Variograms, Kriging and BLUP Flashcards

1
Q

What is the variogram

Also known as the semi-variogram of the strcture function

A

It is the gamma parameter from the definition of intrinsic stationarity

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

Given a convariance function how do you find it’s variogram

A

gamma(h) = sigma^2 - C(h)

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

When des a variogram have a covariance function

A

When the process is ergodic

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

What are 2 variograms without covariance fucntions

A

Linear + Power Law

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

What is Kriging

A

Using the variogram to interpolate between data

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

Give the 5 variations of Kriging we have seen

A
  • Simple Kriging
  • Ordinary Kriging
  • Universal Kriging
  • Block Kriging
  • Robsut Kriging
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is Simple Kriging

A

In simple kriging the mean is assumed to be constant and known

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

Ordinary Kriging

A

The mean is estimated as well as the parameters in the variogram

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

Universal Kriging

A

The mean is a function of some covariates, usually but not
exclusively, spatial co-ordinates.

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

What is the BLUP

A
  • Best - least squares
  • Linear - Linear combination of the data
  • Unbiased - Expected value = “truth”
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

How do you find BLUP

A

See Equation sheet

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

What are the Kriging Equations

A

See Equation sheet

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

What assumptions does Kriging make

A

Optimality and least squares implies normality

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

Explain in words why we need a ergodic process to get a covariance function from the variogram

A

If the process is not ergodic then the variogram might have a sill at infinity meaning the covariance function isn’t finite for lags going to infinity, hence it is not supported as we need finite variance

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

What is the process of finding a covariance function from a variogram

A
  • First find c(0) by finding gamma(infinity) = c(0)
  • Then find c(t) =c(0) - gamma(t)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly