Chapter 13 The Descriptive Research Strategy PDF

Preview

Summary

Chapter 13 notes from the course Experimental Psychology taught by Professor Freer. ...

Description

●

●

●

An Introduction to Descriptive Research ○ Descriptive research typically involves measuring a variable or set of variables as they exist naturally. ○ The descriptive strategy is not concerned with relationships between variables but rather with the description of individual variables. ○ The goal is to describe a single variable or obtain separate descriptions for each variable when several are involved. ○ The first step in understanding a new phenomenon is to gain some idea of the variable interest as it naturally exists. ○ Three descriptive research designs are considered: ■ Observational research ■ Survey research ■ Case study research ○ In the observational research design, we describe observations of behaviors as they occur in natural settings. ○ In survey research design, we describe people’s responses to questions about behavior and attitudes. ○ In case studies, we describe a single individual in great detail. The Observational Research Design ○ In the observational  research design, the researcher observes and systematically records the behavior of individuals for the purpose of describing behavior. ○ As a measurement technique, behavioral observation can be used in a variety of research strategies including experimental and correlational designs. ○ A study using behavioral observation simply for descriptive purposes is classified as an observational research design. Behavioral Observation ○ The process of a behavioral  observation simply involves the direct observation and systematic recording of behaviors, usually as the behaviors occur in a natural situation. ○ This measurement technique, however, introduces two special measurement problems. ■ Because the goal is to observe natural behavior, it is essential that the behaviors are not disrupted or influenced by the presence of an observer. ■ Observation and measurement require at least some degree of subjective interpretation by the observer. ● If we observe two preschool children bumping into each other, we must decide whether the contact was accidental or deliberate, and if it was deliberate, which child initiated the contact and whether it was aggression or simply play.

○

○ ○

○

○ ○

○ ○ ○ ○

○

○

The first problem can be addressed by concealing the observer so that the individuals do not know that their behaviors are being observed and recorded. Habituation r equires repeated exposure until the observer’s presence is no longer a novel stimulus. To address the second problem, subjectivity, researchers typically employ three interrelated devices to help ensure the objectivity of their behavioral observations. First, they develop a list of well-defined categories of behavior; next, they use well-trained observers; and finally, they use multiple observers to assess inter-rater reliability. The first step in the process is to prepare a list of behaviors called behavior categories. Developing a set of behavior categories means that before observation begins, we identify the categories of behavior we want to observe and then list exactly which behaviors count as examples of each category. A preexisting list enables observers to know exactly what to look for and how to categorize each behavior. During the observation period, normally only one individual observes and records behaviors using the set of behavioral categories as a guide. To establish reliability, however, two or more individuals must observe and record simultaneously for some of the observation periods. The degree of agreement between the two observers is then computed, either by computing a correlation between the scores for the two observers or by computing a proportion of agreement. Quantifying Observations ■ Behavioral observation also involves converting the observations into numerical scores that can be used to describe individuals and groups. ■ The creation of numerical values is usually accomplished by one of three techniques. ● The frequency method i nvolves continuing the instances of each specific behavior that occur during a fixed-time observation period. ● The duration method i nvolves recording how much time an individual spends engaged in a specific behavior during a fixed-time observation period. ● The interval method i nvolves dividing the observation period into a series of intervals and then recording whether a specific behavior occurs during each interval. Sampling Observations ■ One solution is to record the situation so the scene can be replayed repeatedly to gather observations.

A second solution is to take a sample of the potential observations rather than attempt to watch and record everything. ■ The first step in the process of sampling observations is to divide the observation period into a series of time intervals. ■ The sampling process then consists of one of the following three procedures: ● Time sampling involves observing for one interval, then pausing during the next interval to record all the observations. ● Event Sampling i nvolves identifying one specific event or behavior to be observed and recorded during the first interval, then shifting attention to a different event or behavior during the second interval, and so on, for the full series of intervals. ● Individual Sampling i nvolves identifying one participant to be observed during the first interval, then shifting attention to a different individual for the second interval, and so on. Content Analysis and Archival Research ○ When researchers measure behaviors or events in books, movies, or other media, the measurement process is called content  analysis. ○ Perhaps the most familiar application of content analysis is the examination of violence on television. ○ Recording behaviors from historical records is called a  rchival research. ○ The measurement process involves the following: ■ Establishing behavioral categories to define exactly which events are included in each category being measured. ■ Using the frequency method, the duration method, or the interval method to obtain a numerical score for each behavioral category. ■ Using multiple observers for at least part of the measurement process to obtain a measure of inter-rater reliability. Types of Observation and Examples ○ Ethologists (researchers who study nonhumans in their natural environment) and researchers interested in human behavior commonly use the observational research design. ○ There are three basic kinds of observation: naturalistic observation, participant observation, and contrived observation. ○ Naturalistic Observation ■ When a researcher observes and records behavior in a natural setting without intervening in any way, it is called n  aturalistic observation, or  nonparticipant observation. ■ Naturalistic observation could be used to describe any behavior. ■

●

●

Naturalistic observation is particularly useful in providing insight into real-world behavior. ■ The results of studies using naturalistic observation also have high degrees of external validity because the behavior is examined in real-world settings as opposed to laboratories. ■ One limitation of naturalistic observation is the time needed to conduct this type of research. ■ A second problem with naturalistic observation is that the observer must take extra care not to disrupt or influence the behavior being observed because the goal is to observe natural behavior. Participant Observation ■ In participant  observation, a researcher does not observe from afar as in naturalistic observation. ■ Instead, the researcher interacts with the participants and becomes one of them to observe and record behavior. ■ This type of observation is needed in situations in which inconspicuous observation is not possible. ■ Participant observation allows researchers to observe behaviors that are not usually open to scientific observation. ■ There are several limitations of this type of observation. ■ It is extremely time-consuming. ■ In addition, participant observation is potentially dangerous for the observer. ■ Furthermore, the observer may inadvertently alter participants’ behavior by directly interacting with them; and, finally, by interacting with the participants and identifying closely with the individuals in the study, an observer may lose objectivity. Contrived Observation ■ Another type of observation is c  ontrived observation, or structured observation. ■ In contrast to observing behavior in natural settings, the observer sets up a situation that is likely to produce the behaviors to be observed so that it is not necessary to wait for them to occur naturally. ■ The purpose of contrived observation is to precipitate a behavior that occurs naturally but infrequently, to create a situation wherein a natural behavior will probably occur and be observed in a more timely fashion. ■ Developmental psychologists frequently use structured observation. ■

○

○

Contrived observation may also take place in a natural but “set up” arena: a field setting arranged by the researcher for the purposes of observing and recording a behavior. ■ An advantage of contrived observation over both natural and participant observation is that researchers do not have to wait for behaviors to occur naturally. ■ Instead, the environment is structured in such a way that the desired behaviors are more likely to occur. ■ However, a disadvantage of contrived observation is that, because the environment is less natural, the behavioral may be as well. Strengths and Weaknesses of Observational Research Designs ○ A major strength of observational research is that the researcher observes and records actual behavior; in contrast, survey research, for example, relies on the participants’ reports of their behavior. ○ Participants can distort or conceal the accuracy or truthfulness of their responses and thus not reflect their actual behavior. ○ A potential problem with observational research is the ethical concern about spying on people. ○ If participants are not aware that their behavior is being observed, the researcher may be violating a person’s privacy and right to choose to participate in the study. The Survey Research Design ○ Surveys and questionnaires are used extensively in the behavioral sciences as relatively efficient ways to gather large amounts of information. ○ The simple notion behind a survey is that it is not necessary to observe directly where people shop or what foods they prefer, or how many hours they sleep each night; instead, we simply ask. ○ With a survey, a researcher does not have to wait until a behavior or response occurs. ○ A study using the results from a survey simply for descriptive purposes is classified as a s  urvey research design. ○ The goal of the survey research design is to obtain an accurate picture of the individuals being studied. ○ The survey provides a “snapshot” of the group at a particular time. ○  ■

●

●...