tag:blogger.com,1999:blog-5652924.post5861702194488484094..comments2021-07-25T00:58:40.091-07:00Comments on Data Mining and <br>Predictive Analytics: Taking Assumptions With A Grain Of SaltDean Abbotthttp://www.blogger.com/profile/16818000233889520746noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-5652924.post-43718104324692309652009-05-16T11:23:00.000-07:002009-05-16T11:23:00.000-07:00Nice post, which reminded me a problem i once had ...Nice post, which reminded me a problem i once had : I was unable to normalize a positively skewed distribution whether doing sqr, log,1/x, you name it! What is your advice on a situation like this?<br /><br />Thanks!Harrynoreply@blogger.comtag:blogger.com,1999:blog-5652924.post-56572320183523291102009-04-26T17:47:00.000-07:002009-04-26T17:47:00.000-07:00I fully agree, Will. Knowing the assumptions gives...I fully agree, Will. Knowing the assumptions gives you clues to why algorithms may or may not work well. For example, outliers can severely impact a linear regressions model because of the squared-error criterion. If one knows this, and identifies the outliers (and removes them or mitigates their influence), the overall model can be improved. <br /><br />Also, knowing how forgiving an algorithm Dean Abbotthttps://www.blogger.com/profile/16818000233889520746noreply@blogger.comtag:blogger.com,1999:blog-5652924.post-24689163951830467792009-04-26T11:33:00.000-07:002009-04-26T11:33:00.000-07:00I think you have a point there. A 'pure' statistic...I think you have a point there. A 'pure' statistician would definitely disagree but the algorithm might work regardless if the assumptions are met. The guilt stays with the analyst all the way to interpretation. If we could just get rid of a priori assumptions...amarkoshttps://www.blogger.com/profile/12448232044058234040noreply@blogger.com