mean results inconsistent with scale

[karen lewis]

I am using a 5 point likert scale in my study.  However, the mean results
are not from 1-5.  Instead the min is 33 and the max is 55 for one sub-
scale and is similarly different for the other.  How can this be?

 Statistics
    Closeness w/ Child  Conflict w/ Child
Mean         48.33 27.9311
Std. Dev 4.865 8.60693
Minimum  33 12.00
Maximum  55 52.00

N Valid 120 122
 Missing 56 54

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (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

[Poling, Taylor Leigh]

Have you summed, instead of averaged, several items to create your scale variable? Is your missing data coded as a number greater than 5?

---

From: SPSSX(r) Discussion on behalf of <Karen Watkins-lewis>
Sent: Thu 8/20/2009 3:37 PM
To: [hidden email]
Subject: mean results inconsistent with scale

I am using a 5 point likert scale in my study.  However, the mean results
are not from 1-5.  Instead the min is 33 and the max is 55 for one sub-
scale and is similarly different for the other.  How can this be?

 Statistics
    Closeness w/ Child  Conflict w/ Child
Mean         48.33 27.9311
Std. Dev 4.865 8.60693
Minimum  33 12.00
Maximum  55 52.00

N Valid 120 122
 Missing 56 54

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (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

[Hector Maletta]

Perhaps the actual values include some cases off range. Ask for a frequency distribution to check on it.
Another possibility is that some cases are codified with some special figures to indicate "No answer", such as 99, and then these values were not marked as missing values. In such case, the mean would include those special codes and distort the mean. With the frequency distribution you can also check on this.

Hector


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of <Karen Watkins-lewis>
Sent: 20 August 2009 15:37
To: [hidden email]
Subject: mean results inconsistent with scale

I am using a 5 point likert scale in my study.  However, the mean results
are not from 1-5.  Instead the min is 33 and the max is 55 for one sub-
scale and is similarly different for the other.  How can this be?

 Statistics
    Closeness w/ Child  Conflict w/ Child
Mean         48.33 27.9311
Std. Dev 4.865 8.60693
Minimum  33 12.00
Maximum  55 52.00

N Valid 120 122
 Missing 56 54

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (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

[Jason Ferris-3]

Hi Karen,
Based on the assumption that you didn't design your data frame (i.e.,
variables etc).  A possibility is that the 1 through 5 that you see are
value labels representing some other form of data value.  For example a
value label 1 could represent a data value 33 and a value label 5 could
represent a data value 55.
This could provide you with your results but your data view display
value labels (1-5).

Again this is to provide a possible answer not to question your data
frame construction.

Jase

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
<Karen Watkins-lewis>
Sent: Friday, 21 August 2009 5:37 AM
To: [hidden email]
Subject: mean results inconsistent with scale

I am using a 5 point likert scale in my study.  However, the mean
results
are not from 1-5.  Instead the min is 33 and the max is 55 for one sub-
scale and is similarly different for the other.  How can this be?

 Statistics
    Closeness w/ Child  Conflict w/ Child
Mean         48.33 27.9311
Std. Dev 4.865 8.60693
Minimum  33 12.00
Maximum  55 52.00

N Valid 120 122
 Missing 56 54

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (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

------------------------------------------
DISCLAIMER: This message (including any attachments) is intended solely for the addressee(s) named and may contain confidential or privileged information.
If you are not the intended recipient, please delete it and notify the sender.
Views expressed in this message are those of the individual sender,and are not necessarily the views of the Turning Point Alcohol and Drug Centre Inc (ABN: 17 302 055 629).

<a href="http://www.turningpoint.org.au">Turning Point Alcohol and Drug Centre Inc</a>

Although this message and any attachments have been scanned for viruses by 'Trend Micro InterScan' at the time of sending,
you are advised to rescan on receipt.

The whole or parts of this email may be subject to copyright of Turning Point Alcohol and Drug Centre Inc (ABN: 17 302 055 629), and/or third parties.
You can only re-transmit, distribute or use the material if you are authorised to do so.

Please consider the environment before printing this email or attachments.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (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

[Melissa Ives]

Karen,

This is my first thought too. 

IF your items are truly 1-5,

AND

IF your scale is internally consistent (alpha > .7),

then you may want to consider using the calculation we use for likert type scales that will end up with a scale using the same metric as the original items:

 

    compute closeness=rnd(mean.3(varlist)*k).

 

where k is the number of items in the scale.  This requires that at leaset 3 items have valid responses and in essence replaces any missing items with the mean of the existing items within subject. It then rounds the results to return to the original metric of 1-5 (with no decimals). 

This should not be done unless the scale has good internal consistency.

Melissa

---

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Poling, Taylor L
Sent: Thursday, August 20, 2009 2:45 PM
To: [hidden email]
Subject: Re: [SPSSX-L] mean results inconsistent with scale

Have you summed, instead of averaged, several items to create your scale variable? Is your missing data coded as a number greater than 5?

---

From: SPSSX(r) Discussion on behalf of <Karen Watkins-lewis>
Sent: Thu 8/20/2009 3:37 PM
To: [hidden email]
Subject: mean results inconsistent with scale

I am using a 5 point likert scale in my study.  However, the mean results
are not from 1-5.  Instead the min is 33 and the max is 55 for one sub-
scale and is similarly different for the other.  How can this be?

 Statistics
    Closeness w/ Child  Conflict w/ Child
Mean         48.33 27.9311
Std. Dev 4.865 8.60693
Minimum  33 12.00
Maximum  55 52.00

N Valid 120 122
 Missing 56 54

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (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

---

PRIVILEGED AND CONFIDENTIAL INFORMATION
This transmittal and any attachments may contain PRIVILEGED AND
CONFIDENTIAL information and is intended only for the use of the
addressee. If you are not the designated recipient, or an employee
or agent authorized to deliver such transmittals to the designated
recipient, you are hereby notified that any dissemination,
copying or publication of this transmittal is strictly prohibited. If
you have received this transmittal in error, please notify us
immediately by replying to the sender and delete this copy from your
system. You may also call us at [phone] for assistance.