Quantitative Methods Test 3
Past Values
A forecast is based *solely* on ___ ___ of a variable
Least Squares
If a time series exhibits a linear trend, the method of ___ ___ may be used to determine a trend line for future forecasts
Larger
If more observations are relevant, than larger or smaller? values of K are better in moving averages
Smaller
If the time series contains substantial random variability, is a smaller or larger value of *a* preferred in exponential smoothing?
Time Period Actual Observed Value
In linear trend projection, what is the independent variable? dependent variable?
Short
MA/WMA/Exp. Smooth. methods are most appropriate for ___ range forecasts
Underestimated Overestimated
Positive forecast error indicates forecasting method Under/Over? estimated actual value and Negative forecast error indicates forecasting method Under/Over? estimated actual value (choose correct answer for both)
Moving
Term ___ used because newly available observations replaces oldest observation
Seasonal
This pattern exists when there is repeating highs/lows over successive periods of time *within a year*
Smoothing Methods
The ma/wma/exp. smooth. are called ___ ___ because they smooth random fluctuates in time series
Horizontal
This pattern exists when data fluctuates around a constant mean
Trend and Seasonal Pattern
This is a combination of long term upward/downward movement and repeating highs/lows during said term
Exponential Smoothing
This is a weighted average of all observations in a time series
Time Series Analysis
This is discovering a pattern in historical data to extrapolate the pattern into the future
Time Series
This is plotting historical data over time with measurements taken at regular intervals
Cyclical
This is when the time series plot shows alternating sequence of points below and above trend line lasting *more than one year*. Generally due to multiyear business cycles. Extremely difficult to forecast
Trend
This pattern exists with gradual shifts to relatively high/low values over a long period of time. Can be *linear* or *nonlinear*. Result of long-term factors such as population, technology, etc...
Moving Average Weighted Moving Average Exponential Smoothing
What are the 3 forecast methods for time series with horizontal patterns
Horizontal Trend Seasonal Trend & Seasonal Cyclical
What are the five most common time series patterns?
Mean Error Mean Absolute Error (MAE) Mean Square Error (MSE) Mean Absolute Percentage Error (MAPE)
What are the four measures of forecast accuracy?
Info Is available Info is quantifiable Reasonable to assume pattern will continue
What are the three conditions necessary to using quantitative forecasting methods?
Forecast Error
What is the key concept of measuring forecast accuracy?
Mean Absolute Error
Which measure of forecast accuracy is the average of absolute values of errors?
Mean Error
Which measure of forecast accuracy is the average of errors?
Mean Square Error
Which measure of forecast accuracy is the average of forecast errors squared?
Mean Absolute Percentage Error
Which measure of forecast accuracy is the error divided by actual value?