search this site.

120507P - ETHICAL ISSUES IN STATISTICAL RESEARCH: LIMITATIONS OF STATISTICAL ANALYSIS

Print Friendly and PDFPrint Friendly



Paper written by Professor Omar Hasan Kasule Sr.


1.0 STATISTICAL VS SUBSTANTIVE:
·      An investigator starts with a substantive question. This is formulated as a statistical question. Data is then collected and is analyzed to answer the statistical question. The answer to the statistical question is the statistical conclusion. The investigator uses the statistical conclusion and other knowledge available to him to reach a substantive conclusion.
·      Statistics therefore gives statistical and not substantive answers.
·      Statistical conclusions are made about groups and not individuals. Any inference to the individual is to a hypothetical individual. In other words the statistical conclusion is depersonalized. 

2.0 ANAYLSIS VS INTERPRETATION:
·      Statistical results are dry unless well interpreted and put in the right context.
·      Bio-statistics only summarizes the data but does not interpret.
·      Interpretation involves knowledge of the context, prior knowledge, and prior suppositions.
·      Personal familiarity with the data may also influence how it is interpreted.
·      Data that is well analyzed may be poorly interpreted

3.0 MISUSE OF STATISTICS:
·      Statistics is a tool that can be used well or badly. If misused, the blame should be on the user and not the tool.
·      Mis-use of statistics can be deliberate deception or can be due to ignorance.
·      Selective presentation of desired results while suppressing undesirable ones is one method of misuse of statistics.
·      Sometimes the cart is put before the horse when the statistical methodology available determines what types of research questions are dealt with. The correct approach is to have research questions and select the suitable method.

4.0 MIS-USE OF THE COMPUTER:
·      Computation is not an end in itself. It is a tool that can be used well or can be mis-used.
·      The computer itself has very little intelligence all it possesses is speed and memory.
·      A human must have a clear idea of what is required of the computer and must instruct it accordingly.
·      The human must also be able to intelligently interpret the output from the computer. 
·      All who tinker with computers must remember the adage ‘rubbish in/rubbish out’.