- Anti Depressants-Sleeping Aid
- Cardio & Blood-Cholesterol
- General health
- Healthy bones Osteoporosis Rheumatic
- Men's Health-Erectile Dysfunction
- Skin Care
- Weight Loss
- Women's Health
March 27, 2009
Our standard practice in this volume is to make explicit the quantity of unknowns, but base all calculations upon the known. In instances where the data for one group contain a large number of unknowns and the data for another group contain few, one is forced to omit the unknowns—otherwise the calculations represent not so much the differences or similarities between the groups but the variations in their proportion of unknowns.
Ordinarily the number of unknowns is small, but there are two situations that lead to very large numbers of unknowns. One results from the fact that a particular question was not included in the earlier interviewing schedule, but was added later. For example, in 1939-1940 we asked only about current masturbation frequency, not about previous frequencies; consequently, nearly every male case history of that early stage of the research will count as an unknown for masturbation frequencies prior to the year of interview.
The second situation arises only in areas of peripheral interest, where we are seeking in our accumulated data an item of information that was not covered in our routine interviews. The best examples concern the circumstances existing at and just prior to the commission of a sex offense. The nature of the place where the offense occurred—at the subject’s residence, at the object’s residence, in an automobile, in a rural area, etc.—is unknown in from one fifth to one third of the cases. The question of who reported the offense to the police has even greater proportions of unknowns.
The exclusion of unknowns is a dangerous procedure only when some bias is involved. In other words, if there is reason to believe that the unknowns differ from the knowns, then drawing inferences from only the knowns is misleading. For example, let us say that the younger the child, the more sensitive and guilt-stricken was the offender, and the less likely he was to admit he knew the child’s age. Thus a high proportion of the unknowns would in actuality represent young children, and a calculation of ages based solely on the knowns would result in an erroneously high average age. It should be added that this illustration actually was no problem to us and, moreover, we had access to the records wherein the age of the object was usually given.
The problem of unknowns has led us to abandon a concept extensively utilized in our earlier publications: the concept of the frequency of total outlet, that is, the frequency of the sum total of all orgasms experienced regardless of source.
No Comments »
No comments yet.
Leave a comment
You must be logged in to post a comment.