tag:blogger.com,1999:blog-4900303239154048192.post6100421601353924598..comments2024-03-06T06:34:42.881-05:00Comments on EconoSpeak: Revised Job Data SurveyUnknownnoreply@blogger.comBlogger3125tag:blogger.com,1999:blog-4900303239154048192.post-54765324861367954662015-04-07T11:01:20.483-04:002015-04-07T11:01:20.483-04:00"filter those out" = "control for&q..."filter those out" = "control for"Sandwichmanhttps://www.blogger.com/profile/11159060882083015637noreply@blogger.comtag:blogger.com,1999:blog-4900303239154048192.post-38797800136590560522015-04-07T11:00:21.490-04:002015-04-07T11:00:21.490-04:00It's like randomizing the question order in a ...It's like randomizing the question order in a survey. Sometimes answers are influenced by incidental qualities of the survey and one wants to filter those out. So in an experiment, I might give half the subjects graphs with losses first and half with gains first.Sandwichmanhttps://www.blogger.com/profile/11159060882083015637noreply@blogger.comtag:blogger.com,1999:blog-4900303239154048192.post-76158349955439173052015-04-07T10:48:05.659-04:002015-04-07T10:48:05.659-04:00Why reverse gains and losses?Why reverse gains and losses?wcwhttps://www.blogger.com/profile/16307608293310560164noreply@blogger.com