The Time Series as the Sequences of Data Points Research - 3300 Words

The Time Series as the Sequences of Data Points Research (Other (Not Listed) Sample) Content: Name of the student;Institutional affiliation;Time SeriesTime series is the sequence of data points typically measured at successive intervals. These data points have the same space between one point to another. This data is collected over a given period, and the data always correlate with each other. This data always is always collected to given time; there should be the close relationship between the data collected and time hence the name time series. Some of the examples of this time series include; tides and sunspots. Time series forecasting this involves using the data collected through analyzing the data through the use of models. Time series data can be used statistically to plot a graph, i.e., line graph which can be used to predict future events. Time series is usually very important and in each and every organization. Some of the importance of time series include; helpful in forecasting, evaluating the achievements, comparison, etc. (Montgomery, Jennings, Kulahci,2011)Studying behavior- time series help in analyzing the behavior of the organization through data collected at a given data points, for example, analyzing at what point in time is the organization performing well regarding profit making and when it is making losses. Hence, this has enabled me understand my organization well and be in the position to overcome challenges during the depression or when an organization is not doing well.Helps in forecasting- the best competition tool of organizations at this era is that they should be in position utilize is the ability to forecast or predict the future. The success of each and every organization is the ability to plan its future well. For example, a firm should be in the position to know when the demand is high and when demand is low. When demand is high, then an organization can arrange for more supplies and when demand is low then it can reduce its supply. This has been the best tool that has helped my organization to avoid over/undersupply at any given time.Evaluating achievements- time series analysis has helped me as a manager in my organization in understanding whether it is performing well or not. Through drawing a line graph of time series on performance, which can shows an upward trend when an organization is performing well and downward trend when it is performing poorly. This can help the organization make corrections or put in place better policies which will promote the performance of the organization in future.Helps in comparison- time series help in comparing two business or the branches of the firm. As a manager time series has enabled me in analyzing my branches by comparing them. This enables I to know which firm is performing well and which one is not performing well and I can be in the position to provide rewards to those firms doing well and those not performing well I can provide the necessary remedies.In conclusion, time series analysis is very important because to each and every o rganization to succeed then it has to understand itself regarding performance, achievements, behaviorally, etc.Each and every organization should ensure use of this method when necessary of forecasting if it is to succeed. A successful business is the one which is in the position to forecast its prospects. In this case, it will be in a position to evade any possible loss that might occur. Time series is done by ensuring that proper planning and putting in place better policies ( Box, Jenkins, Reinsel, Ljung,2016).Forecasting using time seriesDuring forecasting, time series data is usually very important. Many organizations rely on data produced by accountants to forecast prospects of the firm. Company treasures this policy of forecasting since they can be in the position to remedy any future action that can be detrimental to company operations. In this way time series data is very important in forecasting of something that keeps on changing over the long period for example prices of stock, sales figures, and profit. Always, anything that is observed from time to time sequentially is called time series. (Dannecker, 2015)The major aim of forecasting time series data is to be able to determine and get a clue or understanding on how and for how long the observation will continue to future. There are different methods of calculating time series; they include; moving averages, the least square regression method, freehand method, semi-average method and also smoothing method.Moving averages involve calculating the quarter averages to calculate the seasonal components which will, in turn, be used to calculate the deseasonalized components, which will be used to will in turn used to forecast the prospects of the business. Moving averages smooth the data by averaging the consecutive observations in time series. This method can be used when the data you are calculating do not have trend components.When calculating or predicting the future with regression, the data of t ime series is very important in this situation. One of the assumptions underlying these estimation method tests the errors that are found are not correlating with each other. This method is considered to be the best. It always uses of regression formulae in predicting the future.The freehand method involves use of a just graph to predict the future happenings one draws the graph which in the long run he or she can be extrapolated to show the levels or quantity of something in future. This is the easy method and can be used by those who do not understand time series deeply since it does not involve a lot of calculations.Forecasting using calculation and graphical method.The major use of time series is to forecast in a firm, for example, forecasting the total quantity demand or some sales a firm can make in near future. The value of a variable for example sales always change over a given period and this change can either be an upward or downward trend. These general changes of this va riable for example sale, demand or profitability over a given period is called the trend. There are many techniques used in calculating time series in statistics; these methods include; moving average, smoothing, freehand method and least square regression method. The most common method used in time series additive components.Example; when data below is provided by the sales of coca cola company during thirteen months which are grouped three months in each quarter Using calculation to forecastDate Quantity sold (à ¢Ã¢â€š ¬Ã‹Å"000) Jan-mar 1996 239 Apr-June 201 Jul-sep 182 Oct-Dec 297 Jan- march 1997 324 Apr- june 278 July-sep 257 Oct-dec 384 Jan-mar 1998 401 Apr-june 360 Jul-sep 335 Oct-Dec 462 Jan-mar 1999 481 Data above can be analyzed and used to forecast future sales the organization and hence make decisions on the operations and policies to be put in place by the firm with the aim of improving sales.Use of graph in forecasting; we can draw the curve of period against the quant ity to help us in forecasting on future sales.Center moving averages values are calculated but the seasonal components are ratio derived from A/T=S The calculation of this seasonal components are as shown in table below. The seasonal components ratios can be calculated from quarterly estimated.lefttopThis graph suggests that there might be increase in sales in future because there is upward trend of the general sales of the companyà ¢Ã¢â€š ¬s sale in the months provided. Though there might be some fluctuations in the trend the general trend is viewed to be upward. Hence, an organization can forecast that there is possibility that in future the firm will be experiencing more sales that current conditions. This will bring the organization to attention that it has to prepare itself by increasing its production to meet the future demand and by so doing the firm evades the problem of inability to meet the market demand of the product.Using calculation to forecastThe most common method o f calculating time series is moving averages method. in this method, additive model is used where by variation of a given data over a given period of time is derived, calculated and described by summing up the relevant components of data collected for the purposes of forecasting. In calculating time series the following procedure is used; * finding out seasonal components * perform deseasonalisation of the components then calculate the trend * subtract the trend values from deseasonalised values * calculate the mean average deviation and mean standard errorFrom the example above we can use it to forecast on future sales of the organization has follows;Date Quarter no Quantity sold centre 4 point moving average Centre 4 point moving average Seasonal components Jan-mar 1996 1 239 Apr-june 2 201 229.75 July-sep 3 182 240.375 0.7572 251 Oct-Dec 4 297 260.625 1.1396 270.25 Jan-mar 1997 5 324 279.625 1.1587 289 Apr-June 6 278 299.50 0.9282 310 July-sep 7 257 320 0.8031 330 Oct-Dec 8 384 340.25 1.1286 350.5 Jan-Mar 1998 9 401 ...