Header Ads Widget

Auto Regressive Models

auto-regressive-models


Auto regressive models,

it remarkably flexible at handling a wide range of different time series patterns.


1 – Time series and forecasting. 

2 – What is auto regression.

3 – What is stationarity.

4 – Types of autoregressive models.

5 – How to pick the autoregressive model and

6 – Use cases of Ar

 

1 – Time Series And Forecasting.

 

In mathematics a time series is a sequence taken at a successively equally spaced points in time,

 

therefore it's a sequence of separate time data.

 

The time can be of any order such as in terms of years months hours or minutes,

 

for example analyzing profits in a company over many years would be an example of time series or,

 

checking the weather at different time stamps can also be a time series.

 

however checking the temperature over different matrix such as city or latitude will not be an example of time series.

 

so using suitable time series forecasts can be made

 

Soothsaying is a fashion that uses literal data as inputs to make informed estimates,  


that are prophetic in determining the direction of unborn trends.


There are various notations used in time series data.

 

The alphabet t taking numeric values such as 1 2 3 etc is the index denoting the particular time period.

 

y t would be the series of n values corresponding to each time index d.

 

The greek alphabet phi denotes the coefficient for each value of y t.

 

c is a constant term denoting the bias of the model,

 

and eta denotes the error in forecast in time t given the actual value y t minus the forecasted value f d.

 

2 – What is Auto Regression.

 

The term auto regression is composed of two terms auto and regression.

 

The term regression refers to the prediction of some numeric value this value can be of any scale and still be regressive.

 

And auto here means self that is prediction of numeric value based on its own previous cells.

 

No other factors are taken into consideration,

 

except for its own historical data consider this example,

 

here the price of an object is determined based on the date.

 

The predictions are only based on its own older values,

 

thus we can say that auto regression is a time series model that uses observations from previous time steps as inputs to predict the same characteristics at the next time step.

 

To calculate the value at time step t for value y the regression equation looks like this,

 

where y d is the value at time t,

 

c is the constant,

 

phi is the coefficient to each of the previous time stem values and,

 

eta is the error term of the equation.

 

A constraint to using autoregression is that the time series data needs to be stationary.

 

3 – What is Stationarity.

 

Time series data is said to be stationary, if the statistical properties do not change over time,

 

it is supposed to show an inclining or declining overall trend,

 

so the mean and variance should remain constant over different slices in the data,

 

also a time series with seasonal patterns with no clear trend is not stationary.

 

For example this data depicts incline in some months and decline in some others forming a seasonal pattern, hence it is not stationary.

 

however this data is showing a clear inclining trend.

 

so it is an example of stationary data so guys when we know that the data is stationary.

 

we can proceed with auto regression.

 

4 – Types of Autoregressive Models.

 

The types of autoregressive models i mean the number of previous values to take into account.

 

let's see in this example we have data till 2020 for profit and,

 

we want to find the profit for the coming year that is 2021.

 

the type of ar model will determine which of the date from the previous years we will take into consideration.

 

Ar1 will only take one previous year's data point into consideration.

 

The equation shows that to determine yt we are only taking the value of y of t minus 1 along with its coefficient phi constant c and error term eta,

 

similarly ar2 takes both the data of t minus 1 and t minus 2 to predict y t,

 

note that in the equation there's always one constant and one error term,

 

but the number of coefficients of older values depends on the type of autoregressive model we take.

 

the number of previous values is not limited to one or two,

 

it can be any p values taken into consideration.

 

accordingly the equation will contain p coefficients 2.

 

 

5 – How To Pick The Autoregressive Model

 

Let's find out how to pick the number of lag values to consider

 

You might think that it's obvious toconsider all the previous data points to build a model.

 

however the rule of auto regression is to make the simplest model with least number of parameters,

 

to determine which lag values to take we can consider something known as a pacf plot.

 

pacf stands for partial autocorrelation function,

 

as explanatory with the name it determines the partial correlation between a given point and its lag or previous value,

 

we can only take into account those parameters for which the lag is higher than the threshold value,

 

consider this plot the data points corresponding to each year looks like this,

 

we have profit for each year from this data we need to make a derived chart where we will take the difference in profit between that year and two years before.

 

so lag will be equal to 2 and we will find the value of y of t minus y of t minus 2.

 

thus lag of 2020 will be profit of 2020 which is 82 minus profit of 2018 which is 93 that is equal to minus 11.

 

lag of 2018 will be profit in 2018 minus profit in 2016 which is 93 minus 94 equals minus 1 and so on.

 

for this data we make a pacf plot taking threshold as magnitude of 10.

 

From this plot we see that the profit lag for the years 2014 and 2018 is below the magnitude of 10.

 

thus we will only take the points of yt with t equals 2012 2016 and 2020.

 

The equation for this function will be the forecasted value for 2021 equals constant c plus phi into y of 2012 plus phi into y of 2016 plus phi into y of 2020 plus the error term eta.

 

this is the simplest equation of auto regression to forecast the time series taking only the significant lags.

 

 

6 – Use cases of Ar

  

The model of auto regression is based on auto correlation,

 

thus auto regression can help us find if there is a lack of randomness in the data.

 

Secondly as we have seen the primary use case of autoregression is to predict future changes using time series indexing.

 

aAuto regression is also commonly used to analyze markets such as stock market.

 

it can also forecast any kind of recurring or seasonal pattern in the data.

Post a Comment

0 Comments