Note:Please see attachment for more clarification TQSE1 1. List the five assumptions of linear regression 2. Suppose you have measured the temperature, pressure, flow rate and level at various...

Note:Please see attachment for more clarification


TQSE1


1. List the five assumptions of linear regression


2. Suppose you have measured the temperature, pressure, flow rate and level at various locations in a process, and you want to use these to predict the plant output. Identify two of the above assumptions that are likely to be violated. Explain why.


3. Explain the purpose of training, test, and validation data sets in developing a model. What are the data coverage requirements for each data subset?


4. Describe two methods for dividing a large data set in to training, test, and validation data sets. State whether each of your methods is appropriate for observational data, time-series data, or both.


5. Define generalization in the context of model performance. Describe the cross-validation approach to optimizing parameters in a model. How does this address the problem of overfitting?


6. What is data standardization? Give the formula and describe why it may be important for locally weighted regression.


7. What is the minimum regularization parameter (a) needed to have a well-conditioned matrix in ridge regression?




Document Preview:

TQSE1 1. List the five assumptions of linear regression 2. Suppose you have measured the temperature, pressure, flow rate and level at various locations in a process, and you want to use these to predict the plant output. Identify two of the above assumptions that are likely to be violated. Explain why. 3. Explain the purpose of training, test, and validation data sets in developing a model. What are the data coverage requirements for each data subset? 4. Describe two methods for dividing a large data set in to training, test, and validation data sets. State whether each of your methods is appropriate for observational data, time-series data, or both. 5. Define generalization in the context of model performance. Describe the cross-validation approach to optimizing parameters in a model. How does this address the problem of overfitting? 6. What is data standardization? Give the formula and describe why it may be important for locally weighted regression. 7. What is the minimum regularization parameter (a) needed to have a well-conditioned matrix in ridge regression?



May 14, 2022
SOLUTION.PDF

Get Answer To This Question

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here