# Advantages And Disadvantages Of Time Series Analysis Pdf

File Name: advantages and disadvantages of time series analysis .zip

Size: 2235Kb

Published: 27.05.2021

- The Advantages of the Time Series Method of Forecasting
- Subscribe to RSS
- Get the Latest Updates from John Galt

*Asked by Wiki User. The advantage of time series analysis is that it is a very effective method of forecasting because it makes use of the seasoned patterns.*

## The Advantages of the Time Series Method of Forecasting

The goal of this study is to show the role of time series models in predicting process and to demonstrate the suitable type of it according to the data under study. Autoregressive integrated moving averages ARIMA model is used as a common and a more applicable model.

Univariate ARIMA model is used here to forecast egg production in some layers depending on daily data from the period of May to October Depending on these measures the autoregressive integrated moving average model with ordering 2,2,1 is considered the best model for forecasting process. The model fit statistics such as RMSE The high value of R 2 0. Cite this paper: Fatma D. Fatma D. Article Outline 1. Introduction 2.

Statistical Model 3. Using the Model in Forecasting Process 4. Introduction Forecasting is a process to predict some of the future events of a specified variable. It is an outcome of analysis of past or present data. It is widely applied in many fields as it has a major role in increasing profit [1].

Forecasting techniques classified into qualitative and quantitative methods. A time series is a set of observations collected over time. It aims to determine the behavior of the series, identify the important parameters and forecast the future values of the time series. There are many classical forecasting methods such as exponential smoothing, regression and others can be used for prediction process of time series data.

These methods differ according to the data features, number of data and presence of autocorrelation [2]. There are some advantages and disadvantages of the model. The advantages of the ARIMA model were: it is a suitable and proper method particularly incase of short term time series forecasting [5]. Another advantage, it can elevate the prediction accuracy while maintaining the parameters numbers to a minimum. The major disadvantages was difficulty in application compared to other models such as exponential smoothing methods to understand [6].

The characters of ARIMA model are stationarity mean value or variance are constant over time , and the coefficients and the residuals are independent and normally distributed [7]. If the model is non-stationary, first differences of the series can be made to produce a new time series of successive differences Y t ,Y t If first differences do not achieve the stationarity, the second differences of the series are taken and log transformation of the series also can be applied.

As it is known that, the ARIMA model is consisted of p, d, q where, p is the autoregressive parameters, d is the number of differencing passes and q is the moving average parameters. There are many examples of application this model in forecasting future production for many years such as [8] who predicted Indian egg production for seven years.

Material and Methods 2. Source of Data The study was carried out using daily egg production data obtained over 6 months, from May to October. Data were obtained from a farm in Sharkia governorate. This farm contain birds of BabCock BV white egg laying chickens breed. The birds were brought as newly-hatched chicks at the beginning of the cycle December 31, till now. Firstly, birds fed on starter ration of broilers till 21 days of rearing. Then the ration and its components changed to fit egg production during the rearing period.

As these layers are highly producers, ARIMA technique is a good model in predicting the future performance of this farm. These steps are identification, estimation, diagnostic checking and forecasting. Identification step applied to achieve stationarity and to build a suitable model using autocorrelation ACFs , partial autocorrelation PACFs , and transformations differencing and logging.

Estimation or specification step estimate coefficients depending on least squares and likelihood techniques such as AIC, BIC likelihood which introduced by [9] and [10]. Diagnostics step depending on examining the parameters significance using charts, statistics, ACFs and PACFs of residuals to determine the model fitting [12].

Non-significant parameters can be removed from the model. Forecasting step can be applied in prediction process after checking the model in the previous steps. There are many accuracy measures applied after model selection helping in choosing the best model as mentioned by [13].

These measures are explained in Table 1. Table 1. Autocorrelation is a measure of the internal correlation within a time series.

It is a technique of detecting internal relationship between values in a time series. Autocorrelation measures linear relationship, in a similar way with normal correlation.

The partial autocorrelation function PACF gives the partial association of a time series with its own lagged observations, adjusting for the observations of the time series at all shorter lags. It unlikes the autocorrelation function no controlling for other lags. This function introduces an important role in analysis process.

Its role is identifying the extent of the lag in an autoregressive model. Box—Jenkins approach introduced this function to model time series data. Plotting the partial autocorrelation functions is helpful in detecting the suitable lags p in ARIMA p,d,q model. Results and Discussion 3. Figure 1 showed that the pattern of the data under study were non-stationary and in this case transformation process differencing and logging of the data is used to become stationary data as shown in Figure 2.

Figure 1. Time series plot of egg production of the farm under study Figure 2. Time series plot of egg production stationary data The values or the numbers of p and q of the model were identified depending on the autocorrelation and partial autocorrelation coefficients ACF and PACFs of various orders of Y t. Table 2. In the ACF chart, the number of lags above 0. The most fitted model was with the smallest normalized BIC value Table 3. The values of the coefficients and the standard errors of AR and MA parameters were Their t values were They were significantly differ from zero as their P values were 0.

Then, this egg production model will be as follows: 12 Where Y t is the predicted amount of egg at time t. Table 4. Higher R 2 value 0. All these measures were a good indicator of fitting of the model to the data well. Table 5. The graphs of these residuals showed no specific information of the data appeared where all the points were irregularly distributed around zero no systematic pattern indicated that the model fitted was adequate as in Figure 4.

Figure 4. This statistic with a value of Then, the null hypothesis of white noise was accepted, and this meant that the model fitted is adequate as it absorbed all information of the data. Using the Model in Forecasting Process The actual and predicted values of egg production were shown in Table 6 and Figure 5.

Forecasting process with the model 2,2,1 for forecasting i. Table 6. Actual and estimated eggs production 4. It was noticed that egg production would increase as this model give evidence about future egg production. This model give information which are important in decision making process related to the future egg production in this farm.

ARIMA model is a good model in forecasting the future performance not only for this farm but for egg producers all over the world. Box and J. Shiskin, A. Young, and J. New York: John Wiley, , p. Indust Res. All rights reserved.

Forecasts Accuracy Measuring Methods. Time series plot of egg production of the farm under study. Figure 2. Time series plot of egg production stationary data. Figure 3. Statistics for Prediction of Egg Production. Figure 5. Actual and estimated eggs production. Makridakis, S. Eccles, M.

## Subscribe to RSS

R is the most popular programming language for statistical modeling and analysis. Like other programming languages, R also has some advantages and disadvantages. It is a continuously evolving language which means that many cons will slowly fade away with future updates to R. An open-source language is a language on which we can work without any need for a license or a fee. R is an open-source language. We can contribute to the development of R by optimizing our packages, developing new ones, and resolving issues. R is a platform-independent language or cross-platform programming language which means its code can run on all operating systems.

But when done right, it can offer tremendous advantages to companies. That said, there are a few disadvantages that are worth exploring. Forecasting gets you into the habit of looking at past and real-time data to predict future demand. Even if your prediction was nowhere close to what ended up coming to pass, it gives you a starting point. Your forecasts should eventually improve.

Our website is made possible by displaying online advertisements to our visitors. Please consider supporting us by disabling your ad blocker. In data analysis , a time series is a collection of data points organized in time. According to some definitions, the data points in a time series should be equally spaced, although this is not always the case. The varying definitions for a time series can be illustrated with three examples:. Time series analysis is the process of analyzing a time series. It is chiefly concerned with identifying three different aspects of the time series, which can be used to better clean, understand, and forecast the data.

This fact sheet explains time series analysis and discusses the gives an overview of the various options, and specifically discusses the advantages the already mentioned stationarity requirements for ARIMA models, the disadvantages of.

## Get the Latest Updates from John Galt

Data are collected from a population over time to look for trends and changes. Like other ecological studies, the data are collected at a population level and can be used to generate hypotheses for further research, rather than demonstrating causality. Ecological studies are described elsewhere in these notes, but there are four principal reasons for carrying out between-group studies: 1.

The goal of this study is to show the role of time series models in predicting process and to demonstrate the suitable type of it according to the data under study. Autoregressive integrated moving averages ARIMA model is used as a common and a more applicable model. Univariate ARIMA model is used here to forecast egg production in some layers depending on daily data from the period of May to October Depending on these measures the autoregressive integrated moving average model with ordering 2,2,1 is considered the best model for forecasting process.

*Quantitative and qualitative methodologies for forecasting help managers to develop business goals and objectives. Business forecasts can be based on historical data patterns that are used to predict future market behavior.*

Хотя и ненамеренно, именно Стратмор привел Дэвида Беккера в АНБ в тот памятный день, позвонив ему по телефону. Мысли Сьюзан перенеслись в прошлое, и глаза ее непроизвольно упали на листок бумаги возле клавиатуры с напечатанным на нем шутливым стишком, полученным по факсу: МНЕ ЯВНО НЕ ХВАТАЕТ ЛОСКА, ЗАТО МОЯ ЛЮБОВЬ БЕЗ ВОСКА. Дэвид прислал его после какой-то мелкой размолвки. Несколько месяцев она добивалась, чтобы он объяснил, что это значит, но Дэвид молчал. Моя любовь без воска.

*Беккер глубоко вздохнул и перестал жаловаться на судьбу.*

2 comments

### Leave a comment

it’s easy to post a comment