[Music] researchers in the psychological science conduct studies with one of three goals in mind describing behaviors examining the relationships between behaviors and examining how different variables impact behaviors which question a researcher wants to answer will determine which research methods they choose to use if we are interested in describing behaviors we would use descriptive research including case studies naturalistic observations and survey research case studies examine a single person or group in detail over a period of time case studies like this provide researchers with a ton of detail about a specific person or condition and can give them insight that lets them develop broader studies but it also has some downsides case studies typically focus on a person who is a rare characteristic and that can make it hard to generalize or apply any findings to other people naturalistic observation involves directly observing natural behavior in real-world environments without interacting with the participants for example if you wanted to learn more about childhood bullying you might observe children on a playground naturalistic observation has a lot of advantages being able to document people's authentic behavior and not meaning to worry about how you the experimenter might be influencing the behavior you are trying to observe but it also has a number of disadvantages for example observation alone is not enough to understand why people behave the way they do in our example we wouldn't know anything about what led to the bullying behavior we saw on the playground or why some students bully others or who is likely to become a victim of bullying in the future in survey research participants answer questions about their behavior attitudes and feelings this could be through a questionnaire or one-on-one interviews or focus groups this is particularly useful when researchers want to measure mental states and behaviors that they can't directly observe like why students drink coffee or how old they were when they had their first delicious cup but this strategy has a few disadvantages unlike naturalistic observation the people who are taking the survey know that they are being studied and that may make them less willing to answer honestly especially when asked about sensitive topics like sexual behaviors they might feel uncomfortable giving this information even if it is being given anonymously people can also be easily influenced by the wording of a question like do you believe in ghosts is going to get a very different response then do you believe in life after death but what if I wanted to look beyond just describing behaviors and wanted to know more about the relationships between them in this case we would use correlational research a type of methodology that provides us with information about the strength and direction of a relationship between variables like the relationship between time studying and final grades correlational research can be conducted using some of the same strategies we have seen before such as surveys but the difference in this case is that researchers are measuring two variables and then using them to calculate a statistical component known as the correlation coefficient which is written as a numerical value between negative 1 and positive 1 this number will tell us the strength in the direction of the relationship a positive value means the two variables are positively correlated as the value of one variable increases so does the other for example agent height are positively correlated in children a negative value means that the two variables are negatively correlated as the value of one variable increases the value of the other variable decreases for example as a person ages their agility tends to decline the closer the correlation coefficient is to either negative 1 or positive 1 the stronger the relationship between variables a correlation coefficient of zero indicates that no relationship exists between the variables but importantly correlation doesn't tell us anything about what causes what which is often summarized as correlation does not imply causation if smoking and lung cancer are positively correlated then there's only one possible direction for that relationship to go but what about a positive correlation between stress and depression does one cause the other or is there maybe a third factor that could be causing both of them in order to say anything about causality we need to use experimental research which requires things like random assignment of participants to experimental and control conditions and allows us to draw conclusions about the causes of events experimental research focuses on the relationship between independent and dependent variables the independent variable is the variable that researchers change or manipulate in the experiment the dependent variable is the variable that is being measured by the researcher it depends on the independent variable so if we were testing the effectiveness of medication on stopping smoking the independent variable would be whether they got the medication or not and the dependent variable could be how many cigarettes they smoked before and after they took the medication the independent variable is often specified using experimental and control groups where the experimental group is the group containing participants who receive treatment or participate in an experimental condition and the control group is the group containing participants who do not receive treatment will participate in the experimental condition in order to make sure that the experiment is accurate researchers use random assignment to determine which participants will be placed into experimental or control groups random assignment is a process in which each participant has an equal chance of being placed in either the experimental or the control group this is done to minimize the impacts of confounding variables uncontrolled factors that researchers did not account for in the study but that could influence study outcomes if this seems like a lot to take into account it is the high level of control and experiments allows researchers to draw conclusions about cause and effect but because it is so controlled it may not marry the real situation that they are trying to study although there are differences between these methods they all have a number of things in common first they all require that researchers come up with operational definitions of the variables that they want to study an operational definition is the specific description of how a variable will be measured as determined by the researcher this is important because a lot of the questions we might have about behaviors are generally too vague or open-ended to be useful to researchers so instead of measuring sleep deprivation I need to say less than four hours of sleep at night however you measure it you need to be sure that you clearly communicate what definition that you are picking so that other researchers are clear about what your study measured [Music]