ECON F342 AE Time Series 2017

# ECON F342 AE Time Series 2017 - ECON F342 APPLIED...

This preview shows pages 1–13. Sign up to view the full content.

BITS Pilani Pilani Campus ECON F342 APPLIED ECONOMETRICS

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
BITS Pilani Pilani Campus Lecture 2
Time Series Models BASICS Ch.10 of Text Book NVM 3

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Introduction Time series data can be defined as a sequence of observations of some variable at regular time intervals. The intervals can correspond to both: A calendar time: Yearly, quarterly, monthly etc… Or an irregular economic process: such as stock market trading days in a year The observations are indexed with time i.e. dated, and their natural ordering should be respected. The time indexing emphasizes the first important difference between time series data and cross-sectional data. 4
Introduction The second main difference between time series data and cross- sectional data relates to how we should think about sampling. With cross sectional data we can typically assume that a sample is randomly drawn from the appropriate population. In time series, the observations we have are considered as the realization of a given process: We can only see one realization i.e. Reality. It already happened in the past and we can’t change it. If some economic conditions were different in the past, we would have observed a different realization. So all the other potential realizations that did not happen can be considered as the population! 5

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
6 Time Series vs. Cross Sectional Time series data has a temporal ordering, unlike cross-section data Will need to alter some of our assumptions to take into account that we no longer have a random sample of individuals Instead, we have one realization of a stochastic (i.e. random) process