-
A mistake based on believing that what is true for a group must also be true for each individual in the group.
-
A measurement of the strength of a relationship between two variables. A statistical test may tell the researcher that a significant relationship may exist, but the effect size answers the question of how much one variable impacts the other (e.g., diet explains 80% of variance in weight gain).
-
The measure of how well something does what it is supposed to do for a certain group of people under normal conditions.
-
A measure of change after treatment; not an “experimental” study having a “control group.”
-
The measure of how well something does what it is supposed to do under ideal conditions, for example, in a lab instead of in the patient's everyday lives.
-
A study comparing an “experimental group” (who receives the treatment or whatever is being tested) to a “control group” (who does not receive the treatment).
-
The detailed rules for what kind of people a researcher will let into a certain study. For example, being over 60 and having an anxiety disorder diagnosis could be eligibility criteria for a study about how a new medication works for elderly, anxious people.
-
Anything that is based on observation and experimentation.
-
Research conducted "in the field," where data is gathered first hand. Case studies and surveys are examples of empirical research.
-
The act of gaining power (such as the power to make decisions, to question, to communicate, or to act) that often belongs only to a “higher” group; or of helping other people who are not in the “higher” group to get this power.
-
The study of how common a disease or state is among a group of people.
-
A kind of study that looks at and describes a society's culture.
-
The cause, often the medical cause, of a disease.
-
A form of research used to assess the value or effectiveness of social care interventions or programs.
-
A study to see whether a program or a project is doing what it set out to do.
-
When a subject does not meet the basic parameters for participation within the study because she/he doesn't have a certain characteristic or trait, they may be excluded from the sample.
-
The effects and unique contributions attributed to an intervention or specific treatment that the investigator expects to find.
-
In experimental conditions it is common to test the validity of a cause/effect relationship by having two groups of research subjects, an experimental group and a control group. In the former group the causal (independent) variable is present: in the latter it is explicitly excluded. For example, in a study to test the impact of counselling on care-giver stress, the experimental group of care-givers would receive counselling, the control group would not.
-
A kind of study that controls the circumstances of the research and measures the results exactly.
-
Experimental research is a style of research in which the researcher generates or manipulates a causal factor and then seeks to observe or measure the effects which follow. In a drug trial, for example, a group of patients with a particular illness are given a drug which it is hoped will alleviate or cure the illness, and the effect of the drug is monitored. A pure experimental approach involves the random selection of research subjects and control of extraneous variables, as well as manipulation of the independent variable.
-
A type of analysis conducted to discover what underlying factors are behind a set of variables or measures. For example, amount of "television watched", "radio listened", and "newspaper read" might be grouped together in a factor called "mass media exposure".
-
Seeks to find out more about phenomena which are little known. Explorative studies approach a topic broadly to identify the range of issues and opinions associated with it. They are often the fore-runners of more specific research which studies the identified topics in greater depth.
-
A measure of how well the results of a study apply to other people in other places.
-
When an experiment is seeking to monitor the impact of one variable on another (like counselling on stress level), attention has to be paid to other variables which could have an impact (that is, other factors which could affect a person's stress level). These other variables are called 'extraneous'.
-
Experimental research is a style of research in which the researcher generates or manipulates a causal factor and then seeks to observe or measure the effects which follow. In a drug trial, for example, a group of patients with a particular illness are given a drug which it is hoped will alleviate or cure the illness, and the effect of the drug is monitored. A pure experimental approach involves the random selection of research subjects and control of extraneous variables, as well as manipulation of the independent variable.
-
A type of analysis conducted to discover what underlying factors are behind a set of variables or measures. For example, amount of "television watched", "radio listened", and "newspaper read" might be grouped together in a factor called "mass media exposure".
-
This type of research seeks to find out more about phenomena which are little known. Explorative studies approach a topic broadly to identify the range of issues and opinions associated with it. They are often the fore-runners of more specific research which studies the identified topics in greater depth.
-
A measure of how well the results of a study apply to other people in other places.
-
When an experiment is seeking to monitor the impact of one variable on another (such as counselling on stress level), attention has to be paid to other variables which could have an impact (that is, other factors which could affect a person's stress level). These other variables are called 'extraneous'.
-
A statistical test (also known as Analysis of Variance) used to compare two or more groups for significance of the statistical difference between or among them.
-
A measure of whether a study’s results seem to make sense and whether they are clear.
-
A type of study used to find the underlying causes and characteristics of something. The general purpose of this test is to take the information in a large number of “variables” and to link it with a smaller number of “factors” or causes.
-
The measure of whether a test or scale based on a factor analysis makes sense for working with real patients in a clinical setting (not an experimental setting).
-
The observance of the actual treatment delivery to the set of rules originally developed; fidelity assessment considers to what degree the program was implemented as planned. Alternatively referred to as treatment integrity.
-
A kind of study that looks at people in their everyday world, not in a laboratory or other special setting. The everyday world is the “field.” This research is usually not experimental.
-
A term used to describe what happens when a group of subjects in a study have scores that are close to or at the lower limit (floor) of a variable. For example, the majority of subjects score very poorly because the task is too difficult.
-
Focus groups are open-ended, discursive, and are used to gain a deeper understanding of respondents' attitudes and opinions. Focus groups typically involve 6-10 people, and last for 1-2 hours. A key feature is that participants are to able interact with, and react to, each other. In order to facilitate this group dynamic, it is important to ensure that participants do not know each other beforehand and that they are broadly 'compatible'.
-
Contact with a person being studied, made after the first stage of the study, to see if there have been changes since then, and to see how long the changes last. The term can also mean the length of time a person is studied, or the length of time between stages in the study.
-
A scale, drawing, or graph that shows how often something (a number, answer, percentage, score) is found in the total pool of information being studied.
-
Frequency tables or tabulations are a set of data which provide a count of the number of occasions on which a particular answer or response has been given across all of those respondents who tackled the question.