9
votes
Estimating probability of attack in Ukraine, given count data
This is not an answer, but rather a side comment:
Keep in mind that the new attacks are not independent of the previous ones. Historical data is not necessarily relevant for the future. It is probably ...
- 141k
9
votes
Data partitioning for spatial data
After watching the video, I have become more confident that this
application is more like "data reproduction", where a random
partitioning is OK, rather than "data prediction".
To me, you justify ...
- 511
9
votes
Data partitioning for spatial data
Nice question, and I fully agree with Roozbeh.
Spatial cross validation is relevant when you have spatial autocorrelation in your training data that usually occur when your data are clustered in ...
- 91
8
votes
Data partitioning for spatial data
Very interesting question! The importance of spatial/block cross-validation comes to play when you think your performance might be affected by spatial autocorrelation. This totally depends on the ...
7
votes
Estimating probability of attack in Ukraine, given count data
Does anyone know what kind of model I would use for something like this?
...
I was just wondering if anyone know some common approaches.
Two approaches you may want to look into:
"Self exciting ...
- 2,270
5
votes
Stationarity assumption for a point process
Stationarity implies that the statistical parameters of an underlying process do not vary over space (or time), and is often formally described as "invariance under translation" (not to be confused ...
5
votes
Accepted
Why do we treat a value at each location as a random variable?
I think you are confusing the ideas of a random variable, $X$, and a collection of random variables, more properly known as a random process, $(X_{t})_{t \in T}$. In this notation, $T$ is some index ...
- 1,388
4
votes
Accepted
Is the spherical covariance function not positive definite for d > 3?
There are at least two conventional meanings of "spherical covariance function." Based on the conclusion you want to draw, we can infer you are referring to the family of functions $G:\...
- 334k
3
votes
Accepted
Can I simulate a random field with nested variogram by a summation of independently simulated random field for each componnet of the nested variogram?
Yes.
To see why, begin with the definition of the variogram for a second-order stationary random field $Z$ as
$$\gamma(h;Z) = \frac{1}{2}E\left[(Z(u+h)-Z(u))^2\right]$$
for any $u$ where both $u$ and $...
- 334k
3
votes
Algorithm for generating a Poisson process on a complicated 2d geometry
A very simple solution (in the same spirit as the answer by @jbowman) is to generate a Poisson point process in the bounding box and then restrict to the irregular region. This is valid since for a ...
- 1,228
3
votes
What is the nugget effect?
The nugget effect is like the random noise. It's just the small scale variability that you can't estimate with your large scale variability model.
The nugget effect is made of the measurement error ...
- 146
3
votes
Accepted
How to cluster trips, i.e. directed lines on a plain
I would try with only (start lon, start lat, end lon, end lat) because distance does not really mean anything in this case, because one can go the same distance also to the "wrong way" and same ...
- 446
2
votes
How to test for correlation between two weather station's data
Your problem description is not too specific, so for exploratory analysis I can only give some general suggestions. (This may also be relevant.)
First, you should definitely visualize the weather ...
- 13.1k
2
votes
Temporal Variogram
Of course you can use variograms also for time series data. The variogram has one advantage as compared to the autocorrelation function, it only needs the hypothesis of intrinsic stationarity, not ...
- 82.8k
2
votes
Accepted
Parametrization of the Matérn Covariance Function
There's a hyperlink in the explanation to the documentation for RMmodel, where var and scale ...
- 46.8k
2
votes
Accepted
Cokriging and collocated cokriging data requirements
Co-kriging is often used, as you mentioned, when we have a 'secondary' source of data. The main idea is that the abundant data is a good guess of the primary data, but they're not the same so you ...
- 2,937
2
votes
Return Period and Probability
Of course not. Specifically, the probability of not getting hit at all is (Let $P(H_i')$ be the probability of not being hit in day $i$):
$P(H_1')P(H_2')...=P(H_{200}')=\underbrace{(0.995)(0.995)...(...
- 58.2k
2
votes
Accepted
What is the nugget effect?
In the context of estimating a variogram, a nugget allows for the variogram to assume a non-zero value for two observations having a distance of zero. The implication also is that the correlation ...
- 64.8k
2
votes
Can we apply geostatistics on data which is not normally distributed?
Geostatistics is an entire branch of statistics -- it's all the statistics that are applied to spatial data. Some of its methods may require normally distributed data (see below), but many do not. For ...
- 128k
2
votes
Statistical test whether data conforms to a spatial point process--gaza bombing locations
Some thoughts, quite naive perhaps. Use or modify as you see fit.
If you have information on which regions are built and which are not, you can make use of simulation. Compute a suitable statistic of ...
- 8,718
2
votes
Algorithm for generating a Poisson process on a complicated 2d geometry
You can find the areas of the counties in California from https://en.wikipedia.org/wiki/List_of_counties_in_California. This will enable you to generate a count $n_i$ from the appropriate Poisson ...
- 41.1k
1
vote
Quantifying magnitude of change in dataset containing base values of 0?
From a mathematical/statistical point of view, you can scale the differences any way you want. What scale makes sense/is best really depends on your scientific question. Relative differences often ...
- 47.4k
1
vote
Can I create a test dataset with known errors to validate accuracy assessment?
Yes, this is a perfectly valid procedure. You need to make sure that your model can distinguish between "similar" and "not similar". So you simulate both kinds of datasets, and make sure that they are ...
- 12.8k
1
vote
How can I understand these variograms?
I didn't have a chance to look carefully into the code, but I can already guess what you are experiencing. It may have to due with the fact that you are simulating random fields on finite domains (in ...
- 233
1
vote
What are the possible machine learning models for this geospatial analysis task?
I would try a CNN architecture like U-net with following input planes :
- one plane for signal strength with negative value for unknown value
- N planes to encode the terrain type (with one-hot ...
- 209
1
vote
Zonal statistics (mean± StDev) from polygons with different area
Unequal group sizes are often inevitable in observational studies. There is no general problem basing calculations of means and standard deviations on groups with different sizes. It's not usually a ...
- 102k
1
vote
How much data do I need in spatial hotspot analysis?
You need to read the original paper by Getis and Ord that introduces the G statistics:
Getis A, Ord JK. 1992. The analysis of spatial association by use of distance statistics. Geographical Analysis ...
1
vote
How do you interpret this variogram?
This is known as the hole effect in the literature. The oscillations correspond to cyclic patterns in your domain. It is very likely that you have "blobs" of high values and low values. The size of ...
- 233
1
vote
What is the best procedure to detrend data without loosing its anisotropy?
The concepts of anisotropy and trend are disconnected. If you remove a trend and the residual map does not show preferential directions of spatial continuity, then use a isotropic model.
You could ...
- 233
1
vote
How to generate distance variable using street addresses
Not necessarily efficient (though personally I don't consider thousands to be that high of a number data wise) but depending on the region you can download metadata to convert zip/post codes to lat/...
- 810
Only top scored, non community-wiki answers of a minimum length are eligible