survey monkey integrates spss

[msherman]

It looks like the newly created variable (for q0002) used the expanded format as opposed to the condensed format. If the expanded format is desired (which allows for multiple responses per item) then each _0001   extension represents a particular response.  For instance, gender might be coded with  0 and 1 and since an individual cannot be both one would only need to use the condensed format where there would be only one variables (gender) and that variable would have values of 0 or 1. On the other hand, if one had a variable as “race” (with four choices---Caucasian, African-American, Hispanic, and Asian) bone could respond with any number of races then one would want to use the expanded format. Thus,  there would be four variables created-one for Caucasian, one for African-American, one for Hispanic, and one for Asian.  SM most likely would create four variables q0002_0001  q0002_0002  q0002_0003  q0002_0004 and would look like

 

q0002_0001  q0002_0002  q0002_0003  q0002_0004

          1                       1                      .                      .

          .                        .                      1                    .

          1                       .                      .                      1

          .                        1                     .                     .

          1                       1                      1                     1

          1                       .                       .                     .

          1                       .                       1                    .

          .                        .                       .                    1

 

 

Martin F. Sherman, Ph.D.

Professor of Psychology

Director of  Masters Education in Psychology: Thesis Track

 

Loyola University Maryland

Department of Psychology

222 B Beatty Hall

4501 North Charles Street

Baltimore, MD 21210

 

410-617-2417

[hidden email]

 

 

 

 

 

From: SPSSX(r) Discussion [[hidden email]] On Behalf Of John F Hall
Sent: Saturday, September 28, 2013 1:07 AM
To: [hidden email]
Subject: Survey Monkey integrates to SPSS

 

Just been playing around with Google Chrome and came across Pat Cleland’s Feb 2011 post on SPSS and Survey Monkey.  She wrote:

---

I just downloaded ‘my’ survey from SM.  Here’s what I found:

Good news: I have both value and var labels for each variable. The value labels are the options in the questions and the var labels are the questions themselves.

Bad news:  Var names as supplied are not totally helpful.  Here are the var names for the 1^st two questions in my survey:

q0001

q0002_0001

q0002_0002

q0002_0003

q0002_0004

q0002_0005

q0002_0006

q0002_0007

q0002_0008

q0002_0009

q0002_0010

However, when I looked at the survey itself, I could see that the questions numbers, such as Q1 and Q2 now appeared on the survey so it’s not impossible to find your way around.

Overall, in my opinion, this is a vast improvement on exporting to excel, editing the field names so that they work as SPSS var names, reading in and merging a bunch of excel files (if you have more fields than can be accommodated in a single excel sheet) and adding value and var labels for every variable. 

---

She’s a regular contributor to the SPSS-X list so probably already knows this, but one solution would be to use:

RENAME VARIABLES  (q0001 to q0002_0010 = <new varname list>)

Make sure the two lists contain the same number of variables. 

Was Survey Monkey easy to use?  I’m thinking of testing some old questionnaire items from the 1970s on a more recent sample.

 

John F Hall (Mr)

[Retired academic survey researcher]

 

Email:   [hidden email] 

Website: www.surveyresearch.weebly.com

SPSS start page:  www.surveyresearch.weebly.com/spss-without-tears.html