Cour session 6
DownloadTélécharger
Actions
Vote :
ScreenshotAperçu
Informations
Catégorie :Category: nCreator TI-Nspire
Auteur Author: NSRBIKE
Type : Classeur 3.0.1
Page(s) : 1
Taille Size: 2.78 Ko KB
Mis en ligne Uploaded: 24/10/2024 - 08:16:06
Uploadeur Uploader: NSRBIKE (Profil)
Téléchargements Downloads: 0
Visibilité Visibility: Archive publique
Shortlink : http://ti-pla.net/a4272626
Type : Classeur 3.0.1
Page(s) : 1
Taille Size: 2.78 Ko KB
Mis en ligne Uploaded: 24/10/2024 - 08:16:06
Uploadeur Uploader: NSRBIKE (Profil)
Téléchargements Downloads: 0
Visibilité Visibility: Archive publique
Shortlink : http://ti-pla.net/a4272626
Description
Fichier Nspire généré sur TI-Planet.org.
Compatible OS 3.0 et ultérieurs.
<<
Here is the content from the PDF in a simplified text format for easy copying: --- ### **Time Series** --- #### **WHAT IS A TIME SERIES?** A set of evenly spaced numerical data obtained by observing the response variable at regular time periods. The period can be: - Annual or longer - Quarterly - Monthly - Daily - Milliseconds or less --- #### **TIME SERIES VS. CROSS SECTIONAL DATA** - **Time series data** is a temporal sequence of observations. It is desirable that the observation times are regular (same period). It allows tracking the time evolution of a variable of interest. - **Cross sectional data** is a collection of variables measured at the same time. There may be different measurements at different times, but no need to be regularly spaced (often the time of measurement is not even recorded). It allows observing relationships between variables of interest. Key differences: - In cross-sectional data, we typically **interpolate** (though we can also extrapolate). - In time series data, we typically **extrapolate** beyond the last data point. --- #### **PANEL DATA** - Panel data combines time series and cross-sectional data. - You have several time series in which each variable has been measured at the same periods, allowing combined analysis of the common temporal behavior. - Useful for investigating external or common factors affecting more than one variable. --- #### **TIME-SERIES COMPONENTS** Time Series data can be broken down into the following components: 1. **Trend Component** (T): Overall, persistent, long-term movement in the data (increasing or decreasing). Can be linear or non-linear. 2. **Seasonal Component** (S): Regular, periodic fluctuations, usually within a 12-month period, linked to seasonal influences. 3. **Cyclical Component** (C): Repeating swings or movements over more than one year, related to macroeconomic cycles. 4. **Irregular Component** (R): Erratic or residual fluctuations, including random or unknown factors (noise). --- #### **HOW COMPONENTS INTERACT** Components follow either an **additive** or **multiplicative** model. - **Additive model**: Components directly add to the observed variable: ( X = T + C + S + R ) - **Multiplicative model**: Components add to the growth rate of the observed variable: ( Y = T times C times S times R ) or ( Y = T times C times S + R ) (partial multiplicative) --- #### **EXAMPLE OF AN ADDITIVE MODEL** An example showing the interaction of components using an additive approach. --- #### **EXAMPLE OF A MULTIPLICATIVE MODEL** A scenario where the multiplicative model applies. --- Made with nCreator - tiplanet.org
>>
Compatible OS 3.0 et ultérieurs.
<<
Here is the content from the PDF in a simplified text format for easy copying: --- ### **Time Series** --- #### **WHAT IS A TIME SERIES?** A set of evenly spaced numerical data obtained by observing the response variable at regular time periods. The period can be: - Annual or longer - Quarterly - Monthly - Daily - Milliseconds or less --- #### **TIME SERIES VS. CROSS SECTIONAL DATA** - **Time series data** is a temporal sequence of observations. It is desirable that the observation times are regular (same period). It allows tracking the time evolution of a variable of interest. - **Cross sectional data** is a collection of variables measured at the same time. There may be different measurements at different times, but no need to be regularly spaced (often the time of measurement is not even recorded). It allows observing relationships between variables of interest. Key differences: - In cross-sectional data, we typically **interpolate** (though we can also extrapolate). - In time series data, we typically **extrapolate** beyond the last data point. --- #### **PANEL DATA** - Panel data combines time series and cross-sectional data. - You have several time series in which each variable has been measured at the same periods, allowing combined analysis of the common temporal behavior. - Useful for investigating external or common factors affecting more than one variable. --- #### **TIME-SERIES COMPONENTS** Time Series data can be broken down into the following components: 1. **Trend Component** (T): Overall, persistent, long-term movement in the data (increasing or decreasing). Can be linear or non-linear. 2. **Seasonal Component** (S): Regular, periodic fluctuations, usually within a 12-month period, linked to seasonal influences. 3. **Cyclical Component** (C): Repeating swings or movements over more than one year, related to macroeconomic cycles. 4. **Irregular Component** (R): Erratic or residual fluctuations, including random or unknown factors (noise). --- #### **HOW COMPONENTS INTERACT** Components follow either an **additive** or **multiplicative** model. - **Additive model**: Components directly add to the observed variable: ( X = T + C + S + R ) - **Multiplicative model**: Components add to the growth rate of the observed variable: ( Y = T times C times S times R ) or ( Y = T times C times S + R ) (partial multiplicative) --- #### **EXAMPLE OF AN ADDITIVE MODEL** An example showing the interaction of components using an additive approach. --- #### **EXAMPLE OF A MULTIPLICATIVE MODEL** A scenario where the multiplicative model applies. --- Made with nCreator - tiplanet.org
>>
