Time Series Analysis

By Peter J. Brockwell. 2014

167 citations recorded by the source corpus.

Subfields: Finance, Management Science and Operations Research, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Finance

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Conditional Time Series Forecasting with Convolutional Neural Networks (2017, methodology): “ nancial data it is desirable that these will be both able to learn non-linear dependencies in the data as well as have a high noise resistance. Traditional autoregressive models such as VAR and ARMA [9] fail to capture non-linear patterns. Feedforward neural networks have been a popular way of lear”
Bayesian inference on structural impulse response functions (2019, methodology): “, Hamilton, 1994, Prop. 10.1). 76This idea is explored by Hansen & Sargent (1981, p. 44) and Barnichon & Matthes (2015).”
Evaluating the impact of unconventional monetary policy measures: Empirical evidence from the ECB׳s Securities Markets Programme (2016, background): “If the innovation terms in (4) and (5) are Gaussian, then model (1) - (5) is a standard linear Gaussian model in state space form, for which the log-likelihood is easily obtained by a single run of the Kalman Filter (Hamilton (1994)).”
Deep Learning for Time-Series Analysis (2017, methodology): “rning, analysis of Time-Series data have been a popular subject of interest in other elds such as Economics, Engineering and Medicine. Traditional techniques on manipulating such data can be found in [21], and the application of traditional ANN techniques on this kind of data is described in [5]. Mo”
The Three-Pass Regression Filter: A New Approach to Forecasting Using Many Predictors (2015, methodology): “The least squares prediction in the linear system of Assumption 1 is provided by the Kalman filter (Maybeck (1979)) and the system parameters are efficiently estimated by maximum likelihood (Hamilton (1994)).”
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting (2017, methodology): “VAR Vector Auto-regressive model (Hamilton, 1994).”
It Depends on Where You Search: Institutional Investor Attention and Underreaction to News (2017, background): “Each draw is based on the original parameter estimates and the parameters’ covariance matrix accounting for firm and day clustered standard errors (see Hamilton 1994, 336–7 for more detail).”