Joseph Nathan Cohen

Department of Sociology, CUNY Queens College, New York, NY

What is Measurement?

A brief introduction to the topic of measurement

To see more about the “Teaching through YouTube” series.  For more, see this post.

Original Video Description

A look at measurement’s role in the research process

Transcription (Auto-Generated)

Science involves recording information about what we observe in the world around us and then using that information to try to figure out what has happened is happening or will happen in the future if we don’t record our observations properly then it’s hard to use these records to make inferences in this video I describe the topic of measurement in research design I’ll explain what’s involved in forming formulating a measurement strategy and why this phase of developing a research project matters let’s begin by reviewing how measurement fits into the larger scheme of conducting scientific research Theory science generates and tests theories a theory is an explanation of how the world works and it has two parts it has concepts which are ways that we describe or categorize people or things around us and relationships which are links between concepts in relationships we postulate that the presence or absence of one concept will influence the presence or absence of another let’s try to be more concrete religiosity is an example of a concept it classifies people according to the degree to which religion is central to the way they think and behave we use the concept of religiosity to classify people into groups perhaps those who are very invested in religion those who are mildly invested in it and those who aren’t invested in religion at all another example is the concept of criminality it’s a concept in which we categorize people according to the degree to which they are willing to break the law we use this concept to categorize people as well we might divide them into people who have a high willingness or tendency to break laws and those who are unwilling to do so theories are concepts linked by relationships so for example we might theorize that the degree to which someone is religious affects the degree to which their criminal if the relationship between religiosity and criminality is negative in other words as one becomes more religious one becomes less criminal then we’d expect religious people to be less likely to break the law and non-religious people to be more likely to break the law now a Measurement theory without evidence is little more than a guess it’s not scientific to test this theory scientifically we have to find a way to figure out who’s more or less religious and who’s more or less criminal and then see if the people who are more religious are less criminal and the people who are less religious are more criminal this recording process is called measurement when we measure we keep records of our subjects thoughts behaviors or personal characteristics we look for relationships between these measurements to see if relationships exist so in this particular example developing a measurement scheme involves figuring out a way to determine whether or not someone is more or less religious and more or less criminal how could we do it if we were conducting this study using a survey which is not necessarily the best way to do it we might ask our respondents directly are you religious or are you criminal the problem with asking questions directly is that people might have an inaccurate view of themselves that might over or underestimate the degree to which they’re religious and they would probably underestimate the degree to which their criminal wanted to get around this problem we might ask people to report events in their past instead of making global assessments of their character or lifestyle for example instead of asking how religious are you we might ask how often do you attend religious services and assume that people who go to religious services more often are more religious likewise instead of asking are you criminal we might ask how often have you been arrested or have you ever been arrested and presume that people who’ve been arrested are more criminal now these strategies have weaknesses of their own and all strategies that collect information like this through surveys have to deal with the problem that respondents might report inaccurate information they might lie or they might have personally distorted information in their own minds and are conveying that distorted worldview back to you we could use other types of questions or we might use a different method for collecting data for example I might go visit some star sleep Pro and anti-religion people and have extended discussions with them I could take detailed and extensive notes which try to capture the many things that were said or things that I saw that could help me put together a larger picture of the complex relationship between religion and criminality the pitfalls here are that it would be hard for someone else to check my work and there’d be lingering questions about whether or not I was seeing my subjects as they really were or looking at them in a way that the more strongly reflects my personal biases than what these people objectively think or do whether we’re talking about survey questions and quantitative research or note-taking strategies and qualitative research researchers have to figure out a way that they’re going to take information about what they observe and put them into records this process of record taking and classification is known as a measurement strategy my main point in this video is that measurement is not simple often when students get a research project they think that they have a pretty good handle on the questions that they want to ask and they go right to drafting up a survey and then come up to me and ask if they can start collecting data running through that process is dangerous there are lots of pitfalls that you can fall into when you’re developing a measurement strategy so it’s important that you do it carefully and with the cognizance of the strengths and the weaknesses of the method that you choose