Research manifesto Statistics Index CERG Home Page   CERG Resources Bibliography

Tasks I will go directly to the index of statistical and anlytical routines.     I want to check out one variable Is the variable clean? Is there any dirty data?   What do its descriptive statistics look like? Mean (average), dispersion etc.   Can I be confident that it is a reasonable approximation to the population it represents? eg   I want to look at groups of subjects using that variable   Another variable breaks the sample into groups. Is there a difference between these groups?   I have measured subjects, on the same variable, more than once   Do the subjects respond in much the same way each time they are measured?   I want to check out the relationship between two variables   Do these two variables behave in much way the same ? eg Is there a difference in the way people respond to one variable against the other variable? Might the first variable predict the results on the second variable?   I want to look at a bunch of variables   Does the combined effect of a group of variables predict the outcome on another variable? eg Is there some underlying set of variables which simplify the way we see this group of variables? eg There are groups I have used in the study (eg socio-economic background)   Are there variables which distinguish between these groups eg ©CERG 2000 Created by Dr.Selby Markham Last updated  May 2000