Forecasting

Excel'de Veri Analizi

Nick Edwards

Analyst at Mynd

What is forecasting?

Forecasting is the process of predicting future outcomes and trends based on historical data using statistical techniques.
- Forecasts are predictions not actual outcomes

Weather man showing the forecast

A line graph of retail sales between 2018 and 2020 with seasonal trends highlighted gray

¹ https://www.census.gov/retail/sales.html

Woman with laptop thinking

Bias is the distortion of forecasting results from of the way the analysis was set up.

Sampling bias: data is collected in a way that is not representative
Confirmation bias: only accepting results that the analyst already believes to be true
Anchoring bias: failing to adjust adequately for new data or changing trends

A distribution curve with the lower and upper bound labeled

Confidence intervals are the range within an actual outcome is likely to occur
Confidence level: the probability an actual outcome is likely to fall within the intervals

A distribution curve with 90% of the area highlighted

Confidence intervals are the range within an actual outcome is likely to occur
Confidence level: the probability an actual outcome is likely to fall within the intervals

A distribution curve with 95% of the area highlighted

Confidence intervals are the range within an actual outcome is likely to occur
Confidence level: the probability an actual outcome is likely to fall within the intervals

A graph of a moving average

Weighted moving average

The formula for a weighted moving average

Weighted moving average

The formula for a weighted moving average

Example find the weighted average

[(2 x 0.15) + (3 x 0.35) + (4 x 0.50)]/
(0.15 + 0.35 + 0.50)

3.6/1 = 3.6

Excel'de Veri Analizi