Abstract
In a first course in statistics a teacher sometimes wishes to find a problem in which the standard deviations, standard error, correlation coefficient, correlation constant, and regression coefficient are all integers or decimal fractions. If the instructor is willing to use artificial data, the main difficulty is usually finding two series with these desired characteristics. Once these are found, it is a relatively easy matter to change the scale and origins to put the constructed data into the desired range. A method for constructing such problems is given in this paper. I Using conventional notation let y be the dependent variable, x the independent variable and e the error. Since we will later shift the origins we can specify the averages x and y = 0. By definition e, the average error, also = 0. Since we can later change both the absolute and relative scales of y and x, we can also specify oy = 1 and b = 1. From b = r (oy/ix) we then get r o ax. The governing equations for the problem then become:
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
