The Bayesian estimation of private investment in Finland
Abstract
This paper estimates an investment equation for private investment using Bayesian estimation techniques. In the paper we derive the optimal capital accumulation behavior in the model economy from the households’ optimization problem of utility. The equation is derived as in Smets and Wouters (2003). The model contains costly adjustment of investment and random shocks to adjustment cost function. The driving variable of investment is Tobin Q variable.
The empirical proxy for Tobin Q in this paper is the ratio of OMX Helsinki Cap Index to the price index of the physical capital. The investment series is the seasonally adjusted private investment in quarterly national accounts.
The AR(1) modelled investment shocks are found to be less persistent in Finland than in the euro area. The estimated median of persistence parameter for Finland is 0.485. Also the shocks to investment adjustment cost function are found to vary less in Finland as in the euro area. The estimated standard deviation of the shocks is 0.065. The adjustment cost parameter is roughly the same for both data sets. The results are robust to loosening the strict prior of discount factor,
beta=0.99. The paper also provides discussion about adjustment cost parameter and we investigate the behaviour of the posterior chain of B with different prior distributions for the parameter.
Tiivistelmä
Tässä pro gradussa estimoidaan yhtälö yksityisille investoinneille bayesilaisella menetelmällä. Tässä työssä optimaalinen pääoman akkumulointi mallikansantaloudessa johdetaan kotitalouksien hyödyn optimointi-ongelmasta. Investointiyhtälö johdetaan kuten Smets’n ja Wouterin (2003) artikkelissa. Malli sisältää investointien sopeutuskustannukset ja satunnaisia shokkeja sopeutuskustannus-funktioon. Investointien selittävä muuttuja on Tobin Q -muuttuja.
Empiirinen vastine teoreettiselle Tobin Q muuttujalle on OMX Helsinki Cap indexin arvo suhteutettuna fyysisen pääoman hintaindeksillä. Työssä käytetty investointisarja on kausitasoitettu yksityisten investointien sarja kansantalouden neljännestilinpidossa.
Investointishokit ovat AR(1)-prosessi. Shokit osoittautuvat vähemmän pysyviksi Suomessa kuin euroalueella. Estimoitu AR(1)-kerroin investointishokeille on 0.485. Investointishokit myös vaihtelevat vähemmän Suomessa kuin euroalueella, sillä estimoitu shokkien keskihajonta on 0.065. Investointien sopeutuskustannus on likipitäen samankokoinen Suomessa ja euroalueella. Tulokset ovat robusteja kiinnitetyn diskonttausparametrin beta=0.99 löysäämiselle antamalla betalle eri
priorijakaumia. Tässä työssä myös keskustellaan sopeutuskustannusparametrista ja tutkitaan sen posterioiriketjujen käyttäytymistä kun sille annetaan eri priorijakaumia.
...


Keywords
Metadata
Show full item recordCollections
- Pro gradu -tutkielmat [23396]
Related items
Showing items with similar title or keywords.
-
A Bayesian Reconstruction of a Historical Population in Finland, 1647–1850
Voutilainen, Miikka; Helske, Jouni; Högmander, Harri (Springer, 2020)This article provides a novel method for estimating historical population development. We review the previous literature on historical population time-series estimates and propose a general outline to address the well-known ... -
The Ghost of the Hawk : Top Predator Shaping Bird Communities in Space and Time
Burgas, Daniel; Ovaskainen, Otso; Blanchet, F. Guillaume; Byholm, Patrik (Frontiers Media SA, 2021)Despite the wide recognition that strongly interacting species can influence distributions of other species, species interactions are often disregarded when assessing or projecting biodiversity distributions. In particular, ... -
Conditional particle filters with diffuse initial distributions
Karppinen, Santeri; Vihola, Matti (Springer, 2021)Conditional particle filters (CPFs) are powerful smoothing algorithms for general nonlinear/non-Gaussian hidden Markov models. However, CPFs can be inefficient or difficult to apply with diffuse initial distributions, which ... -
A Surrogate-assisted Reference Vector Guided Evolutionary Algorithm for Computationally Expensive Many-objective Optimization
Chugh, Tinkle; Jin, Yaochu; Miettinen, Kaisa; Hakanen, Jussi; Sindhya, Karthik (Institute of Electrical and Electronics Engineers, 2018)We propose a surrogate-assisted reference vector guided evolutionary algorithm (EA) for computationally expensive optimization problems with more than three objectives. The proposed algorithm is based on a recently developed ... -
Surrogate-assisted evolutionary biobjective optimization for objectives with non-uniform latencies
Chugh, Tinkle; Allmendinger, Richard; Ojalehto, Vesa; Miettinen, Kaisa (Association for Computing Machinery (ACM), 2018)We consider multiobjective optimization problems where objective functions have different (or heterogeneous) evaluation times or latencies. This is of great relevance for (computationally) expensive multiobjective optimization ...