SUBJECT: Re : [ &NAME ] Statistical tests for corpus studies Dear &NAME , I would recommend the log-likelihood statistic over chi-squared as it is applicable to a wider range of frequencies . For more details see : &WEBSITE Regards , &NAME . Dr. &NAME &NAME Director of UCREL University &NAME for Computer Corpus Research on Language Computing Department , &NAME University , &NAME , &NAME &NAME , &NAME . Web : &WEBSITE &NAME : &NUM &NUM &NUM &NAME : &NUM &NUM &NUM Dear all , As a lay-man to statistics , I wish to get some advice on the tests suitable for comparing the frequency of a specific type of word in corpora of different genre . Having in mind are &NAME and &NAME but I 'm not sure they are the appropriate &NUM . Thanks in advance &NAME &NAME Research Assistant Dept. of English and &NAME City University of &NAME &NAME