Time Series Flashcards

1
Q

What is a time series?

A

A set of data that is collected at regular intervals of time

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

What is time series data used for?

A

Understanding cause and effect AND Making decisions about the future

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

In a time series what is a trend?

A

The general direction (increasing or decreasing) in which the series is running over a long period

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

In a time series what is seasonality?

A

A relatively short term repetitive pattern of fluctuations from the trend

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

In a time series what are cyclical changes?

A

Patterns of highs and lows in the data over time periods, usually of more than a year

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

In a time series, what is residual variation?

A

Random, irregular or unexpected fluctuations

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

Why do statisticians aim to smooth out the variations?

A

So that the underlying trend becomes more visible

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

How can you smooth out variations?

A

Moving averages - replaces each observation with an average based on nearby observations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What does r mean in a time series?

A

Point moving average

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is the moving average of the order of r?

A

The mean of every set of r consecutive values in a time series

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What do we do with every moving average?

A

Match it to a date on the original time series

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What do we do with the moving average when it is an odd number?

A

Use the same time point of the middle observation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What do we do with the moving average when it is an even number?

A

1) calculate the moving average 2) take the average of each adjacent pair of moving averages and then match it against the ‘third’ data point and so on

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

When the time series does not have any seasonality, what order should you use?

A

You should use moving averages of fairly low order

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

When the time series is seasonal, what order should you use?

A

Select a moving average of order equal to the period - which is the number of time points in its cycle of repetition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How can you determine forecasting error?

A

Compare forecast values with actual values

17
Q

What is mean absolute deviation (MAD)?

A

The mean of the absolute values of the differences

18
Q

What is the mean absolute deviation formula?

A

xi = actual value

Fi = forecast value

19
Q

What do smaller values of the mean absolute deviation indicate?

A

A better model resulting in a more accurate forecast