LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (January 2008)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Mon, 21 Jan 2008 21:05:08 -0500
Reply-To:     Richard Ristow <wrristow@mindspring.com>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Richard Ristow <wrristow@mindspring.com>
Subject:      Re: Dummy Coding and Interpreting Regression Analysis
Comments: To: Justin Meyer <justin.meyer@rowlandreading.org>
In-Reply-To:  <2BDDE596EB04B6459ADDF6592D8AE3105CC91E@rowlandsrvr.Rowland
              Reading.local>
Content-Type: text/plain; charset="us-ascii"; format=flowed

At 03:36 PM 1/18/2008, Justin Meyer wrote:

>I am working to determine if a subjective rating of schools' >implementation is a predictor of posttest score for students in >those schools. For the subjective rating of schools' implementation, >schools are rated as tier 1, 2, or 3, with 1 being the best >implementation and 3 being the worst. I am using a regression >analysis, entering all of the variables at the same time. Because >the tier status consists of three possible responses, I dummy coded >it into two variables. The first variable is 1 for "Tier 2", 0 for >"not Tier 2". The second variable is 1 for "Tier 3", and 0 for "not >Tier 3". Is this the correct way to code this variable for a >regression analysis?

It is certainly correct; there are some variations, that are also correct.

>I found a b (unstandardized coefficient) of -10.269 for Tier 2 and >21.171 for Tier 3. Does this mean that, when all other variables are >equal, students in Tier 2 score an average of 10 points less on the >posttest and students in Tier 3 score an average of 21 points more >on the posttest when compared to Tier 1?

It means exactly that. However, don't forget that these estimates should be expressed as confidence intervals: "95% confidence interval is...", and give the range. The 95% confidence interval is the estimated value, +/- twice the standard error of estimate.

>The output from the regression, except for charts, is pasted below:

Thank you for that. However, you may see that it came through with so many line-breaks added, that one can't do much with it.

So, does this get you farther?

-Best of luck, Richard Ristow

===================== To manage your subscription to SPSSX-L, send a message to LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD


Back to: Top of message | Previous page | Main SPSSX-L page