The research underscores the role of national media in disseminating ECB messages and the diverse reactions among consumers in different euro area countries.
Juelsrud, Ragnar Enger & Larsen, Vegard Høghaug (2023)
We investigate the impact of macro-related uncertainty on bank lending in Norway. We show that an increase in general macroeconomic uncertainty reduces bank lending. Importantly, however, we show that this effect is largely driven by monetary policy uncertainty, suggesting that uncertainty about the monetary policy stance is key for understanding why macro-related uncertainty impacts bank lending.
Ellingsen, Jon; Larsen, Vegard Høghaug & Thorsrud, Leif Anders (2022)
News media versus FRED-MD for macroeconomic forecasting
Using a unique dataset of 22.5 million news articles from the Dow Jones Newswires Archive, we perform an in depth real-time out-of-sample forecasting comparison study with one of the most widely used data sets in the newer forecasting literature, namely the FRED-MD dataset. Focusing on US GDP, consumption and investment growth, our results suggest that the news data contains information not captured by the hard economic indicators, and that the news-based data are particularly informative for forecasting consumption developments.
ter Ellen, Saskia; Larsen, Vegard Høghaug & Thorsrud, Leif Anders (2022)
We propose a simple method to quantify narratives from textual data, and identify what we label “narrative monetary policy surprises” as the difference in narrative focus in central bank communication accompanying interest rate meetings and economic media coverage prior to those meetings. Identifying narrative surprises in this way using Norwegian data provides surprise measures that are uncorrelated with conventional monetary policy surprises, and, in contrast to such surprises, have a significant effect on subsequent media coverage. In turn, narrative monetary policy surprises lead to macroeconomic responses similar to what recent monetary policy literature associates with the information component of monetary policy communication, highlighting media’s role as information intermediaries.
Larsen, Vegard Høghaug & Thorsrud, Leif Anders (2021)
We decompose the textual data in a daily Norwegian business newspaper into news topics and investigate their predictive and causal role for asset prices. Our findings suggest that news published through the mass media has significant, persistent, and potentially economically profitable predictive power for returns. Moreover, during an exogenous media strike returns for firms particularly exposed to our news measure experience a substantial fall relative to the control group. Together these findings lend support for a view where the media act as “information intermediaries” between agents and the state of the world, and disseminate fundamental information to investors.
Uncertainty is acknowledged to be a source of economic fluctuations. But, does the type of uncertainty matter for the economy’s response to an uncertainty shock? This paper offers a novel identification strategy to disentangle different types of uncertainty. It uses machine learning techniques to classify different types of news instead of specifying a set of keywords. The paper finds that, depending on its source, the effects of uncertainty on a macroeconomic variable may differ. I find that both good (expansionary effect) and bad (contractionary effect) types of uncertainty exist.
Larsen, Vegard Høghaug; Thorsrud, Leif Anders & Zhulanova, Julia (2021)
News-driven inflation expectations and information rigidities
Using a large news corpus and machine learning algorithms we investigate the role played by the media in the expectations formation process of households, and conclude that the news topics media report on are good predictors of both inflation and inflation expectations. In turn, in a noisy information model, augmented with a simple media channel, we document that the time series features of relevant topics help explain time-varying information rigidity among households. As such, we provide a novel estimate of state-dependent information rigidities and present new evidence highlighting the role of the media in understanding inflation expectations and information rigidities.
Bergholt, Drago; Larsen, Vegard Høghaug & Seneca, Martin (2019)
The recent oil price fall has created concern among policy makers regarding the consequences of terms of trade shocks for resource-rich countries. This concern is not a minor one – the world’s commodity exporters combined are responsible for 15–20% of global value added. We develop and estimate a two-country New Keynesian model in order to quantify the importance of oil price shocks for Norway – a large, prototype petroleum exporter. Domestic supply chains link mainland (non-oil) Norway to the off-shore oil industry, while fiscal authorities accumulate income in a sovereign wealth fund. Oil prices and the international business cycle are jointly determined abroad. These features allow us to disentangle the structural sources of oil price fluctuations, and how they affect mainland Norway. The estimated model provides three key results. First, oil price movements represent an important source of macroeconomic volatility in mainland Norway. Second, while no two shocks cause the same dynamics, conventional trade channels make an economically less significant difference for the transmission of global shocks to the oil exporter than to oil importers. Third, the domestic oil industry’s supply chain is an important transmission mechanism for oil price movements, while the prevailing fiscal regime provides substantial protection against external shocks.
Larsen, Vegard Høghaug & Thorsrud, Leif Anders (2019)
This article quantifies the epidemiology of media narratives relevant to business cycles in the US, Japan, and Europe (euro area). We do so by first constructing daily business cycle indexes computed on the basis of the news topics the media writes about. At a broad level, the most influential news narratives are shown to be associated with general macroeconomic developments, finance, and (geo-)politics. However, a large set of narratives contributes to our index estimates across time, especially in times of expansion. In times of trouble, narratives associated with economic fluctuations become more sparse. Likewise, we show that narratives do go viral, but mostly so when growth is low. While narratives interact in complicated ways, we document that some are clearly associated with economic fundamentals. Other narratives, on the other hand, show no such relationship, and are likely better explained by classical work capturing the market’s animal spirits.