| A | B |
|---|
| Case Studies | Intensive investigation of the behavior and mental processes associated with a specific person or situation. Provide detailed descriptive data and analyses of new, complex, or rare phenomena. May not be representative. |
| Central Tendency | Describes average of a distribution. Median is middle score when data is ordered by size. Mean is arithmetic average of scores. Mode is most frequent score, bimodal distribution has 2 most frequent scores, multimodal distribution has 3 or more. |
| Confounding Variables | Factors that cause differences between the experimental group and the control group other than the independent variable. Example: Experimenter bias (also called expectancy effect)--occurs when a researcher's expectations about the outcome of a study influence the results. |
| Correlation Coeffient | Measure of the degree of relatedness or association between 2 sets of data. (r) varies from -1 to +1. The closer to 1 or -1, the greater the association. If (r) = +1, the perfect relationship is direct: if (r) = -1, the perfect relationship is inverse. (r) = 0 shows no relationship. |
| Demand Characteristics | Clues participants discover about the purpose of the study. gle-blind--participants don't know if they are in the experimental or control group, and double-blind--neither experimenter nor participants know. |
| Descriptive Statistics | Numbers that summarize a set of research data from a sample.Can be pictured as histogram or frequency polygon. |
| Ethical guidelines | Suggested rules for acting responsibly and morally when conducting research or in clinical practice. APA guidelines for research require IRB (Institutional Review Board) approval and informed consent by participants. |
| Experiment | Research method that involves manipulation of an independent variable (IV) under controlled conditions and measurement of its effects on a dependent variable (DV). Only method that can establish cause and effect between IV and DV. |
| Experimental Group | Subgroup of the sample in an experiment that receives the treatment or independent variable.Another subgroup, the control group, does not receive the treatment and is compared to the experimental group to measure the effects of the IV on the DV. |
| Hypothesis | Prediction of how 2 or more factors are likely to be related. Can be phrased as "If …, then …." statement. Often called "an educated guess".An experiment tests a hypothesis. |
| Inferential Statisctics | Statistics used to interpret data and draw conclusions.● Uses rules to evaluate probability that a correlation or difference between groups reflects a real relationship, not just chance (p)is the measure of real difference, p < .05 or p < .01 needed. |
| Measures of Variability | Describe spread or dispersion of scores. Variance and Standard deviation (SD) indicate degree to which scores differ from each other and vary around the mean value for the set. Taller, narrower graphs--less variability. |
| Naturalistic Observations | Careful observations of humans or other animals in real-life situations. Provides descriptive data about behavior with wide applicability. Lacks experimental control and cannot establish cause and effect. |
| Normal Distribution | Represented by a normal curve--symmetric with mean, mode, and median the same score; 2 sides are mirror images. ● Represents data about how most human traits are distributed through population. Examples: SAT, ACT, IQ, height. |
| Placebo | Physical or psychological treatment given to the control group that resembles the treatment given to the experimental group, but contains no active ingredients. Placebo effect--response to belief that the IV will have an effect, rather than the actual effect of the IV. |
| Population | All of the individuals in the group to which the study applies.A sample is a subgroup of the population that participates in the study. |
| Quantitative Data | Information can be reported as numbers for ease of handling. Nominal scale uses numbers to name something, can be used to count cases.Ordinal scale can be ranked, ordered. Numbers cannot be averaged. |
| Quasi-Experiment | Measurement of DV (dependent variable) when random assignment to groups of a randomly selected sample is not possible. Often applies to studies involving sex or age of participants. Can suggest cause and effect. |
| Random Assignment | Division of the sample in an experiment into groups so that every individual has an equal chance of being put in any group or condition.Is not possible for studies dealing with differences between sexes or age groups. |
| Random Selection | Choosing of members of a population so that every individual has an equal chance of being chosen for a sample. |
| Reliability | Consistency or repeatability of results. Split halves reliability compares scores on one half to the other half. Test retest reliability compares scores on the same test taken at different times. Interrater reliability compares scores by different scorers of the same tests. |
| Skewed Distribution | Distribution with most scores squeezed to one end, few scores stretch out like tail. Skew named for direction of tail. Negatively skewed--skewed to left. Positively skewed--skewed to right. Mean pulled in direction of tail away from median; median measures centrality best. |
| Standard Score | Enables comparison of scores that are initially on different scales. Also called z score. Z score of 0 is at the mean of a distribution, z = 1 is 1 SD from the mean. Percentile score can also be used for comparison; percent of scores at or below score. |
| Statistics | Field that involves analysis of numerical data about representative samples. Interval scale used with numerical data with meaningful difference between each of the numbers. Ratio scale has real zero point, used with data when meaningful ratio can be made. |
| Surveys | Obtain large samples of abilities, beliefs, or behaviors through questionnaires or interviews at specific time and place.Can get distorted results from sampling error, poor questions, and response biases. Example post facto--retrospective surveys look at effect and seek the cause. |
| Tests | Procedures to measure attributes of individuals at a particular time and place to gather lots of information quickly.Needs reliability--consistency or repeatability, and validity--measures or predicts what it is supposed to. |
