Discussion of why the additive method rather than multiplicative method is used is covered in the second PowerPoint. Copy across the spreadsheet that you produced using the previous presentation. See the information sheet mentioned before for a discussion of this process. Students need to work through the process of choosing a good model before they do the forecast from it. Open the worksheet marriage from examples. The linear model is an estimation to give a model for doing the forecast.

We will do an estimate for March What are the things that could make it completely wrong? Because it is quarterly data, use an order of 4 initially. It is not required for this level. How good an estimate of the seasonal variation did you have? The linear model is an estimation to give a model for doing the forecast. This is covered in detail over the next few slides. Students can work through the processes shown in the PowerPoint on the same data in the spreadsheet.

September Created by Polly Stuart. Achievement with Merit Use time series analysis to make forecasts. The main difference is that seies seasonal pattern is compared to one not to zero as in an additive model.

Subtract out the trend to leave the estimated seasonal and irregular components. Handles lots of data and multiple calculations. Improvements Should you have used an additive or multiplicative method? Every step needs to be commented on and justified.

Analysis of Time Series – ppt download

These are in advance of the requirements of the standard. Analysis of cyclic effects is not expected. Fill in the boxes by highlighting cells on your spreadsheet. The End But see Extra for Experts!


Forecast will most likely srries based on: Then they need to justify what they have done. This could be done per quarter, but the yearly figure is possible more relevant.

The use of moving averages will give a more responsive value for the seasonal component as it will capture these changes. Students need to look at the entire series as well as this graph to make comments.

An advantage of the one step method is that 2 cells are left blank at each end. We are using the closest values as the best estimate of the missing ones. This is a poor model for forecasts as it increases so quickly.

The moving sedies is much more responsive to changes in the slope of the trend. An outlier can be defined as an element in the irregular which is 1.

Analysis of Time Series

Tables Computer Information Technology Section Some text and examples used with permission from: It also shows you how to do a forecast. Physics Graphing Using Excel. The spreadsheet and graphs produced form the previous presentation are used.

My presentations Profile Feedback Log out. Advantages of Graphing with Spreadsheet Programs Can be fast. The distortion in the trend may 90614 affect the model used for the forecast. More information about techniques used at Statistics New Zealand is tine in the information section on Schools Corner. In addition, many of the other methods of seasonal adjustment shown here are very much simplified.

The first way gives a more accurate estimate of the most recent trend. The spreadsheet Example sales. This example uses a short cut method to do both columns in one step. It is srries to transfer results into a word document to make the report more coherent. It is easier to read and to see what has been done than using the Excel spreadsheet. Then identify the values which are outliers by the definitions on the previous slide. The process is explained in detail in the next slides. To use this website, you must agree to our Privacy Policyincluding cookie policy.


You will need to open the spreadsheet: Identify and describe the seasonal pattern. This may involve relating factors such as the gradient of the trend line to the situation.

Excel will use all the decimals in its calculations so rounding error is not a problem here. So a trough is a number between zero and one and a peak between one and two.

Use the formula from your model of the trend line. Students may need to be reminded of why deflation can give more useful results in some cases. This is a preferred method to the one often used, which averages over the whole series. Rounded to 3sf why?

Use a moving average to estimate the seasonal component value.