Just one question: If one question works, why ask several?
While shorter instruments are more limited than longer measures, they have obvious benefits for both research and policy in terms of reduced burden and costs, and ease of interpretation.
A frequently asked question by clinical investigators is why they should use a lengthy, multi-item measurement scale to assess patients’ perceptions of their health, or quality of life, when there is evidence that a measure containing a single, global question is likely to suffice. Researchers may not wish to use lengthy scales because their core questionnaires are already long, the patient group of interest is ill or frail, they wish to minimise the burden on the patient and on the research team, or they simply want a “snap shot” of a topic rather than comprehensive coverage. In such circumstances, single questions have the obvious advantage of brevity, of making fewer demands than multi-item measures on respondents and researchers. Single, global questions have long been used in population surveys to measure health status, quality of life (QoL), and health related quality of life (HRQoL). The two most popular single global health items are self rated health status and self reported limiting, longstanding illness.
Well, honestly said, it is not one question which measures a variable, but rather the answer to that question. The question is to be ver well set out, of course.
A simple answer to a question can be either yes versus no, ignoring 'yes' but..... or 'no' but? The question therefore has to be very precise, e.g. do you wish to participate at an event?
Variables are defined by both model (concept) and operation (mode of measurement). All research questions have a dependent variable. However, sometimes a research question is not simply interested in measuring the dependent variable in its entirety, but a particular component of the dependent variable. So, how the dependent variable is written out in a research question and what you call it are often two different things. I agree with Dear Carlos - "not one question which measures a variable, but rather the answer to that question."
Just one question: If one question works, why ask several?
While shorter instruments are more limited than longer measures, they have obvious benefits for both research and policy in terms of reduced burden and costs, and ease of interpretation.
A frequently asked question by clinical investigators is why they should use a lengthy, multi-item measurement scale to assess patients’ perceptions of their health, or quality of life, when there is evidence that a measure containing a single, global question is likely to suffice. Researchers may not wish to use lengthy scales because their core questionnaires are already long, the patient group of interest is ill or frail, they wish to minimise the burden on the patient and on the research team, or they simply want a “snap shot” of a topic rather than comprehensive coverage. In such circumstances, single questions have the obvious advantage of brevity, of making fewer demands than multi-item measures on respondents and researchers. Single, global questions have long been used in population surveys to measure health status, quality of life (QoL), and health related quality of life (HRQoL). The two most popular single global health items are self rated health status and self reported limiting, longstanding illness.
Most of scientific problems depend on a lot of parameters as well as the results and answers. I think we need very precise questions with clear definitions, not only one variable.
However, most classical research involves questions/hypotheses that entail looking at relationships between at least two variables. But here are some common situations where you want to look at graphs and descriptive statistics for cases on one variable:
Some variables can be measured with just one question. Take, for example, the widely used single question to measure Interpersonal Trust, which was devised by Elizabeth Noelle-Neumann in 1948 and has been applied since then:
"Generally speaking, would you say that most people can be trusted or that you can't be too careful in dealing with people?"
This is a dichotomous variable: Most people can be trusted / Can't be too careful.
When the variable is multidimensional, however, we need more than one question. An example is Socioeconomic Status (SES), which includes at least education, income and occupation.
Sometimes, although we can measure a variable with just a single question, it may be preferable to use two or more items, because this improves reliability.
If the variable is a simple fact, then a simple question will do : "do you have a fulltime working contract ?", "did you ever get epidural anesthesia ?". If the variable envolves some kind of evaluation then a simple question won't do : "are you a safe driver ?".
I believe, we may use one question with a variable and some statistical analyses can be performed. At the same time, some other statistical analyses are difficult to be utilized such as factor analysis and structural equation modeling.
there are lot of research studies that have measured a variable with one question only e.g. job satisfaction, . But response to one variable construct is not taken as reliable especially in behavioural sciences
The questionnaires questions must past through "the filter question", that make the researcher think about the variables and the aspects of his research.
I have read all answers to your question on what was the Maximum Number of Items that a Construct could have. The question and its answers were very useful and interesting.
Regarding Hinkin`s (1995) statement that scales with too many items can create problems with respondent fatigue or response biases. I agree with the first part regarding creating problems with respondent fatigue, but, I would like to say that one question, and not too many questions, can cause response biases.
The variable is measured with the observation or response to the question. If we know the response to the question in all the population units, we know the searched variable.
Since factor analysis is a statistical procedure that is conducted to identify groups of related items, do we have to consider factor analysis output in this regard?
Why not, its depend on researcher need. If researcher achieve objectives and goals with one question or variable surely he can do it. Ex. In satisfaction survey salary or reward for work one gets from his work.
A variable can be measured with correction with the true answer to a question. If the answer is not true, the measure would be incorrect and would not serve to measure the variable in truth.
Human creativity has no limit.Why not a a single question to measure a variable ? The answer may be yes or No or similar to that, when the question leaves nothing to imagination!