The chisquare test uses the chisquare distribution of one or more sets of data, to test whether there is a significant difference between observed frequencies and expected frequencies.
The chisquare distribution is given by the formula :
where,
A_{ij}  =  actual frequency in the i'th row & j'th column 
E_{ij}  =  expected frequency in the i'th row & j'th column 
r  =  number of rows 
c  =  number of columns 
The chisquare test can then be used to determine whether the value of this function is likely to have occurred by chance alone, in independent sets of data.
In Excel 2010, the Chitest function has been replaced by the Chisq.Test function, which has improved accuracy.
Although it has been replaced, the Chitest function is still available in Excel 2010 (stored in the list of compatibility functions), to allow compatibility with earlier versions of Excel.
The Excel CHITEST function uses the chisquare test to calculate the probability that the differences between two supplied data sets (of observed and expected frequencies), are likely to be simply due to sampling error, or if they are likely to be real.
The syntax of the function is :
Where the function arguments are:
actual_range    An array of observed frequencies 
expected_range    An array of expected frequencies (must have the same dimension as the actual_range array) 
You should bear in mind that the chisquare test is not reliable when the expected values are too small. As a guideline, if any of the expected values are less than 5, or if the total of the expected values is less than 50, you should not rely on the result of the chisquare test.
Cells B3C5 and F3G5 of the spreadsheet below show the observed and expected frequencies of responses from men and women to a simple question.
The chisquare test for independence, for the above data sets, is calculated using the Excel Chitest function as follows:
=CHITEST( B3:C5, F3:G5 )
This gives the result 0.000699103.
Generally, a probability of 0.05 or less is considered to be significant. Therefore, the returned value of 0.000699103 in this example, indicates that there is a significant difference between the observed frequencies and the expected frequencies, which is unlikely to be simply due to sampling error.
Further examples of the Excel Chitest function can be found on the Microsoft Office website.
If you get an error from the Excel Chitest function this is likely to be one of the following :
#N/A   
Occurs if either:


#DIV/0!    Occurs if any of the supplied expected_values are zero  
#NUM!    Occurs if any of the supplied expected_values are negative 