lecture 8 - time series data Flashcards

1
Q

what is time series data?

A

x(t)

anything attached to a time stamp e.g. months, years, seconds

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

when studying time series data we are interested in?

A
  • any changes in a specific variable over time
  • obvious oscillations
  • obvious trends
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

data and patterns can be considered as:

A
  • random
  • clustered
  • cyclic
  • chaotic
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

what are the different components of a time series?

A
  • trend component
  • periodic component
  • random noise component
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

what is interpolation?

A

the estimation of an unknown quantity between two known quantities

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

types of interpoaltion

A
  • linear
  • nearest neighbour
  • cubic
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

steps of linear interpolation

A

1 - identify the gap
2 - subtract the difference between the values before and after the gap
3 - divide this by the number of missing values +1
4 - either add the answer to the data point (if ascending)
OR subtract (if descending)

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

what is signal processing?

A

the alteration of a time series to extract specific components to reduce noise

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

define noise

A

the amount of unexplained variation in a sample

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

reducing noise is also known as?

A

smoothing

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

methods of smoothing

A
  • moving average

- Savitzky-Golay filtering

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

root-mean-square

A

removes negatives

used to determine strength of a signal

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

define frequency

A

number of cycles or data points within a period of time (generally 1 second)

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

what is a wavelength?

A

time and distance between 2 identical points e.g. peak to peak

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

what is amplitude?

A

height of the wave (from zero)

also known as power or force

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

what is phase?

A

refers to the difference between troughs and peaks in amplitude

17
Q

what does “in phase mean”?

A

2 datasets are identical - matching peaks and troughs

18
Q

what does anti-phase mean?

A

the peak in one signal is directly above the trough in another

19
Q

Savitzky-Golay filtering is better than moving average for:

A
  • preserving the periodic component

- where there is a lot of high frequency noise on low frequency signals

20
Q

Savitzky-Golay filetring uses?

A

polynomial least squares

21
Q

what does polynomial mean?

A

equation with multiple terms

22
Q

polynomial least squares performs

A

a curved fit - not linear

23
Q

time series regression

A
y = a + bx + u
*x = the timestamp
24
Q

how do you assess normality?

A

use a Q-Q plot (Quantile-Quantile plot)

compares the quantiles of a variable against theoretical quantiles of one with a normal distribution

25
Q

what is a quantile?

A

subdivision of a dataset whereby an expected number of values would be expected

26
Q

sample autocorrelation:

A

detects oscillations
assumes that the periodic component is stable
correlates the series against itself and an identical dataset which is shifted by a range of lags

27
Q

cross-correlation determines?

A

links between offset data

28
Q

the aim is to remove the noise component to reveal?

A
  • trend component

- periodic component

29
Q

why do we smooth data?

A
  • to reduce noise
  • to find the trend component
  • to find the periodic component