Determining error of function value from state estimates

In summary, the conversation discusses a problem with determining the error in the output of a function called f() from an error covariance matrix. The function operates on a vector of state estimates generated by an observational model, but the true state is unknown. The function is complex and cannot take the error covariance matrix as input. The speaker is seeking advice on how to determine the error in the output of f() based on the given information.
  • #1
hadron23
28
1
Hello,

I have an observation model that generates a vector of state estimates (of the true underlying states) and a corresponding error covariance matrix.

I have a function called f(), which operates on the state estimate to return a scalar value. Note that I do not know the true state, only the estimates and the error cov. matrix. I am trying to determine the error in the scalar value returned by f() from the information provided in the error covariance matrix.

The function f() is rather messy and operates on components of the state estimate vector, thus I cannot input the matrix into this function.

Any idea how I would determine the error in the output of f() based on the error covariance matrix?

Thanks
 
Last edited:
Physics news on Phys.org
  • #2
I suggest you explain what you are doing or give a link to an explanation of it. "Observational model" may be a meaningful term in some specialized field, but apparently it doesn't ring any bells for people on the forum familiar with the mathematical theory of probability.
 

FAQ: Determining error of function value from state estimates

1. What is the purpose of determining the error of a function value from state estimates?

The purpose of determining the error of a function value from state estimates is to assess the accuracy of a predicted value compared to the actual value. This can help identify areas of improvement in the state estimation process and ensure the reliability of the results.

2. How is the error of a function value calculated from state estimates?

The error of a function value is typically calculated by taking the difference between the predicted value and the actual value, and then dividing by the predicted value. This value is often expressed as a percentage to show the relative error.

3. What factors can contribute to errors in function values from state estimates?

There are various factors that can contribute to errors in function values from state estimates, such as measurement errors, inaccuracies in the model used for state estimation, and uncertainties in the initial conditions or input data. Environmental factors or external disturbances can also affect the accuracy of the estimates.

4. How can the error of a function value be minimized in state estimation?

To minimize the error of a function value in state estimation, it is important to use accurate and precise measurement data, validate the model and assumptions used, and carefully consider any uncertainties in the inputs. Additionally, using advanced estimation techniques and incorporating feedback control can also help improve the accuracy of the estimates.

5. What are some common methods for evaluating the error of a function value from state estimates?

Some common methods for evaluating the error of a function value include statistical techniques such as root mean square error or mean absolute error, as well as graphical methods like scatter plots or time series plots. Other methods may involve comparing the estimated values to ground truth measurements or using simulation or validation studies.

Similar threads

I Desirable estimator properties...
Replies
7
Views
2K
I Error bars in Excel (standard deviation, standard error, percentage)
Replies
4
Views
2K
I Scaling covariance for an error calculation
Replies
9
Views
2K
I Extract error from simulated data
Replies
13
Views
1K
I What is the correct definition of measurement uncertainty?
Replies
21
Views
2K
I How to implement proper error estimation using MC
Replies
3
Views
1K
A How to combine correlated vector-valued estimates
Replies
11
Views
2K
I Is Unbiasedness in Estimation Truly Reflective of Population Parameters?
Replies
9
Views
2K
I How Do You Estimate Covariance in Physics Experiments?
Replies
3
Views
1K
I Determining the covariance of two parameters given their explicit relationship
Replies
13
Views
2K

Hot Threads

Recent Insights

Back
Top