Forecasting Flashcards

1
Q

What is linear regression?

A

Determines the equation of a straight line relationship between variances. For example, total costs and units made. Or it could be time period and sales.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the limitations of linear regression analysis?

A
  • assumes a straight line relationship between the variables
  • Only measures the relationship between two variables
  • It shouldn’t be used predict beyond current quantities
  • Assumes historical behaviour continues for the foreseeable future
  • only reliable if there is a significant correlation between the data
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is time series analysis?

A

Timeseries analysis uses moving averages to create a trend line overtime. this is established from historical data that when adjusted for seasonal variations can be made to get predictions for the future

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are the four components of time series analysis?

A

The trend
This is the straight line that describes the general movement of the data

Cyclical variations
The economic cycle of boom and slumps

Seasonal variations
Irregular variation around the trend over fixed period which is usually a year

Residual variations
Irregular and random fluctuations in the data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are the limitations of time series analysis?

A
  • assumes what has happened in the past is a reliable guide for the future
  • assumes a straight line trend exists
  • Assumes that the seasonal variations are constant
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Three ways to calculate the trend

A
  • The high low method
  • Linear regression
  • Moving averages

Moving averages attempts to remove seasonal or surgical variations by a process of averaging

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

How to work out the seasonal variation in time series analysis

A

For each season, the seasonal variation is the difference between the trendline value and the actual historical value for the same period

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the additive model and the multiplicative model?

A

Additive model
Prediction = trend + seasonal variation

Multiplicative model
Prediction = trend x seasonal variation ( expressed as a percentage)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly