At the end of this chapter you will be able to do the following.
Explain the steps in the research process.
Define and identify dependent and independent variables.
Calculate the mean, median, and mode of data.
Identify levels of measurement of variables.
Analyze ethical concerns in research.
One of the most remarkable traits that August Comte mandated for Sociology was a core of scientific rigor. He proposed the concept of positivism which is scientifically-based sociological research that uses scientific tools such as survey, sampling, objective measurement, and cultural and historical analysis to study and understand society. Although the current definition of positivism expands far beyond Comte’s original vision, sociological scientific methodology is used by government and industry researchers and across higher education and the private sector. Comte was originally interested in why societies remain the same (social statics) and why societies change (social dynamics). Most sociological research today falls within these broad categories. Sociologists strive for objectivity which is the ability to study and observe without distortion or bias, especially personal bias. Bias-free research is an ideal that, if not present, will open the door to extreme misinterpretation of research findings.
Sociology is both different from and similar to other scientific principles. It differs from chemistry, biology, and physics in that sociology does not manipulate the physical environment using established natural science theories and principles. It’s similar to chemistry, biology, and physics in that statistical principles guide the discovery and confirmation of data findings. Yet sociology has no universally social laws that resemble gravity or the speed of light. This is because chemistry, biology, and physics have the luxury of studying phenomenon which are acted upon by laws of nature. Sociologists study people, groups, communities, and societies which are comprised of agents (people who use their agency to make choices based on their varied motivations).1
THE RESEARCH PROCESS2
Problem Recognition and Definition
Researchers start with a question such as “What do I want to know?”; “What is important for society to know?”; or “Why does this occur?” Unfortunately some questions cannot be answered, such as “How many angels can dance on the head of a pin?” Even though many would like to know the answer to this question, it cannot be empirically observed; that is we cannot perceive it through one of our fives senses (empirical means we are able to perceive it through one of the five senses of sight, taste, touch, hearing, or smell). After a researcher decides on what question she wants to answer she must state her goals and objectives. Does she want to determine if religious service attendance causes couples to have happier marriages? Or does she want to describe the characteristics of happy marriages. The first one is a causal study (what causes what) and the second is a descriptive study. The next step is to conduct a literature review to establish what is already known about the topic. Why reinvent the wheel? If someone has already done research on the characteristics of happy marriages, why do you need to do that? But maybe the person before you only studied certain characteristics and you have thought of more that might be important. Much research in sociology builds on existing research. The research question is usually stated as a hypothesis. A hypothesis is the researcher’s educated belief about what she will find, such as “Those marriages that possess the most characteristics of happy marriages will be the happiest.”
Creating the Research Design
There are many different types of studies that can be conducted. The most common type in sociology is survey research. But there are also interviews, observation, action research, polls, and experiments, as well as others. One determinant of the research design is whether the researcher wants to describe some social phenomenon or determine if one phenomenon causes another phenomenon. Descriptive studies answer the questions of who, what, where, and when. Causal studies are undertaken to determine how one variable affects another, how and why. Back to our marital happiness study, do we want to describe the characteristics of a happy marriage? Or do we want to determine if the presence of many of the characteristics causes a happier marriage? In other words, how does presence of characteristics influence happiness?
Sometimes the entire population-the group you are interested in researching-can be studied. Often it is too large to study everyone. Think of a survey of all the students at College of the Canyons; that’s over 20,000 people. Do we really need to survey all of them? Can we realistically survey all of them? If we choose our sample-subset of the population– carefully it will reflect the characteristics of the population and the way the sample answers the questions will be representative of everyone in the population.
Sampling methods are classified as either probability or nonprobability. In probability samples, each member of the population has a known chance of being selected. Probability methods include random sampling, systematic sampling, and stratified sampling. In nonprobability sampling, members are selected from the population in some nonrandom manner. These include convenience sampling, judgment sampling, quota sampling, and snowball sampling. You will learn about all of these sampling methods in your research methods class. We will discuss only random and convenience sampling here.
In random sampling each member of the population has an equal chance of being selected. You need a list of everyone in your population to obtain a random sample. The easiest way to draw a random sample is to assign a number to each person in the population and then use a table of random numbers (you’ll learn about this in your research methods class) to select the subset (sample). Convenience sampling is used when you don’t have a list of everyone in your population so you choose participants because they are convenient to you.
Data Collection and Analysis
The next step is to collect your data by administering your survey, interviewing your subjects, or making observations. If you collect quantitative data-data that is, or can be converted to, numbers-you can enter it into a computer program, typically SPSS (you’ll use this in your statistics class). If you collect qualitative data-data that can’t be converted to numbers; data that is about the quality of something-you look for themes in the results.
Reporting the Results
The reason we do research is to expand the knowledge base and in order to do that we need to report our results. This is typically done via journals and conferences. Journal articles typically contain several sections: abstract, statement of the problem, methods used, results, discussion of the results, and references.
The analysis is the process through which large and complicated collections of scientific data are organized so that comparisons can be made and conclusions drawn. The study must show validity—the study must actually test what you intended to test. If you want to say one even is the cause of another, you will need to rule out other possibilities or explanations to show that your research is valid. For example if you want to prove that marijuana use leads to heroine use, you have to prove that there are no other contributing factors such as peer pressure or emotional or mental dysfunctions. The study must also demonstrate reliability—the ability to repeat findings of a research study. To demonstrate reliability we must demonstrate that the research process can be replicated with similar results.
SOCIOLOGISTS PERFORM SURVEY RESEARCH
Since by far the most common form of research in sociology is survey research, we are going to discuss how and when it is most useful. Sociologists study people who chose, decide, succeed, fail, harm others, harm themselves, and behave in rational and irrational ways. If you took an ounce of gasoline and placed a burning match upon it, the gas would have to burn. The gas has no choice just as the flame has no choice. But, if someone placed a burning match on your arm, or the arm of your classmate, you or they might respond in any number of ways. Most would find the experience to be painful. Some might enjoy it, others might retaliate with violence, and yet others might feel an emotional bond to the one who burned them. Sociologists must focus on the subjective definitions and perceptions that people place on their choices and motivations. In general surveys are research instruments designed to obtain information from individuals who belong to a larger group, organization, or society. The information gathered is used to describe, explain, and at times predict attitudes, behaviors, aspirations, and intended behaviors. Surveys are easily used to collect information about political views, social and religious opinions, demographic information, past or expected future behavior, and even marital happiness and characteristics such as communication style, level of commitment, and fidelity.
Polls are typically surveys which collect opinions, such as who one might vote for in an election, how one feels about the outcome of a controversial issue, or how one evaluates a public official or organization. Surveys can be administered once (cross-sectional). Or they can be administered at two or more times (longitudinal).
If you administer your survey and get a good response rate–the percentage of people who complete your survey–you can generalize your results to the entire population. Generalizability means that the results from the sample can be assumed to apply to the population as though the population itself had been studied.
Also important is the quality of the survey itself as a scientific instrument. Valid survey questions are questions that are accurate and measure what they claim they’ll measure. For example let’s say we wanted to know how students feel about a Lacrosse team at College of the Canyons. Which statement should we ask them about their agreement to? 1. “Every campus needs a Lacrosse team” or 2. “College of the Canyons would benefit from a Lacrosse team.” The first asks about all campuses, not specifically this one. It’s seeking an opinion about campuses and Lacrosse teams in general. The second asks specifically about this campus and is a valid measure of what we want to know. Reliable questions are questions that are relatively free from bias errors which might taint the findings. In other words, reliable survey questions are consistent and if I ask a similar group of people the same question I will get similar results.
There are 2 types of survey questions: Open-ended questions are questions designed to get respondents to answer in their own words (e.g., “What might be the benefits of having a Lacrosse team?”_______________ . Closed-ended questions are questions designed to get respondents to choose from a list of responses you provide to them (e.g., “Are you married?” Yes or No.) Likert scale questions are statements which respondents are asked to agree or disagree with. They are the most common types of questions used in surveys (e.g., “How much do you agree that the president is doing a good job of running the country?” Strongly Disagree, Disagree, Neither Agree nor Disagree, Agree, Strongly Agree). Demographic questions are questions which provide the basic categorical information about respondents such as age, sex, race, educational level, marital status, etc.
Levels of Measurement
Nominal level data is data with no standard numerical values. This is often referred to as categorical data (e.g., What is your favorite type of pet? __Reptile __Canine __Feline __Bird __Other). There is no numerical value associated with reptile that makes it more or less valuable than a canine or other type of pet. Other examples include sex, favorite color, or town you grew up in.
Ordinal level data is categories with an order to them. One category is more of something than another category. For example height measured as short, medium, and tall is ordinal because medium is more height than short and tall is more height than both short and medium.
Interval level data is categories with an order, but we add standard numerical values with regular intervals. If we measure height in feet and inches we have interval data. A height of 5 feet, 3 inches is 8 inches away from 5 feet, 11 inches. Each of those 8 inches has the same value, the intervals are identical. Five feet, 3 inches is one of the categories, but in this case the categories are numbers. The Fahrenheit temperature scale is an example of an interval scale. The difference between 68 degrees and 72 degree is the exact same four degrees as the difference between 101 degrees and 105 degrees.
Ratio level data adds a real zero starting point for the numerical values. We can create ratios with ratio level data. With ratio data we can say that someone who has two children has twice as many children as someone having only one child, and someone having four children has twice the children of someone who has just two children, and the person with four children has four times the number of children as the person with only one child. Ratio data is used to compare to other data. For example, the sex ratio is the number of males per 100 females in a society. In 2006, the sex ratio for Alaska, Rhode Island, and the U.S. was Alaska 107; Rhode Island 93.6, and U.S. 97.1.3 We can say that Alaska had more males than females (107 males per 100 females) while Rhode Island had more females than males (93.6 males per 100 females). The U.S. overall has more females than males (97.1 males per 100 females).
Number of males and females, opinions about a Lacrosse team, marital happiness, height, and sex are variables. Variables vary by respondent (one is male, the next is female, the next is female, etc.). Sex is the variable and male or female are the attributes, or the possible choices. Everyone in your class is human, so humanness is not a variable—it doesn’t vary. But almost everything else you can observe is a variable.
Two types of variables are dependent and independent variables. Dependent variables change in response to the influence of independent variables; they depend upon the independent variables. Independent variables are variables that when manipulated will stimulate a change upon the dependent variables. If I know the independent variable can I predict what the dependent variable will be? If I know that you possess many of the characteristics of happy marriages can I predict your level of happiness? Yes. That doesn’t mean that everyone with many of the characteristics will be the happiest, but more often than not, they will be. So possession of characteristics is the independent variable and happiness is the dependent variable. How happy you are depends on how many of the characteristics you possess.
Is this a causal relationship or merely an association or correlation? A causal relationship is when one variable actually causes the other to occur, such as eating lots of Krispy Kreme donuts causes you to gain weight. That’s pretty clear, but in sociology most relationships are not that clear. Do I know for certain that possession of many of the characteristics that are found in happy marriages causes a marriage to be happy? No. What if there is something else that is causing both happiness and possession of characteristics? Maybe it’s religion or optimistic personality or something else. If this is true then this is an association or correlation. They go hand in hand, but one does not cause the other.
When basic statistics are performed on data, we call them measures of central tendency (mean, median, and mode). Consider this list of numbers which represents the number of movies that nine students have seen in the last two weeks: 0, 1, 1, 1, 3, 4, 4, 5, 8.
The mean is the arithmetic score of all the numbers divided by the total number of students (i.e., 27÷9=3). The median is the exact mid-point value in the ordered list of scores (e.g., 0, 1, 1, & 1 fall below and 4, 4, 5, & 8 fall above the number 3 thus 3 is the median). The mode is the number which occurs most often (e.g., 1 occurs the most, so the mode is 1). The extreme values or outliers are the especially low or high number in the series (e.g., 8). Notice that if you removed the 9th student’s score and averaged only the remaining scores the mean would be 2.375. Extreme values can increase or decrease the mean. You will cover these basic and more interesting statistics in your statistics class.
ETHICS OF RESEARCH
Ethics are standards of what is right and wrong . They are a general agreement shared by researchers as to what is proper and improper in scientific research. Our culture and sociology have ethical standards that may be different from other disciplines or other cultures. Standards may arise from religious, political, or pragmatic sources. Standards differ over time, for example long ago we didn’t have formal considerations about how to treat people who participate in scientific studies.
There are four major ethical issues that protect research subjects: 1.) Voluntary participation means that subjects must participate voluntarily, they must understand the risks of participating, and they must be able to withdraw from the study at any time. 2.) Researchers can do no harm to participants. This includes anything from killing someone to causing them undue stress. 3.) Every study must be confidential which means that the researcher can never divulge the participants’ identities. Some studies are anonymous which means the researcher does not know the participants’ identities. 4.) Deception cannot be used to get people to participate in research they would not want to participate in.
To be sure subjects know what they are getting into when they agree to participate in a study they sign an informed consent form which tells them the general purpose of the study, explains their right to withdraw, explains the confidentiality of the study, tells whether it is anonymous, explains the potential risks, and describes how to contact the researcher.
You can probably think of times when it would be necessary to deceive a subject or when you might need to cause just a little stress to investigate something. Of course there are exceptions, but we’ll leave that to your research methods class.
One of the largest social surveys taken in the United States has been the General Social Surveys collected almost every year since 1972. It has provided 27 national samples with over 50,000 survey takers and thousands of variables as of 2008.4 These large volumes of data and variables allow researchers to study the family at a scale that most could never attain if left to fund and collect the data for themselves.
In Great Britain the Family Resource Survey began in 1992 and has provided much needed insight into the needs and functioning of these families.5 In China, a U.S. team of researchers performed a survey research study called the National Health and Nutrition Survey.6 Numerous family and health data were collected for study. In Iraq, a medical family survey was conducted by the World Health Organization and Iraqi officials wherein over 9,000 households were surveyed.7 The focus here was on the ravages that the ongoing war had taken on families and social networks.
Clinical observation studies typically take place in counseling, medical, residential treatment settings, or community centers. Perhaps two of the most prominent clinical researchers of the family have been Judith Wallerstein and John Gottman. Dr. Wallerstein studied children of divorce over the course of 25 years and has made a thorough study of the impacts that divorce has had on these children and their adult marriages and life experiences.8
Dr. Gottman studied couples in depth by videotaping them in clinically controlled apartments “love labs” where he observed their daily interaction patterns and carefully analyzed the footage of their interaction patterns. His research lead to the “Four Horsemen of Divorce” and the classification of four aspects of deeply troubled marriages: Defensiveness, Stonewalling, Criticism, and Contempt.9
Participant observations are much less common than surveys and clinical studies. They basically are studies where the researcher lives in, belongs to, or participates in the very social familial experience that is being studied.
The National Survey of Families and Households was collected in the early 1990s where 13,000+ families were interviewed in depth for survey information. This massive data set now exists in electronic form and can be analyzed by anyone seeking to look at specific research questions that pertain to many different aspects of the family experience in the U.S. at that time. When a researcher analyzes existing data it is called secondary analysis. This would apply to a research examining any of the above mentioned surveys, the U.S. Census, or even the Population Reference Bureau’s world data.10
Finally, family members can be interviewed through in-depth qualitative interviews designed to capture the nuances of their experiences. This is what Dr. Judith Wallerstein did when she wrote the book, The Good Marriage (1995). She carefully interviewed 50 happily married couples that were considered by those around them to have a really good marriage. Her work was published in an era of family research that was flooded with studies about divorce and family dysfunction. The Good Marriage began a turn of events that made it more acceptable to study the positive functioning and side of family experiences in the U.S.
- Google Anthony Giddens-human agency, January 18, 1938 British Sociologist.
- ds_name=ACS_2005_EST_G00_&-_lang=en&-format=US-30) 5 February, 2009.
- see http://en.wikipedia.org/wiki/General_Social_Survey retrieved 5 February, 2010
- http://www.natcen.ac.uk/ for family research studies online.
- retrieved 5 Feb., 2009 from http://en.wikipedia.org/wiki/China_Health_and_Nutrition_Survey
- see http://en.wikipedia.org/wiki/Iraq_Family_Health_Survey
- see research-based books: The Good Marriage (1995 HM); Second Chances: 1996 HM); Surviving the Breakup (1996 HC); and the Unexpected Legacy of Divorce (2000H)
- see research-based books: The Relationship Cure (2002 TRP); Why Marriages Succeed or Fail (1995 FP); Seven Principles (2007 TRP); and Ten Lessons to Transform Your Marriage (2007 TRP).