The only count less than one for a cell is zero. So you cannot mean that. What the rule of thumb applies to for the Chi-squared contingency coefficient is the expected value of a cell. If you have two nominal level variables, you can crosstab them, i.e., make a table that has as many rows as the first variable has legitimate values, and as many columns as the second variable has legitimate values. The rows and columns are labeled with the values of the two variables. The intersection of a row and a column is called the cell. The edges of the table are called the row and column margins. The "observed value" is the count of cases in a cell (i.e., that have a particular pair of values.)
Since this seems like a homework problem, I'll refer you to your textbook to see how to get the expected value for a CELL. Hope this helps. Art [EMAIL PROTECTED] Social Research Consultants University Park, MD USA (301) 864-5570 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
