Advantages for quantitative techniques in forecasting

Comstock/Comstock/Getty Images

Forecasting techniques fall into two categories of methods: quantitative and qualitative. Quantitative forecasting relies on data list past volumes -- purchase, sales, traffic, for example. Quantitative techniques do not rely on opinions or imagination. They are purely statistical methods for forecasting.


The main advantage of quantitative techniques is that the forecast has a solid recorded base of actual data. This lends the results a of projection authority. It is hard to dispute a forecast like “we expect to sell 400 widgets in March because we sold 400 last March.” A forecast based on opinion, such as “industry opinion indicates that we will sell 400 widgets in March” is open to dispute. Such a forecast leads the receiver of the projection to question who the experts are and what the foundation for their opinion is.


Quantitative techniques for forecasting have more to offer than just copying past data into a projection. Trend analysis provides a modifying factor to bare numbers. For example, sales of 400 widgets last March came after February sales figures of 380 and were followed by April’s figures of 420. If a steady increase, decline or cycle in numbers forms a pattern, quantitative forecast will adjust past data to fit in with the pattern. Again, data manipulation has to be backed up by evidence of actual trends in order to be credible.


Quantitative methods are usually simpler than qualitative techniques. However, this does not mean that all quantitative forecasts are based on direct application of one or two factors researched from past behaviour. Analysts construct models to perform forecasts and these models may contain many different factors that adjust historical data to produce the projection. These other factors modify the results of the bare historical data and so they are called “modifiers.”


The collection of source data is not a mandatory part of quantitative methods. The analyst undertaking the forecast may use data collected by others, possibly for different purposes. This data, however, should not reduce the authority of the forecast. Information imported into the project from other sources should come from authoritative organisations, like government, or supranational bodies, academic institutions or respected Non-Governmental Organisations. The analyst needs to guarantee that the data upon which the forecast was based is correct. If she did not oversee data collection, there is a risk the data could have been forged, or manipulated to prove someone else’s goals and so it would not be a viable base for any forecasts.


Quantitative techniques for forecasting are usually cheaper to implement than qualitative methods. This is because the main resource of the forecast is the data. Beyond the cost of data gathering, there is little extra expense involved. Qualitative methods require the use of surveys, expert opinion and alternative scenarios, which require consultants and paid advisors to compile.