Evaluating a Regression Model Using the Constant Variance Assumption

J

Jim Shelor

#1


Covers,

I am reviewing a regression model that is structured like this:

Y = β0*(X1^β1*X2^β2*X3^β3*X4^β4)

The analyst performed a transformation to obtain:

Ln(Y) = lnβ0 + β1lnX1 + β2lnX2 + β3lnX3 + β4lnX4

The analyst then regressed the ln equation to find the coefficients and provided the equation in both the ln form and the power law form.

When I regress the power law form against the experimental result, there is a severe violation of the constant variance assumption. A severe triangle increasing to the right on the residuals vs fit plot.

When I regress the ln form of the regression against the ln of experimental data the constant variance assumption is met, slightly increasing variation, (naturally since it is an ln function).

The analyst says that the equation for Y is valid because the equation for ln(Y) satisfies the constant variance assumption.

Since I am not interested in the value of ln(Y), I am only interested in Y, I am telling the analyst that the violation of the constant variance assumption makes the regression model of interest (Y) invalid, regardless of the result of residuals vs fits for the ln form of the equation.

Is there something I am missing here? Doesn’t the model for Y have to meet the constant variance assumption? Am I supposed to care whether or not the ln(Y) model meets the constant variance assumption when ln(Y) is not the number I care about?

By the way, if I take the antilog of the result of the ln form of the equation, the severe violation of the constant variance assumption returns (as would be expected).

Thanks in advance for the help.

Sincere regards,

Jim Shelor
 
Last edited by a moderator:
Elsmar Forum Sponsor
J

Jim Shelor

#3
Thanks Miner,

I guess I must just be thick because when I do the equation

Y = exp(ln(Y))

and I regress it against the observed Y, I get exactly the same residuals vs fits plot as I do if I use the non-log form of the equation.

It is difficult for me to picture why working the problem to get ln(Y) and then converting to Y (exp(ln(Y)) makes the end result any less flawed.

Jim Shelor
Not the brightest bulb in the lamp.
 

Bev D

Heretical Statistician
Staff member
Super Moderator
#5
Jim: you asked what you are missing. you are missing physics. you need an equation (model) that works for your situation.

are you only interested in the mathematics of this situation or are you looking for a model that will help resolve some real world situation?

If the latter a bit more info on the situation, how the original model(s) was developed - if you could, post the data - what you hope to use the model for etc. will help us help you...
 

Statistical Steven

Statistician
Staff member
Super Moderator
#6
I am thinking perhaps I have not expressed my question correctly. I have attached a more thorough explanation of the question for your review.

Thank you in advance for the help.

Jim Shelor
Jim -

I think you are confusing some concepts (then again, I might be also). Typically when you have a data set with X's and Y's you try to fit the linear model Y=X. If the residual pattern shows that the assumptions of regresssion are violated, you transform the data. Sometimes you transform both X and Y, sometimes just X and sometimes just Y (see Daniel and Wood for residual pattern interpretation). In your case, you are doing a log-log transformation. So the coefficients (betas) are not in the natural units, but in log units. So you transform back the betas to get the appropriate coefficents for the model. If you regress ln(Y)=ln(X), then take exp(beta), you will NOT get the same coefficent as Y=X.

Does that make any sense?
 
J

Jim Shelor

#7
Bev and Steven,

Right now I am only interested in the mathematics of the situation.

I cannot provide more detail on the experiment because the data files are hugh and the experiment is a one of a kind research project.

I can say that the only number I am concerned with at this point is Y and is the model presented by my analyst adequate for predicting Y.

It seems to me that if every model that actually outputs Y has these serious constant variance issues, and every model that calculates lnY then Y is recovered using exp(ln(Y)) has these serious variance issues, the models do not effectively predict Y for future X combinations.

I have studied transformation some Steven and there are two reasons why my analyst wanted to do the ln-ln transformation.

1. To linearize the right side of the equation.
2. To stabilize the variance by transforming the left side of the equation.

I think transforming both sides of the equation was a mistake. I would have transformed only the right side of the equation and then examined the variance. But before I have my analyst redo this regression analysis I wanted to find out if anyone else thought the current analysis is correct from a purely statistical perspective and I just don't understant constant variance as well as I thought I did.

The bottom line for me is that Y must have a constant variance, ln(Y) only needs a constant variance if ln(Y) is my response value of interest.

Am I misinterpreting the statistics of this situation?

Thanks,

Jim
 

Statistical Steven

Statistician
Staff member
Super Moderator
#8
Bev and Steven,

Right now I am only interested in the mathematics of the situation.

I cannot provide more detail on the experiment because the data files are hugh and the experiment is a one of a kind research project.

I can say that the only number I am concerned with at this point is Y and is the model presented by my analyst adequate for predicting Y.

It seems to me that if every model that actually outputs Y has these serious constant variance issues, and every model that calculates lnY then Y is recovered using exp(ln(Y)) has these serious variance issues, the models do not effectively predict Y for future X combinations.

I have studied transformation some Steven and there are two reasons why my analyst wanted to do the ln-ln transformation.

1. To linearize the right side of the equation.
2. To stabilize the variance by transforming the left side of the equation.

I think transforming both sides of the equation was a mistake. I would have transformed only the right side of the equation and then examined the variance. But before I have my analyst redo this regression analysis I wanted to find out if anyone else thought the current analysis is correct from a purely statistical perspective and I just don't understant constant variance as well as I thought I did.

The bottom line for me is that Y must have a constant variance, ln(Y) only needs a constant variance if ln(Y) is my response value of interest.

Am I misinterpreting the statistics of this situation?

Thanks,

Jim
Jim -

The problem is that Y is NOT distributed as a normal distribution. I agree that it is probably more accurate to only transform the X side of the equation then fit the regression. If that stabilizes the variance, you have your model. Since I am not the statistician doing the analysis, it is hard for me to know if just transforming the X's is sufficient.

Since Y is most likely a lognormal distribution, the variance increases with the X and must be stabilized if you want to use "linear" regression. You can use logistic regression with a log link function to get the parameters directly in the correct distribution.

Hope that helps.
 
J

Jim Shelor

#9
Steven,

I believe the plots clearly demonstrate that Y is normally distributed.

Respects,

Jim Shelor
 
Thread starter Similar threads Forum Replies Date
Tagin Evaluating nonconformances for escalation using Bayesian methods? Statistical Analysis Tools, Techniques and SPC 2
R Evaluating the need for preventive action Preventive Action and Continuous Improvement 3
M Informational US FDA – FDA provides updates on the agency’s continued commitment to evaluating postmarket safety of Essure device Medical Device and FDA Regulations and Standards News 0
S Evaluating the possibilities of using qmswrapper or greenlightguru Document Control Systems, Procedures, Forms and Templates 4
C Evaluating GRR Scores %Tol vs %TV Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 9
Q Evaluating Effectiveness of a Preventive Action after Closure Preventive Action and Continuous Improvement 7
J Potential Customers Asking for EIRs / 483s when evaluating a CRO for future work US Food and Drug Administration (FDA) 2
P FDA - Evaluating Substantial Equivalence in Premarket Notifications 21 CFR Part 820 - US FDA Quality System Regulations (QSR) 1
M Quality Control Procedure and Procedure for Evaluating Sub Contractor Document Control Systems, Procedures, Forms and Templates 1
M Evaluating Vendor (Supplier) Products using SQC Statistical Analysis Tools, Techniques and SPC 6
K Evaluating different Startup Options in EU and MDD ISO 13485:2016 - Medical Device Quality Management Systems 4
S Trading Company - Evaluating Supplier Performance and Approved Supplier List ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 2
J The 510(k) Program: Evaluating Substantial Equivalence in Premarket Notifications 21 CFR Part 820 - US FDA Quality System Regulations (QSR) 2
E Evaluating Lean Knowledge: Lean Philosophy Course for Production Engineering Students Lean in Manufacturing and Service Industries 1
A Evaluating an Integrated Management System - Dissertation Topic ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 5
optomist1 Evaluating Capability Indices with Minitab Using Minitab Software 7
C Trend Analysis - Evaluating Quality of Pricing - ANVOA or Std Dev? Statistical Analysis Tools, Techniques and SPC 25
W Re-Evaluating Corrective Actions - Recurrence of a Customer Complaint Nonconformance and Corrective Action 7
D Good source for Checking and Evaluating Control Plans needed FMEA and Control Plans 4
R EMP (Evaluating the Measurement Process) Studies for Bias Effect Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
Wes Bucey "Downsizing" ramifications - Evaluating and Interpreting the News World News 0
A Methods of evaluating compliance to ISO 14001 ISO 14001:2015 Specific Discussions 6
M Evaluating my QMS (Quality Management System) ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 11
G 100% Sort Verification - Statistical Method for Evaluating Suspect Material Statistical Analysis Tools, Techniques and SPC 19
J Evaluating and Reporting the Results of Layered Process Audits Document Control Systems, Procedures, Forms and Templates 9
G Evaluating Software for GMP Criticality? Software Quality Assurance 3
M Evaluating adverse effect on device tested with out of tolerance instrument General Measurement Device and Calibration Topics 3
Q Evaluating Internal Audit Results Internal Auditing 24
P Rockwell, Brinell, Vickers Conversion - Evaluating Aluminum 6061-T6 and 6063-T6 General Measurement Device and Calibration Topics 11
U Evaluating the aspects... All judgement based or is there a more objective way? Miscellaneous Environmental Standards and EMS Related Discussions 1
D Evaluating competence on training for new ISO 13485 standard for employees ISO 13485:2016 - Medical Device Quality Management Systems 7
Q "Service" Vendor (Supplier) Evaluation - How are you evaluating suppliers? Supplier Quality Assurance and other Supplier Issues 5
N Evaluating Process Stability - Unstable Processes - Cpk/Ppk? Capability, Accuracy and Stability - Processes, Machines, etc. 6
Z Seeking GM standard GM9684P - Procedure for evaluating parting lines Customer and Company Specific Requirements 2
S Metrics for Evaluating Design process Design and Development of Products and Processes 2
C Evaluating software that measures Ppk, Cmk, Cpk, PPI, etc. Capability, Accuracy and Stability - Processes, Machines, etc. 4
H Good starting point for a new QC Manager? Evaluating Existing Procedures Document Control Systems, Procedures, Forms and Templates 21
Gman2 Evaluating training, needed for office personnel? ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 18
G Evaluating Processes - Cycle Time Concepts - Three Levels for any process Manufacturing and Related Processes 3
C Evaluating the Effectiveness of Internal Audit Process Internal Auditing 16
Marc Evaluating 5.3 c - Quality Policy - Framework General Auditing Discussions 1
T Evaluating Customer Satisfaction ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 14
B Risk Anlysis for Evaluating then Voiding or Not Issuing CPAR's Nonconformance and Corrective Action 1
M ISO 9001:2000 - Evaluating Training Effectiveness and Why ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 12
C Can anyone suggest a means of evaluating a suppliers performance? Supplier Quality Assurance and other Supplier Issues 4
Raffy Evaluation Form - Re-evaluating suppliers for their performance Supplier Quality Assurance and other Supplier Issues 8
G Evaluating Training Effectiveness - 6.2.2 Competence, Awareness and Training ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 55
S Supplier Evaluation - Evaluating transport suppliers and equipment suppliers Supplier Quality Assurance and other Supplier Issues 2
D What exactly is needed on the subcontractor list for evaluating subcontractors QS-9000 - American Automotive Manufacturers Standard 4
D Evaluating Subcontractor On-time Delivery Misc. Quality Assurance and Business Systems Related Topics 3

Similar threads

Top Bottom