Measurements in Psychology
Psychological measurement is the use of specified testing procedures to evaluate the abilities, behaviors, and personal qualities of people. It is used to describe how individuals are different from, or similar to, other individuals—how many more test questions they can answer than other people of their age, whether they seem more successful in a career than other people, etc.
What is Measurement?
Measurement is the process of quantifying observations (or descriptions) of a quality or attribute of a thing or person.
Process of Measurement
The process of measurement involves three steps:
- Identifying and defining the quality or attribute that is to be measured;
- Determining a set of operations by which the attribute may be made manifest and perceivable; and
- Establishing a set of procedures or definitions for translating observations into quantitative statements of degree or amount.
Variables and Measurement
The concept of a variable is basic and virtually important in statistical studies. A variable simply refers to anything that varies and can be measured. For instance, the sex of students in an economics class is a variable since it can be measured as either male or female, and generally, the sex of students varies accordingly. Similarly, socio-economic status is a variable because a set of individuals will belong to high, medium, and low socio-economic statuses. Thus, measurement can involve merely categorizing.
Types of Variables
There are two main types of variables used in the study of psychology; these are
- Independent variables, and
- Dependent variables.
Independent variables (IVs) are those that the experimenter purposely manipulates. The independent variables constitute the reasons the research is being conducted; the experimenter is interested in determining the effect of the IV on the DV.
The term 'independent' is used because the IV does not depend on other variables; it stands alone. A few examples of IVs that experimenters have used in psychological research are price, deprivation, temperature, noise level, removal of a portion of the brain, and psychological context.
The dependent variable (DV) changes as a function of the level of the independent variable (IV) the participant experiences; the value the DV assumes truly depends on the IV. The DV is the effect of the cause-and-effect relationship the researcher is examining.
For instance, in researching "the effect of price on consumer buying behavior," "price" is the independent variable, whereas the effect of price determines the quantity of goods or items the consumer will purchase. In other words, "quantity purchased" in this sense is the dependent variable.
Participants in an experiment are individuals whose behavior is being studied or observed. They are assigned either to the experimental group, that is, the group exposed to the independent variable, or to the control group, the group exposed to all the conditions of the experiment except for the independent variables.
Major Types of Measurement
In psychological studies, the psychologist emphasizes different types of measurement, which include:
- Score numerical measurements, and
- Nominal or Category Measurements.
(1) Score or Numerical Measurement
This refers to the assignment of a numerical value to a measurement. This includes most physical and psychological measures, e.g., a student's score in a course work. In psychological expression, these numerical values or measurements are called scores.
(2) Nominal or Category Measurement
This is simply deciding which category of a variable a particular case belongs to. For instance, if a researcher is interested in measuring a person's job status in an organization, he or she would have to decide whether or not the employee is a truck driver, a security officer, a cashier, and so forth. This is called nominal measurement since usually the categories are described in words and given names. Thus, a cashier is a name or verbal description of what sort of case should be placed in that category.
The Four (4) Theoretical Scales of Measurement
Many researchers speak of tools or scales of measurement in carrying out their research investigation. The scales are conceptually different. In psychological studies, there are four 'theoretical scales of measurement. They are as follows:.
- Nominal Scale: This is the placing of cases into named categories. The word nominal clearly refers to names. Nominal scale is the lowest form of assigning numerals to objects, and the numbers sometimes assigned have no meaning; they serve as labels to assist in categorization. For example, we can categorize socio-economic status as (1) high, (2) medium, and (3) low.
- Ordinal Scale: The assumption here is that the values of the numerical scores tell us little else other than which is the smallest, the next smallest, and so forth up to the largest. In other words, we can place the scores in order (hence ordinal) from the smallest to the largest. It is sometimes called rank measurement since we can assign rank to the first, second, third, fourth, etc.
- Interval Scale: It is the most widely used in scientific research because it combines the qualities of both nominal and ordinal scales, especially that of rank ordering. In addition, numerically equal distances on interval scales represent equal distances in the property being measured. For example, if we have values like 4, 6, 8, and 10, that means the distance between 4 is the same as 8 and 10. and 6 is the
- Ratio Scale: This is exactly the same as interval scale measurement, with one important agreement. A ratio scale of measurement has an absolute zero point that is measured as 0. Most physical measurements, such as distance and weight, have zero points that are absolute. Thus, zero on a tape measure is the smallest distance one can have, and there is no distance between two coincident points.
Observational Method
Systematic observation has been described as the starting point of any science. Making observations involves watching a phenomenon of interest in the environment. We all do this in one way or another in our daily lives. We watch how people eat, dress, associate, etc. Psychologists are engaged in the same activity, only in a more objective and systematic way.
Observation techniques in psychology are done in at least three different ways, viz:
- Case study technique;
- Survey technique and
- Naturalistic observation technique.
(i) Case Study Technique
Through this means, psychologists study individuals in great depth and detail with the hope of revealing certain things about them. After making a number of observations on an individual, the psychologist would then infer the causes of the behavior of the individual. This is, however, done according to certain rules of logic.
Frequently, scientists use case studies in clinical settings to help formulate hypotheses and ideas for further research. For example, the French physician Paul Broca (1824–1880) reported the case study of a patient nicknamed "Tan" because he said nothing except the word "tan" and an occasional obscenity when he was frustrated or annoyed. Based on his observations, Broca hypothesized that the center controlling the production of speech was located in the frontal lobe of the left hemisphere of the brain and that this area was damaged in the patient's brain. An autopsy indicated Broca's hypothesis was correct.
(ii) Survey Technique
In this approach, people are asked specific questions about their behavior, opinions, attitudes, feelings, expectations, or individual knowledge. A number of methods exist that facilitate the survey technique. These are: interview method, in which questioning is done in a face-to-face interaction with the individual under study; and the questionnaire method, which most of us are very familiar with.
It is a way of getting responses to a list of questions that follow a fixed format of presentation where the individual is expected to fill in his responses to the questions asked. Questionnaires may be structured or unstructured, open or closed-ended.
The choice of any of these depends on the interests of the researcher and the nature of the research. Generally, surveys can be helpful in establishing how strong a particular reaction is among a given population of people, how widespread a problem is, or what the significant issues are from the viewpoint of the public.
(iii) Naturalistic Observation Technique
Observing some naturally occurring behavior with no atmosphere to change, alter, or interfere with it is called naturalistic observation. For example, you might sit behind a one-way glass window with a class of primary school children and observe them play without their being aware of your presence.
Naturalistic observation is especially useful in the early stages of an investigation for discovering the extent of some phenomena or getting an idea of what the important variables and relationships might be.
Correlational Method
Survey research represents a more general approach to psychological research, called correlational research. The correlational method does not involve the manipulation of independent variables, as in the case of a laboratory or field experiment.
Instead, the correlational method assesses relationships among naturally occurring variables with the goal of identifying predictive relationships. Predictive relationships that are found in the correlational method allow researchers to make predictions about future behavior, and they also play an important role in decision-making such as diagnosing psychological disorders and selecting among job applicants.
A correlation exists when two different measures of the same people, events, or things vary together; that is, when scores of one variable covary with scores of another variable. A familiar correlation is the predictive relationship between smoking and lung disease.
The more an individual smokes (e.g., measured by the length of time the person has been smoking), the greater their likelihood of contracting lung disease. Thus, smoking and lung disease are covariant, or go together, and we can describe this correlation by saying, "The less people smoke, the lower their chances of contracting lung disease."
Based on this correlation, we can make predictions about lung disease. For example, if we know how long an individual has smoked, we can predict (to some degree) his or her likelihood of developing lung disease. The nature of our predictions and the confidence we have in making them depend on the direction and strength of the correlation.
The direction and strength of a correlation are determined by computing a correlation coefficient. The direction of a correlation coefficient can be either positive or negative. Positive correlations indicate that as the values of one measure increase, the values of the other measure also increase. For example, the correlation between measures of smoking and lung disease is a positive correlation; as smoking increases, lung disease increases.
With a negative correlation, as the value of one measure increases, the value of the other measure decreases. For example, a national survey of high school seniors showed a negative correlation between the amount of time spent watching TV and the number of correct answers on an academic achievement test. Students who spent more time watching TV answered fewer questions correctly on an achievement test.
Experimental Method
The difficulty in ascribing a causal role to any variable or behavior as it is done in naturalistic observation is what leads psychologists to use the experimental method. A controlled experiment is a research method in which observations are made of specific behavior under systematically varied conditions. Here, the investigator manipulates one or more stimulus variables and observes the effects on one or more behaviors.
The stimulus variable that is systematically manipulated by the subject or the individuals in the experiment is called the independent variable. The response is the unit of behavior whose form or amount is expected to depend on the manipulations of the independent variable; it is therefore called the dependent variable. The respondents in an experiment are the individuals whose behavior is being observed.
They are assigned to either the experimental group (the group exposed to the independent variable) or the control group (the group exposed to all the conditions of the experiment except for the independent variable). Generally, controlled experiments are used for testing hypotheses. They determine how two or more variables are related and whether there is a cause-and-effect relationship between them, that is, between a particular condition and a later response.
For testing hypotheses, carrying out scientific research, and generating psychological theories, a psychologist must first of all select a method of data collection from among those described above. After the necessary details about the subjects have been collected, the behavioral outcomes of the subjects will then form the data for the study.
The data needs to be processed and analyzed to achieve the goal of the researcher. These are the statistical manipulations that psychologists, like their counterparts in the natural sciences, must make.
Why Psychological Measurements?
Measuring or assessing the attributes of individuals serves a number of functions for the psychologist.
- It enables him to formalize the procedures by which predictions about individual behavior can be made with minimum error and maximum accuracy.
- It makes sense of the incredible range of individual differences. Measurements attempt to explain how different traits go together to form a unique personality. Psychologists are curious to discover ways of describing the diversity of individual behavior. By testing, classifying, and categorizing individuals who share similar traits, psychologists can correlate behavioral differences with personality types.
- Another aspect of the scientific concern for measurement has to do with learning about how people develop. At what age do children develop certain skills, attitudes, and ways of dealing with the world? How important are sex, race, intelligence, and other human characteristics in predicting specific behavioral outcomes?
For the purposes highlighted above, psychologists make use of many instruments in their measurement and assessment intentions. These include interviews as well as psychological testing, which utilizes tests, scales, and inventories to measure virtually all aspects of human functioning, such as intelligence, personality, creativity, self-report (also called self-inventory), in which respondents are to answer questions or give information about themselves, and finally, ratings.
However, whatever the measurement instrument adopted by a psychologist, it must satisfy certain requirements. The assessment instrument or test should be:
- Reliable;
- Valid; and, for most purposes,
- Standardised
If a measurement instrument fails to meet these requirements, then the validity or trustworthiness of a person's score will be in doubt.
Reliability
A test is reliable if its measurement consistently results in the same findings over and over again.
Validity
This refers to whether the instrument is measuring what the assessor intends it to measure. A valid test of intelligence tells us how intelligent people are and predicts performance in situations where intelligence is important.
Standardisation
To be most useful, the measuring device should be standardized, i.e., capable of being administered to all persons in the same way under the same conditions. Standardization is a method that establishes norms, or statistical standards, so that an individual's score can be compared with those of others in a defined group.
Examples of reliable, valid, and standardized instruments in psychology are the following:
- The Stanford-Binet Intelligence Test was developed in 1960 on intelligence.
- The Minnesota Multiphasic Personality Inventory (MMPI), developed by Starke Harthaway and J.R. Mckinley at the University of Minnesota in 1930, measures personality.
- The Rorschach inkblot test was developed by a Swiss psychiatrist. Hermann Rorschach, in 1924, measured personality.
- Thematic Apperception Test (TAT), developed in 1938 by the American psychologist Henry Murray to measure personality.