hi, Tricia some content analysis software has an inter-rater reliability feature that will provide you with a coefficient of agreement (can't recall the name of the specific test right now) between raters. i don't know what is considered an acceptable threshold, but i would suspect the higher, the better.
what is an example of the discrete variable that you are coding for? the hypothesis shouldn't change due to the coding; if you have established a hypothesis prior to conducting the research, then the coding (and the inter-rater reliability coefficient) subsequently provide evidence to support or not support the hypothesis just like in other research endeavors. i suspect it would be a difficult argument to satisfactorily accept or reject the hypothesis based solely on a content analysis, however. the reliability coefficient simply identifies the level of agreement, it doesn't indicate the extent to which the agreement is related to anything else, i.e., relationship between variables that are coded for. john John E. Glass, Ph.D. Professor of Sociology Treasurer, CCCC Faculty Association Division of Social & Behavioral Sciences Colin County Community College Preston Ridge Campus 9700 Wade Boulevard Frisco, TX 75035 +1-972-377-1622 http://iws.ccccd.edu/jglass/ [EMAIL PROTECTED] "We are more concerned about the discovery of knowledge than with its dissemination" B. F. Skinner --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "Teaching Sociology" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/teachsoc -~----------~----~----~----~------~----~------~--~---
