1. Critical thinking is the process of evaluating propositions or hypotheses and making judgments about them on the basis of well-supported evidence. (see Thinking Critically About Psychology)
Example: Consider the five steps of critical thinking. (a) What am I being asked to believe or accept? What is the hypothesis? (b) What evidence is available to support the assertion? Is it reliable and valid? (c) Are there alternative ways of interpreting the evidence? (d) What additional evidence would help to evaluate the alternatives? (e) What conclusions are most reasonable based on the evidence and the number of alternative explanations?
2. A hypothesis is a prediction stated as a testable proposition, usually in the form of an if-then statement. (see Critical Thinking and Scientific Research)
Example:If rats have access to toys, then they can practice behaviors similar to those used in running a maze and perform better than rats raised without access to toys.
3. Data are numbers that represent research findings and provide the basis for research conclusions. (see Critical Thinking and Scientific Research)
Example: For a psychologist studying learning, a test score might represent an operational definition of the amount one has learned. Sets of test scores for classes that received different teaching methods are the data.
4. An operational definition is a statement of the specific methods used to measure a variable. (see Critical Thinking and Scientific Research)
Example: If we are conducting a study regarding the effects of caffeine on anxiety, we would have to decide exactly how we plan to measure anxiety. Our operational definition of anxiety might be changes in blood pressure or the subjects' answers to an anxiety questionnaire--whatever logically fits our research hypothesis.
5. A theory is a cohesive cluster of explanations of behavior and mental processes. Theories are not definitive; they are constantly amended as researchers collect and analyze new data. (see The Role of Theories)
Example: Finding that people under stress often overeat or drink more alcohol led to the theory that behaviors that appear self-destructive may be stress alleviators.
6. Sampling is a procedure used to choose subjects for research. Ideally, the participants chosen should be representative of the population being studied. (see Selecting Human Participants for Research)
Example: If you are studying the behavior of gifted children, your sample should be drawn exclusively from this group.
7. Random samples are groups of subjects selected from the population of interest. A sample is random if every person in the population has an equal chance of being selected. If a sample is not random, it is said to be biased. (see Selecting Human Participants for Research)
Example: A social psychologist is interested in studying the influence of parents on the career choice of first-year college students in the United States. If the sample is to be random, every first-year student must have an equal chance of being selected as a subject. The researcher thus draws the sample from lists of first-year college students in schools all over the United States, not just from the schools in one state.
A sample is biased if everyone in the population of interest does not have an equal chance of being selected to participate in a study. (see Selecting Human Participants for Research)
REMEMBER: Experimental results obtained from a biased sample may not be generalizable to the population of interest. The results are biased by characteristics of the subjects, not by the independent variable.
8. Naturalistic observation, a method of gathering descriptive information, involves watching behaviors of interest, without interfering, as they occur in their natural environments. (see Naturalistic Observation: Watching Behavior)
Example: A researcher interested in how much time children of different ages play alone could observe children at a playground.
REMEMBER: A researcher observes a phenomenon in its natural environment.
9. Case studies are used to collect descriptive data through the intensive examination of a phenomenon in a particular individual, group, or situation. Case studies are particularly useful for studying rare or complex phenomena. (see Case Studies: Taking a Closer Look)
Example: Biological psychologists cannot alter a person's brain in the laboratory for the purposes of study; therefore, they are interested in people who have suffered brain injuries in accidents.
Researchers examine these patients intensively over long periods of time.
10. Surveys are questionnaires or special interviews administered to a large group. Surveys are designed to obtain descriptions of people's attitudes, beliefs, opinions, or behavioral intentions. (see Surveys: Looking at the Big Picture)
Example: Social psychologists interested in learning what teenagers from families of varying income levels think of marriage can administer a questionnaire to a sample of teenagers.
11. An experiment allows a researcher to control the data-collection process. A random sample of subjects is selected and divided into a control group and an experimental group. Both groups are identical in every way except the administration of the independent variable to the experimental group. The dependent variable is then measured in both groups. Any difference in the dependent variable between the two groups is caused by the independent variable.
Experiments show causation. (see Experiments: Exploring Cause and Effect)
REMEMBER: An experiment is a trial or test of a hypothesis.
12. Independent variables are manipulated or controlled by the researcher in an experiment. They are administered to the experimental group. (see The Experimental Method)
Example: An experiment is conducted to test the effects of alcohol on reflex speed. Two groups of subjects are randomly selected. One group, the experimental group, is given alcohol (alcohol is the independent variable), and the other group, the control group, is given a nonalcoholic beverage.
13. Dependent variables are the behaviors or mental processes affected by the independent variable. They are observed and measured before and after the administration of the independent variable. (The Experimental Method)
Example: In the experiment examining the effects of alcohol on reflex speed, the dependent variable is reflex speed.REMEMBER: The measure or value of the dependent variable depends on the independent variable.
14. The experimental group receives the independent variable in an experiment. (see The Experimental Method)
Example: In the experiment examining the effects of alcohol on reflex speed, the group who receives alcohol (the independent variable) is the experimental group.
15. The control group provides a baseline for comparison to the experimental group and does not receive the independent variable. This group is identical to the experimental group in every way except that these subjects do not receive the independent variable. (see The Experimental Method)
Example: In the experiment examining the effects of alcohol on reflex speed, the group who received the nonalcoholic beverage is the control group.
REMEMBER: The control group provides the control in an experiment. Comparing the measure of the dependent variable in both the control and experimental groups indicates whether the independent variable is causing the changes in the dependent variable or whether these changes occurred by chance.
16. Confounding variables are factors affecting the dependent variable in an experiment instead of or along with the independent variable. Examples of confounding variables include random variables, experimenter bias, and the placebo effect. (see The Experimental Method)
17. Random variables are uncontrollable factors that could affect the dependent variable in an experiment instead of or along with the independent variable. (see Random Variables)
Example: An experimenter wishes to test the effects of a teaching technique on test performance. The subjects are assigned to the control and experimental groups. The researcher doesn't know it, but most of the students in the experimental group are much brighter than the control group students. The data may suggest that the students who received the teaching technique scored higher than those who didn't. In this case, however, intelligence is a random variable that, instead of the independent variable, could be responsible for the results.
18 Random assignment is an attempt to try to minimize effects of random variables by distributing them randomly across groups. Thus, participants are randomly assigned to experimental or control groups. (see Random Variables)
19. A placebo is a physical or psychological treatment that contains no active ingredient but produces an effect on the dependent variable because the person receiving it believes it will. (see Participants' Expectations)
Example: In an experiment on the effects of alcohol, a researcher may find that people who have been given a nonalcoholic beverage behave as though they're drunk only because they believe they have been given an alcoholic drink.
20. Experimenter bias occurs when a researcher inadvertently encourages subjects to respond in a way that supports her hypothesis. (see Experimenter Bias)
Example: An experimenter hypothesizes that an expert will be able to persuade a group of people that decision A is better than decision B. After the expert has spoken to the subjects, the researcher asks them which decision they prefer. She can ask in several ways. Asking, Now, don't you think A is better than B? will bias her data more than if she asks, Which do you think is better, decision A or decision B?
21. In a double-blind design neither the experimenter nor the participants know who has received the independent variable. (see Experimenter Bias)
Example: The experiment studying the effects of alcohol on reflex speed (described in relation to Key Term 10) is repeated using a double-blind design. Neither the participants nor the experimenter knows who has received alcohol and who hasn't. Thus participants are prevented from changing their behavior simply because they think they have been given alcohol. At the same time, the experimenter is prevented from biasing observations of the subjects' behavior or mental processes.
22. Descriptive statistics summarize a set of data. Examples of descriptive statistics are measures of central tendency, measures of variability, and correlation coefficients. (see Statistical Analysis of Research Results)
23. The mode is the most frequently occurring score in a data set. (see Measures of Central Tendency)Example: In the data set 3, 12, 14, 16, 17, 18, 19, 22, 22, 22, 22, the mode is 22.
24. The median is the score that divides a data set in two; half the scores are higher than the median, and half the scores are lower than the median. (see Measures of Central Tendency)Example: In the data set, 3, 12, 14, 16, 17, 18, 19, 22, 22, 22, 22, the median is 18.REMEMBER: The median is "the score in the middle"--the score that divides the data set in half. When there is an even number of scores in a data set, the median is halfway between the two middle numbers.
25. The mean is the arithmetic average. To compute the mean, add the numerical values of all the scores in a data set and divide that sum by the number of scores in the data set. (see Measures of Central Tendency)Example: For the previous data set the mean is equal to (3 + 12 + 14 + 16 + 17 + 18 + 19 + 22 + 22 + 22 + 22)/11 = 187/11 = 17.
REMEMBER: This measure of central tendency takes into account all of the values of the scores in a data set. Therefore, even one extreme score can change the mean radically, possibly making it less representative of the data.
The range is a measure of variability computed by subtracting the lowest score from the highest score in a data set. The range is affected by extreme scores. (see Measures of Variability)Example: In the data set 2, 3, 4, 5, 5, 5, 6, 7, 8, 100, the range is 100 - 2 = 98. If the extreme score (100) is dropped, the range is 8 - 2 = 6. Extreme scores can radically affect the range of a data set.
26. The standard deviation is a measure of variability. It reflects the average distance between each score and the mean of a data set. The standard deviation will tell you how different the scores are from the mean. (see Measures of Variability)
Example: Following are two data sets.Data set 1: 1, 2, 3, 4, 5, 6, 7, 8, 9Data set 2: 4, 4, 4, 4, 5, 6, 6, 6, 6The mean of both data sets is 5. However, the scores in data set 1 are a greater distance from the mean. In other words, they are more different from the mean than the scores in data set 2. Therefore, the standard deviation (SD) in data set 1 is larger than the SD for data set 2.
REMEMBER: To deviate means to "differ." The standard deviation describes, overall, how different the scores in a data set are from the mean.
27. A correlation is an indication of the relationship between two variables (x and y). (see Correlation and Correlation Coefficients)
Example: In a small English town, the seasonal appearance of a large number of storks is positively correlated with the number of human births; as x (the number of storks) increases, y (the number of births) increases. If correlations indicated causation, we could say that the storks cause babies to appear. But correlations do not imply causation, and storks do not bring babies.
REMEMBER: Correlations do not indicate causation.
28. The correlation coefficient (r), a number between -1.00 and +1.00, is a mathematical representation of the strength and direction of a correlation. The higher the absolute value of r is, the stronger the relationship is. A perfect correlation, whether positive or negative (where r equals + or -1.00), describes a perfect relationship; knowing the value of x allows the certain prediction of y. A positive correlation (where r varies from 0 to +1.00) describes two variables that change in the same direction: as x increases, so does y (and vice versa). A negative correlation (where r varies from -1.00 to 0) describes an inverse relationship: as x increases, y decreases (and vice versa). (see Correlation and Correlation Coefficients)
29. Inferential statistics are used to judge the meaning of data. Inferential statistics assess how likely it is that group differences or correlations would exist in the population rather than occurring only due to variables associated with the chosen sample. (see Inferential Statistics)
REMEMBER:Inferential statistics allow psychologists to infer what the data mean.
If a statistic is statistically significant, it is an indication that the group differences or correlation is larger than would occur by chance. (see Inferential Statistics)
Example: If the difference between two group means is statistically significant, a researcher would conclude that the difference most likely exists in the population of interest. If the difference is not statistically significant, a researcher would conclude that the difference occurred by chance--possibly because of an unrepresentative sample or the presence of confounding variables.
30. Behavioral genetics explores the impact of genetics and environmental factors on differences in the behavioral tendencies of groups. (see Linkages: Psychological Research and Behavioral Genetics)
Example: A behavioral genetics study might look for similarities in behavior among relatives. The children of a person who experiences depression, for example, might be more likely to develop depression than distant relatives or unrelated people.
