Sociologist claim their knowledge of social behavior comes from using scientific methods. To understand why we reach the conclusions we do about social phenomena, you need a basic understanding of how we go about our work.
The ultimate goal of science is to describe reality. The scientific method isn't so much about what we know (or don't know) but how we know we know. The basic strategy of science is to compare theory and data.
The process is often described as circular and ongoing. New data can modify our theory. Likewise, theory can make new observational (data) predictions which can then support, modify or refute the theory. And so on.
In this class, we use a rather general definition of theory. Basically, theory is a linguistic description of reality. We use words and pictures to describe how the world fits together and works. We might have a theory that the world is flat and held up by a six legged tortoise (we all know a four legged tortoise would not be strong enough to hold up the entire world). There are likely to be several theories trying to describe and explain the same phenomena.
Scientific theories are based on numerous statements about reality. These statements must be internally consistent and obey the rules of logic and mathematics. Scientific theories generally include both qualitative and quantitative concepts. In the words of the late Carl Sagan, "If you know a thing only qualitatively, you know it no more than vaguely. If you know it quantitatively - grasping some numerical measure that distinguishes it from an infinite number of other possibilities - you are beginning to know it deeply. You comprehend some of its beauty and you gain access to its power and the understanding it provides. Being afraid of quantification is tantamount to disenfranchising yourself, giving up on one of the most potent prospects for understanding and changing the world." (Billions and Billions, page 21)
Science requires that we test our theories by comparing them to empirical observations or measurements. Thus a theory that planets revolve about the sun and moons revolve about planets is confirmed by observing and measuring such movements. Similarly, social science theories that predict unmarried individuals will commit suicide more frequently than married individuals would be tested using data on suicide rates and marital status.
While we all observe and measure the world in our everyday lives, scientists are noted for taking extraordinary care. We want our observations to be as valid and reliable as possible.
Validity refers to the closeness of fit between our theoretical concept and the way we measure it.
Reliability refers to the consistency of the measurement.
Research designs - Social scientists usually use one of three research designs - experiments, surveys or case studies.
Experiments - the key to an experimental design is that the researcher assigns the value to the independent variable. The dependent variable is usually measured using observations or questionnaires. These studies usually measure a small number of variables and rarely manipulate more than two. Most often only one variable is manipulated. Random assignment of cases to experimental groups is important.
Surveys - a survey measures one or more variables from a population of cases. All variables are measured as compared to manipulated. If all cases in the population are not measured, random sampling of cases will generate the most representative sample. Surveys often measure a large number (sometimes hundreds) of variables.
Case studies - researchers use case studies when they are interested in studying one case in depth. The case can be an individual, an organization or an event.