• Time series analysis is a statistical method used in market research to analyze and forecast sales data. It involves studying the pattern and trend of sales data over time to make predictions about future sales.


There are various quantitative methods used in time series analysis, some of which are:

  1. Moving average: This method involves calculating the average of a fixed number of periods, such as months or quarters, and using it to forecast future sales. For example, if the average sales for the last 6 months were $50,000, then the forecast for the next 6 months could be $50,000.
  2. Exponential smoothing: This method involves weighting the most recent sales data more heavily than older data to give more importance to recent trends. For example, if the sales for the last 3 months were $30,000, $35,000, and $40,000, the forecast for the next month could be calculated using exponential smoothing with a weight of 0.3 for the most recent month: forecast = 0.3($40,000) + 0.7(average of last 2 months) = $37,000.
  3. Trend analysis: This method involves analyzing the trend in sales data over time and using it to make predictions. For example, if sales have been increasing steadily by 5% each year for the past 5 years, then the forecast for next year’s sales could be calculated by increasing this year’s sales by 5%.


  1. Time series analysis is a reliable method of sales forecasting as it is based on historical sales data.
  2. It allows businesses to identify trends and patterns in sales data that can inform decision making.
  3. It helps businesses to plan production, inventory and staffing levels in advance.
  4. It can be automated using software, which saves time and reduces the risk of human error.
  5. It can be used to forecast sales for different time periods, such as days, weeks, months, and years.
  6. It provides a quantitative basis for decision making.


  1. Time series analysis assumes that the future will follow the same pattern as the past, which may not always be accurate.
  2. It can be affected by outliers or unusual events that may not occur again in the future.
  3. Complexity: Time series analysis can be quite complex, especially for those who are not familiar with statistics and forecasting methods. It requires a high level of technical knowledge and expertise, which can be a barrier to entry for some businesses.
  4. Data quality: The accuracy of time series forecasting depends heavily on the quality of the data used. If the data is incomplete or inaccurate, the resulting forecasts may be unreliable.
  5. Lack of external factors: Time series analysis is based solely on historical data, which means that it may not take into account external factors that could influence future sales. For example, a sudden change in consumer behaviour due to a new competitor entering the market may not be reflected in the historical data.
  6. Assumption of stationarity: Time series analysis assumes that the data is stationary, meaning that the statistical properties of the data remain constant over time. However, in real-world scenarios, data is rarely stationary, which can lead to inaccurate forecasts.
  7. Limited applicability: Time series analysis is most effective when there is a clear pattern or trend in the data. In cases where sales data is highly volatile or erratic, it may not be an effective forecasting method.
  8. Over-reliance on the past: Time series analysis is based solely on past sales data, which can lead to an over-reliance on historical trends and patterns. This can result in a lack of innovation or adaptation to changing market conditions.

Business Studies

Discover more comprehensive and exam-focused ZIMSEC Advanced Level Business Studies Notes.

Get more notes