SPSSX Discussion

A 4 point Likert scale

Classic

List

Threaded

5 messages Options

Arnaldo Ferrari Nasi-3

A 4 point Likert scale

Hi, I did a certain number of "experiment" using Likert scales as an
ordinal or a continuous scale (this last is the forced assumption).
The results didn't differ so much. Or better, the help that the
results can give you to interpretate the social phoenomenon you are
studying is almost the same. So, I think that you can consider Likert
scales as continuous variables, doing, this way, statistical analysis
that in theory you could not do.

Regarding 4, 6 or 7 point.
I am a Public Opinion Researcher, so I prefer eliminate the neutral
option and suggest the respondent to take positive or negative position.
In my experience the 4 point is better. The 6 points is often
difficult to interpret, often point 1 or 6 are residuals, and give me
too little cells in crosstabs (I usualy conduct 800/1000 cases
surveys). In 99% of times, I ask a 4 points, then I recode in 2
points (positive/negative) and I use this variable in double entry
crosstabs with other pos/neg.
I think that all depends with what kind of survey you will conduct
and what kind of use you do with.

Hope it helps,
Arnaldo.

>With what Art said in mind, if = you're desirous of eliminating the
>neutral option, a six-point scale is far = superior to a four-point
>scale. The research on Likert and Likert-type = scales is that most
>people can discriminate up to seven levels of response, so = you're
>safe with six.
>
>Brian
>
>Why do you want to use only a 4 point Likert = scale?
>_The more you restrict the variance of a variable the more you
>restrict = its possible covariance._
>As a rule of thumb you want items to approximate a continuous
>construct = as much as possible given who your respondents are.
>
>An actual Likert item has 5 points SD D ? A SA. Do you have a =
>Disagree to Agree construct for your response scale?
>
>If your scale has many items, the total (mean) score might not be
>too restricted.
>If you do not have scales, but are measuring a construct with a
>single = variable the restriction of variance and therefore on
>covariance is even more problematical.
>
>In short, a 4 point response scale is usually inadvisable. Why
>coarsen = your measurement any more than is really necessary?
>
>
>Art Kendall
>Social Research Consultants
>
>On 10/17/2011 1:13 PM, Mohamed wrote:
>
>Hi
>
>
>I intend to use a 4 point Likert scale format =
>in my survey.
>
>
>
>I want to know if this puts limitations on =
>the type of statistical =
>analysis

John F Hall

Re: A 4 point Likert scale

Here's my 2 cents' worth. My old mate Nick Moon (Head of Social and
Political Research at GfK/NOP) and other colleagues in the survey research
industry used to claim that there are only two answers to any question,
"Yes" and "No". Forget the statistical modelling: look at the questions.

Mind you, in all or most of the surveys I ever did, the attitude and
semantic differential scales had mid-points.

(See:
http://surveyresearch.weebly.com/ssrc-survey-unit-quality-of-life-in-britain
-surveys.html)

John F Hall

[hidden email]
www.surveyresearch.weebly.com

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Arnaldo Ferrari Nasi
Sent: 18 October 2011 09:30
To: [hidden email]
Subject: A 4 point Likert scale

Hi, I did a certain number of "experiment" using Likert scales as an
ordinal or a continuous scale (this last is the forced assumption).
The results didn't differ so much. Or better, the help that the
results can give you to interpretate the social phoenomenon you are
studying is almost the same. So, I think that you can consider Likert
scales as continuous variables, doing, this way, statistical analysis
that in theory you could not do.

Regarding 4, 6 or 7 point.
I am a Public Opinion Researcher, so I prefer eliminate the neutral
option and suggest the respondent to take positive or negative position.
In my experience the 4 point is better. The 6 points is often
difficult to interpret, often point 1 or 6 are residuals, and give me
too little cells in crosstabs (I usualy conduct 800/1000 cases
surveys). In 99% of times, I ask a 4 points, then I recode in 2
points (positive/negative) and I use this variable in double entry
crosstabs with other pos/neg.
I think that all depends with what kind of survey you will conduct
and what kind of use you do with.

Hope it helps,
Arnaldo.

=====================
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

=====================
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

Arnaldo Ferrari Nasi-3

Re: A 4 point Likert scale

>Here's my 2 cents' worth. My old mate Nick Moon (Head of Social and
>Political Research at GfK/NOP) and other colleagues in the survey research
>industry used to claim that there are only two answers to any question,
>"Yes" and "No". Forget the statistical modelling: look at the questions.

This is what I was just telling, no?
Usually who works in private industry prefers striking yes/no, than
theoretical models (also because they know how fields are done...)

>Mind you, in all or most of the surveys I ever did, the attitude and
>semantic differential scales had mid-points.

Yes, but I prefer the other way:

Some people likes Berlusconi, some other not.
To whom do you feel nearest?

1. like
2. dislike
3. DK

;-) Arnaldo.

>(See:
>http://surveyresearch.weebly.com/ssrc-survey-unit-quality-of-life-in-britain
>-surveys.html)
>
>
>John F Hall
>
>[hidden email]
>www.surveyresearch.weebly.com
>
>
>
>
>
>
>-----Original Message-----
>From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
>Arnaldo Ferrari Nasi
>Sent: 18 October 2011 09:30
>To: [hidden email]
>Subject: A 4 point Likert scale
>
>Hi, I did a certain number of "experiment" using Likert scales as an
>ordinal or a continuous scale (this last is the forced assumption).
>The results didn't differ so much. Or better, the help that the
>results can give you to interpretate the social phoenomenon you are
>studying is almost the same. So, I think that you can consider Likert
>scales as continuous variables, doing, this way, statistical analysis
>that in theory you could not do.
>
>Regarding 4, 6 or 7 point.
>I am a Public Opinion Researcher, so I prefer eliminate the neutral
>option and suggest the respondent to take positive or negative position.
>In my experience the 4 point is better. The 6 points is often
>difficult to interpret, often point 1 or 6 are residuals, and give me
>too little cells in crosstabs (I usualy conduct 800/1000 cases
>surveys). In 99% of times, I ask a 4 points, then I recode in 2
>points (positive/negative) and I use this variable in double entry
>crosstabs with other pos/neg.
>I think that all depends with what kind of survey you will conduct
>and what kind of use you do with.
>
>Hope it helps,
>Arnaldo.
>
>
>
> >With what Art said in mind, if = you're desirous of eliminating the
> >neutral option, a six-point scale is far = superior to a four-point
> >scale. The research on Likert and Likert-type = scales is that most
> >people can discriminate up to seven levels of response, so = you're
> >safe with six.
> >
> >Brian
> >
> >Why do you want to use only a 4 point Likert = scale?
> >_The more you restrict the variance of a variable the more you
> >restrict = its possible covariance._
> >As a rule of thumb you want items to approximate a continuous
> >construct = as much as possible given who your respondents are.
> >
> >An actual Likert item has 5 points SD D ? A SA. Do you have a =
> >Disagree to Agree construct for your response scale?
> >
> >If your scale has many items, the total (mean) score might not be
> >too restricted.
> >If you do not have scales, but are measuring a construct with a
> >single = variable the restriction of variance and therefore on
> >covariance is even more problematical.
> >
> >In short, a 4 point response scale is usually inadvisable. Why
> >coarsen = your measurement any more than is really necessary?
> >
> >
> >Art Kendall
> >Social Research Consultants
> >
> >On 10/17/2011 1:13 PM, Mohamed wrote:
> >
> >Hi
> >
> >
> >I intend to use a 4 point Likert scale format =
> >in my survey.
> >
> >
> >
> >I want to know if this puts limitations on =
> >the type of statistical =
> >analysis
>
>=====================
>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

Swank, Paul R

Re: A 4 point Likert scale

That depends. Are people who dislike Berlusconi a little more like those who hate him intensely or those who like him a little? Opinions have strengths. Think about elections. If there is one candidate you dislike intensely and one you dislike a little, which one would you vote for?

Dr. Paul R. Swank,
Children's Learning Institute
Professor, Department of Pediatrics, Medical School
Adjunct Professor, School of Public Health
University of Texas Health Science Center-Houston

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Arnaldo Ferrari Nasi
Sent: Wednesday, October 19, 2011 3:05 AM
To: [hidden email]
Subject: Re: A 4 point Likert scale

>Here's my 2 cents' worth. My old mate Nick Moon (Head of Social and
>Political Research at GfK/NOP) and other colleagues in the survey research
>industry used to claim that there are only two answers to any question,
>"Yes" and "No". Forget the statistical modelling: look at the questions.

This is what I was just telling, no?
Usually who works in private industry prefers striking yes/no, than
theoretical models (also because they know how fields are done...)

>Mind you, in all or most of the surveys I ever did, the attitude and
>semantic differential scales had mid-points.

Yes, but I prefer the other way:

Some people likes Berlusconi, some other not.
To whom do you feel nearest?

1. like
2. dislike
3. DK

;-) Arnaldo.

Arnaldo Ferrari Nasi-3

Re: A 4 point Likert scale

Yes, in fact I ask in 4 point, then, if the distinction have a too
little interest (most of time), I recode in 2.

Arnaldo.

>That depends. Are people who dislike Berlusconi a little more like
>those who hate him intensely or those who like him a little?
>Opinions have strengths. Think about elections. If there is one
>candidate you dislike intensely and one you dislike a little, which
>one would you vote for?
>
>Dr. Paul R. Swank,
>Children's Learning Institute
>Professor, Department of Pediatrics, Medical School
>Adjunct Professor, School of Public Health
>University of Texas Health Science Center-Houston
>
>
>-----Original Message-----
>From: SPSSX(r) Discussion [mailto:[hidden email]] On
>Behalf Of Arnaldo Ferrari Nasi
>Sent: Wednesday, October 19, 2011 3:05 AM
>To: [hidden email]
>Subject: Re: A 4 point Likert scale
>
> >Here's my 2 cents' worth. My old mate Nick Moon (Head of Social and
> >Political Research at GfK/NOP) and other colleagues in the survey research
> >industry used to claim that there are only two answers to any question,
> >"Yes" and "No". Forget the statistical modelling: look at the questions.
>
>This is what I was just telling, no?
>Usually who works in private industry prefers striking yes/no, than
>theoretical models (also because they know how fields are done...)
>
>
> >Mind you, in all or most of the surveys I ever did, the attitude and
> >semantic differential scales had mid-points.
>
>Yes, but I prefer the other way:
>
>Some people likes Berlusconi, some other not.
>To whom do you feel nearest?
>
>1. like
>2. dislike
>3. DK
>
>;-) Arnaldo.
>
>
>
>
>
> >(See:
> >http://surveyresearch.weebly.com/ssrc-survey-unit-quality-of-life-in-britain
> >-surveys.html)
> >
> >
> >John F Hall
> >
> >[hidden email]
> >www.surveyresearch.weebly.com
> >
> >
> >
> >
> >
> >
> >-----Original Message-----
> >From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
> >Arnaldo Ferrari Nasi
> >Sent: 18 October 2011 09:30
> >To: [hidden email]
> >Subject: A 4 point Likert scale
> >
> >Hi, I did a certain number of "experiment" using Likert scales as an
> >ordinal or a continuous scale (this last is the forced assumption).
> >The results didn't differ so much. Or better, the help that the
> >results can give you to interpretate the social phoenomenon you are
> >studying is almost the same. So, I think that you can consider Likert
> >scales as continuous variables, doing, this way, statistical analysis
> >that in theory you could not do.
> >
> >Regarding 4, 6 or 7 point.
> >I am a Public Opinion Researcher, so I prefer eliminate the neutral
> >option and suggest the respondent to take positive or negative position.
> >In my experience the 4 point is better. The 6 points is often
> >difficult to interpret, often point 1 or 6 are residuals, and give me
> >too little cells in crosstabs (I usualy conduct 800/1000 cases
> >surveys). In 99% of times, I ask a 4 points, then I recode in 2
> >points (positive/negative) and I use this variable in double entry
> >crosstabs with other pos/neg.
> >I think that all depends with what kind of survey you will conduct
> >and what kind of use you do with.
> >
> >Hope it helps,
> >Arnaldo.
> >
> >
> >
> > >With what Art said in mind, if = you're desirous of eliminating the
> > >neutral option, a six-point scale is far = superior to a four-point
> > >scale. The research on Likert and Likert-type = scales is that most
> > >people can discriminate up to seven levels of response, so = you're
> > >safe with six.
> > >
> > >Brian
> > >
> > >Why do you want to use only a 4 point Likert = scale?
> > >_The more you restrict the variance of a variable the more you
> > >restrict = its possible covariance._
> > >As a rule of thumb you want items to approximate a continuous
> > >construct = as much as possible given who your respondents are.
> > >
> > >An actual Likert item has 5 points SD D ? A SA. Do you have a =
> > >Disagree to Agree construct for your response scale?
> > >
> > >If your scale has many items, the total (mean) score might not be
> > >too restricted.
> > >If you do not have scales, but are measuring a construct with a
> > >single = variable the restriction of variance and therefore on
> > >covariance is even more problematical.
> > >
> > >In short, a 4 point response scale is usually inadvisable. Why
> > >coarsen = your measurement any more than is really necessary?
> > >
> > >
> > >Art Kendall
> > >Social Research Consultants
> > >
> > >On 10/17/2011 1:13 PM, Mohamed wrote:
> > >
> > >Hi
> > >
> > >
> > >I intend to use a 4 point Likert scale format =
> > >in my survey.
> > >
> > >
> > >
> > >I want to know if this puts limitations on =
> > >the type of statistical =
> > >analysis
> >
> >=====================
> >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
>
>=====================
>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