The Likert scale is commonly used in survey research. It is often used to measure respondents' attitudes by asking the extent to which they agree or disagree with a particular question or statement. There are many different scales in use. The Likert scale is common rating format.nly used in survey research. Respondents rank their attitudes, preferences, expectations and quality of a product or life as part of a greater survey from high to low or best to worst using five or seven levels.

Likert scales are typically multiple-choice questions with five responses, ranging from "Strong Affirmation” to "Strong Negation." Likert scales may vary in the number of points in the scale. Generally five-point is the most common, but some Likert scales have 4-point response scales, eliminating the not sure/undecided/average category. Some even have 7-point response scales.

Likert scaling is a bipolar scaling method, measuring either positive or negative response to a statement. Sometimes a four-point scale is used; this is a forced choice method as the middle option of "Neither agree nor disagree" is not available.

Likert scales may be subject to distortion from several causes. Respondents may avoid using extreme response categories (central tendency bias); agree with statements as presented (acquiescence bias); or try to portray themselves or their organization in a more favourable light (social desirability bias).

Likert scales are generally considered arbitrary. For, score given to a Likert item has no objective basis form measurement theory nor from the view of scales of measurement as distances between two scores of an individual cannot be determined. Though, scholars use these scores as measured on ordinal scale, however, as referred above it is difficult to say that distance between each successive item category is equivalent, which is inferred traditionally. For example, 5>4>3>2>1, but in Likert scale it cannot be concluded that responses A>B>C>D because it is quite likely that A>B, but C>B.

Therefore, to be on the safe side, Likert are converted into Rasch measurement, if data from Likert scale have been thoroughly checked to fulfil the strict formal axioms of Rasch model to obtain interval level estimates.

However, this exercise needs expertise. Generally, researchers, despite disagreement, treat Likert score as ordinal in principle. As such, Likert scalar data could not be subjected to parametric analysis but should rely on the ordinal nature of the data. When treated as ordinal data, Likert responses can be collated into bar charts, central tendency summarised by the median or the mode, dispersion summarised by the range across quartiles, or analysed using non-parametric tests, e.g. chi-square test, Mann–Whitney test, Wilcoxon signed-rank test, or Kruskal–Wallis test. Parametric analysis of ordinary averages of Likert scale data is also justifiable by the Central Limit Theorem, although some would disagree that ordinary averages should be used for Likert scale data. Each item may be analysed separately or in some cases item responses may be summed to create a score for a group of items. Hence, Likert scales are often called summative scales.

I would use a 5 point Likert Scale. Easy to interpret and to analyse the information you gather. Also, if you don't have any information about that issue, maybe an open question wouldn't be a bad idea.

The Likert scale is commonly used in survey research. It is often used to measure respondents' attitudes by asking the extent to which they agree or disagree with a particular question or statement. There are many different scales in use. The Likert scale is common rating format.nly used in survey research. Respondents rank their attitudes, preferences, expectations and quality of a product or life as part of a greater survey from high to low or best to worst using five or seven levels.

Likert scales are typically multiple-choice questions with five responses, ranging from "Strong Affirmation” to "Strong Negation." Likert scales may vary in the number of points in the scale. Generally five-point is the most common, but some Likert scales have 4-point response scales, eliminating the not sure/undecided/average category. Some even have 7-point response scales.

Likert scaling is a bipolar scaling method, measuring either positive or negative response to a statement. Sometimes a four-point scale is used; this is a forced choice method as the middle option of "Neither agree nor disagree" is not available.

Likert scales may be subject to distortion from several causes. Respondents may avoid using extreme response categories (central tendency bias); agree with statements as presented (acquiescence bias); or try to portray themselves or their organization in a more favourable light (social desirability bias).

Likert scales are generally considered arbitrary. For, score given to a Likert item has no objective basis form measurement theory nor from the view of scales of measurement as distances between two scores of an individual cannot be determined. Though, scholars use these scores as measured on ordinal scale, however, as referred above it is difficult to say that distance between each successive item category is equivalent, which is inferred traditionally. For example, 5>4>3>2>1, but in Likert scale it cannot be concluded that responses A>B>C>D because it is quite likely that A>B, but C>B.

Therefore, to be on the safe side, Likert are converted into Rasch measurement, if data from Likert scale have been thoroughly checked to fulfil the strict formal axioms of Rasch model to obtain interval level estimates.

However, this exercise needs expertise. Generally, researchers, despite disagreement, treat Likert score as ordinal in principle. As such, Likert scalar data could not be subjected to parametric analysis but should rely on the ordinal nature of the data. When treated as ordinal data, Likert responses can be collated into bar charts, central tendency summarised by the median or the mode, dispersion summarised by the range across quartiles, or analysed using non-parametric tests, e.g. chi-square test, Mann–Whitney test, Wilcoxon signed-rank test, or Kruskal–Wallis test. Parametric analysis of ordinary averages of Likert scale data is also justifiable by the Central Limit Theorem, although some would disagree that ordinary averages should be used for Likert scale data. Each item may be analysed separately or in some cases item responses may be summed to create a score for a group of items. Hence, Likert scales are often called summative scales.

Dear Naira, I think the response format, discussed above, does not answer your question. I suggest you have a look into the World Value Survey.

Dear Naira,

I'm not sure I understand exactly what you are attempting to assess: What the world's social expectations are of an adult? Or... An adult's social expectations of the world around him/her?

Some scales available are:

The Social Responsiveness Scale, 2nd Ed.

This scale is primarily designed to identify autistic like symptoms within the social realm. However, the 'norm' of such a scale would then be 'average' social behaviors.

Adaptive Behavior Assessment System - 2nd Ed.

This scale measures current adaptive and functional behaviors of an individual against the 'normative' populations. Social behaviors are a subscale on this instrument.

There are many other categories of social/emotional/behavioral type assessment instruments. However, they are fairly specialized. As such, my first question of what exactly are you attempting to measure?

I hope this is at least somewhat helpful. I hope you find what you are looking for.

I would define the research variables re: the concepts represented in your question. Your question describes the phenomena or characteristics of your interest in the study. Describe the phenomena or characteristics in a way that they can be measured, e.g., a response, a perception, or behavior. Then develop your conceptual definitions and operational definitions. Once this is done, go ahead and define data collection procedures. Since no known instruments already exist to measure your phenomena, do a small pilot study with 30 to 40 subjects. The results of this should tell you that the instrument you developed can be used for a larger study. Make sure you look at reliability results for the study, e.g., correlation coefficients. What you are doing is instrument development. After the pilot study and refinement of the instrument, do a larger study and use factor analysis to determine the true correlation among the variables. Too, before the pilot, have face validity done by some experts in your field to make sure the items measure what your after.

Thank you for your answers and advice, they are all helpful for me.

Marianne Törner, The WVS you mentioned above is very large project, but it is focused on changing values and their impact on social and political life. The values and expectations certainly related to each other, The question is that I can`t find their questionnaire samples.

Pedro Simão and Mohammad Firoz Khan the Likert scale is more consistent for my research, thank you for your advice.

William Whetstone, the process you have described in your answer is what I am doing in this period of time, My survey is now in approbation phase and I am wondering is there any analogue to compare with mine.

Scubby Mack I probably could not explain clearly what I want and seeking. My research interests are focused on the expectations of adults,i.e. what they expect in the future from different fields of life, eg school, work, friends, from ourselves, and so on.

Naira, you mentioned that your proposed study is in the approval stage. By whom? Off hand, I don't know of any analogue. I suggest you do an search on PubMed, Medline, and PsychINFO to see if you can come up with an analogue comparison. Otherwise, look at it this way, your breaking new ground by doing instrument development for a scale you could name yourself, e.g., The Naira Social Expectation Scale for Adults, etc. Good to hear that your making progress. Stick with it.

Another approach you can take for future development of your study, do a small qualitative study. Do a focus group with adults, find out what their social expectations might be after your data analysis. Some researchers will do this to help in developing an instrument to measure their perceptions. Qualitative studies answer the lived experience by adults related to their social expectations. I hope you have narrowed down the conceptual/operational definitions of adult social expectations. By itself, the concept is broad. Is there a particularized aspect of adult social expectations your trying to get at. As a side bar, I was in your neck of the woods in 2010. Sad how the Soviets just picked up and left in 1991 leaving buildings unfinished et al. Armenia is an interesting country.

Thank you Naira,

Great ideas have been presented here. Since it appears that there is no known norm referenced survey meeting your criteria, William's methodology presents significant insight into how to develop your own assessment instrument to glean the evaluative information you seek. I think that in your answer to my request to more clearly define what it is you are attempting to assess, you have started the process of drafting your own assessment instrument. In your response to me you stated: "My research interests are focused on the expectations of adults, i.e. what they expect in the future from different fields of life, eg school, work, friends, from ourselves, and so on." As such, you have delineated the major category sections of your survey. Now, devise questions for each category. Those questions can either have multiple choice answers for the client to chose from, True/False answers, or fill in the blank type responses. A sample question might be: "I expect government to take care of my needs whether I choose to work or not.... T - F." Next, distribute your survey to a variety of selected sampling of adults (gender, age range, race, ethnicity, etc.). Then compile your results to create a 'normal' range of responses against which future survey takers responses can be compared.

Best wishes in your future endeavors.