Please login first

A Computer-Aided SAS Macro for the Evaluation of the Simulation Performances in Missingness Settings
Urko Aguirre * 1 , Inmaculada Arostegui 2, 3 , Jose M. Quintana 1
1  Research Unit, REDISSEC: Red de Investigación en Servicios Sanitarios y Enfermedades Crónicas, Hospital Galdakao-Usansolo, Galdakao, Spain;
2  Department of Applied Mathematics, Statistics and Operational Research; REDISSEC: Red de Investigación en Servicios Sanitarios y Enfermedades Crónicas. Faculty of Science and Technology, Leioa. Spain
3  BCAM-Basque Center for Applied Mathematics, Bilbao, Spain.

10.3390/MOL2NET-1-e012
Abstract:

Model validation has become a topic of great interest to many fields such as industry, medicine or even to government. Its main challenge is to provide stable and credible tools so that the decision-maker with the information necessary can make high-consequence judgments.  This process requires simulation modelling and consequently, some guidelines or evaluation criteria are essential in order to draw meaningful conclusions. A computer-aided SAS® macro is developed using the SAS/IML programming language.  Researchers should provide the dataset to be analyzed and the true values to be compared. As a result, the statistical program shows measures (i.e., number of simulations to be performed, bias, accuracy, coverage, etc…) which help investigators to make decisions with a minimal effort of programming.  Numerical results of the aforementioned statistical parameters, plots and a report are returned by the statistical tool. Although this macro is focused on the missingness setting, it is applicable to any other discipline. We encourage researchers to use it to make better statistical assessments of the used methods.

Keywords: simulation; missing data; bias; validation; SAS macro
Comments on this paper
Georgia Tsiliki
Simulation results and missing data mechanisms
Is this intended to be used for simulated data only? I see you need true values of the parameters as input. Also could you elaborate a bit more about the missing data mechanisms- when data are missing 'not at random' this means they have been filtered out?

Thanks.
Urko Aguirre
Dear Georgia Tsiliki,

Many thanks for your feedback, I really appreciate it.

Currently, as it is the first version, this macro is focused on the assessment of the simulations perfomance, conditional on the missingness mechanism. Based on your argument ( by the way, very useful), it is remarkable that more detailed information should be provided when missingness follows MNAR (missing not at random) pattern. That could be a nice improvement for this tool, which will be the future work of this research.


Best regards,


Urko



 
 
Top