Budgeting: Preparing forecasts Flashcards
When working out the total variable cost per unit between 2 departments over 2 activity levels, what do you do?
Look for entirely variable costs (stay the same)
Look for semi-variable costs (changing with activity level)
Look for entirely fixed costs.
What is a forecast ?
A forecast is an attempt to predict what will happen.
What is the reason for seasonally adjusting the data in a time series ?
To find the Trend.
If forecasts obtained from a multiplicative time series analysis are to be reliable, it is necessary that …
There must be no unforeseen events.
The pattern of seasonal variation must continue as it has in the past.
What is the advantage of Linear regression ?
All data points are taken into account when calculating a and b.
What are the disadvantages to Linear regression ?
Assumes historical behavior of data continues into future.
Predictions only reliable if there is significant correlation between data.
If two variables are highly correlated, what can be said about the Correlation coefficient (r) and the Coefficient of determination (r^2) ?
If r = 0.98, then r^2 = 0.96,
this implies: 96% of variation in dependent variable (y) can be explained by variations in independent variable (x).
What is a confounding variable ?
Correlation between two variables does not mean that a change in one causes a change in the other, there could be a third additional variable (Confounding).
If a data set is small, is correlation occurring by chance more likely than if the data set is large ?
Yes.
If there is causal relationship, does this automatically mean Correlation ?
Yes.
Why is correlation and causation not the same thing ?
Just because X and Y are correlated does not mean that X causes the change in Y, vice versa!
Sales volume (Y) is described by
Y = 560 + 9X, where X is the number of months.
Seasonal variation for April is 104% of the trend.
What are the forecast sales for April X2 ?
Jan X1 - Apr X2 = 16 months
Trend = Y = 704
Forecast sales = T x SV = 704 x 104%
What three ways are there to calculate The Trend ?
HL method.
Linear Regression.
Moving Averages.
What is the purpose of using moving averages ?
Used to smooth out the variations in a time series to identify a trend.
What are the limitations (assumptions) of a Time-series analysis ?
The past is a reliable guide to the future.
A straight-line trend exists.
SV are constant.
