Exam Revision: Definitions of HPS104 content PDF

Preview

Summary

Complete glossary of all definitions required for examination in easy to remember dot-point form.
...

Description

DEFINITIONS OF HPS104 Internal Validity: refers to the degree to which a research finding provides accurate or compelling information about causality. The degree to which changes in the independent variable in a particular study really do influence the dependent variable in the way suggested by the results of the study. The extent to which a cause‐effect relationship is (or has been) established External Validity: Ability to generalize findings beyond sample and able to apply the observed relation between and IV and DV to the real world. Confound/Confounding Variable: a variable other than the independent variable that has an unwanted effect on the dependent variable, making it impossible to determine which of the variables produces the change in the dependent variable Control Group: no treatment administered (baseline) Operational Confound: A confound that occurs when a measure designed to assess a specific construct such as self-esteem, time pressure, or happiness inadvertently measures something else as well. Experimenter Bias: Occurs when an experimenters expectations influence the outcome of the study Homogeneous attrition: when you have an equal number of people dropping out in each group. A threat to external validity Heterogeneous attrition: when attrition rates are different across experimental conditions. A threat to internal validity Artefact: A variable that is held constant in a study but which influences the relation between the independent (or predictor) variable and the dependent variable. Consider a drug study that includes only male participants. If the drug being studied works for men but not for women, gender would be an artifact. This is a threat to external validity. Causation: Being able to show that an independent variable directly causes the dependent variable. Correlation: A relationship between two variables, but not necessarily a causation relationship. Hypothesis: A testable, plausible and definitive test of the original research question. They need to contain the following =   

It needs to be a logical test; It needs to be relevant to the research question of interest; and It needs to be clear in the sense that the predictions the hypothesis makes are unambiguous with no mysterious components to it, and all the variables of interest have been or can be operationalised

Testable Research Questions: A testable question is one that can be answered by designing and conducting an experiment. Testable questions are always about changing one thing to see what the effect is on the other thing. Against which criteria should a theory be evaluated?: validation, falsification, qualification Constructs: Things that are defined by theory, and that which don’t contain concrete tangible boundaries. Reverse Causality: Reverse causality means that X and Y are associated, but instead of X causing a change in Y, it is really the other way around: Y is causing changes in X. Non Response Bias: The bias that occurs in research when a substantial proportion of those invited to take part in a study refuse to do so. Selection Bias: Choosing research participants from a nonrepresentative sample by using imperfect (i.e., biased) sampling techniques rather than true random sampling. This typically represents a threat to external validity. Attitude Polarisation: Attitude polarization is a phenomenon where people’s attitudes or beliefs strengthen and become more extreme as they engage in intensive thought about the attitude object. Social Desirability bias: refers to the fact that in self-reports, people will often report inaccurately on sensitive topics in order to present themselves in the best possible light

Four Canons of science 1. 2. 3. 4.

Empiricism: discovery through experience Determinism: orderly, predictable, natural, cause-effect Parsimony: simple=better Testability: testability/falsifiability; operationalism

Moderation: is a variable that affects the strength and/or direction of the relationship between an independent variable (X) and a dependent variable (Y). Mediation: explains how or why an independent variable is related to a dependent variable. Also known as an indirect effect of X on Y through M Scientist-practitioner model: A Scientist-Practitioner is a professional whose activities are performed in an empirical framework. Ideals: 1. To be Intelligent and discerning producers/consumers of new knowledge 2. To be evaluated of their own activities 3. To be researches who contribute new data from their own settings Operationalisation: when an experimental variable is stated in terms of how it will be observed, manipulated and/or measured

Construct validity: is used to ensure that the measure is actually measuring what it is intended to measure (i.e. the construct), and not other variables. Eg. How well a study on depression measures depression (as opposed to anxiety, etc) Conceptual validity: Conceptual validity refers to how well the study as a whole (ie, the method, participants, results etc) reflects the broader research question. So it takes construct validity one step further, by not only focusing on the IV & DV in relation to the construct of interest, but rather looking at the study as a whole in relation to the research question that it is intending to answer? (Ie.Does one’s risk of depression increase as they age and does our study effectively address this question?) Levels: a term that simply refers to the number of discrete values that a categorical/discrete variable can take (ie; if a variable in a study is gender, it most likely has 2 levels; male and female)

Types of Measurement Scales Nominal: A nominal level of measurement is simply a matter of distinguishing by name, e.g., 1 = male, 2 = female. Even though we are using the numbers 1 and 2, they do not denote quantity. EG;    

Meal Preference: Breakfast, lunch, dinner Religious Preference: 1 = Buddhist, 2 = Muslim, 3 = Christian Political Orientation = Republican, Democratic, Green Time of Day: AM / PM (categories, no additional information)

Ordinal: Ordinal refers to order in measurement. An ordinal scale indicates direction, in addition to providing nominal information. Low/Medium/High; or Faster/Slower are examples of ordinal levels of measurement. Ranking an experience as a "nine" on a scale of 1 to 10 tells us that it was higher than an experience ranked as a "six." EG;   

Rank: 1st place, 2nd place.... last place Political orientation: Left, Centre, Right Time of Day: Night, dawn, afternoon, evening (indicates direction or order of occurrence; spacing between is uneven

Interval: Interval scales provide information about order, and also possess equal intervals. Scale that uses real numbers designating amounts to reflect relative differences in magnitude. Can be negative. EG;   

Temperature: 12 degrees, 13 degrees, 14 degrees Political Orientation: Score on standardized scale of political orientation Time of day: On a 12-hour clock (difference between 1 and 2 pm is same as difference between 11 and 12 am)

Ratio: Measurement scales that use real numbers designating equal amounts to reflect relative differences in magnitude. Cannot be negative. Have the same properties of Interval scales except ratio scales always have a true zero point. EG;  

Ruler: Inches or centremeters Income: Money earned last year

Manipulation: Systematically varying the level of an independent variable in an experiment, with the goal of seeing whether doing so has any effect on the measured level of a dependent variable. Reliability: Refers to the extent to which your measure is consistent in its performance, performs in the manner in which it is intended. Inter-rater reliability: Used to assess the degree to which different raters/observers give consistent estimates of the same situation.. Test-retest reliability: Test-Retest Reliability measures test consistency — the reliability of a test measured over time. In other words, give the same test twice to the same people at different times to see if the scores are the same.

All study designs Repeated Measures Design: An experimental design in which each participant serves in more than one condition (typically all of the conditions) of the experiment. Factorial Design: A research design containing two or more independent variables that are completely crossed, meaning that every level of every independent variable appears in combination with every level of every other independent variable. Matched-participants design: an experimental research design in which pairs of participants who are very similar in a characteristic(s) that can influence the dependent variable are selected and then allocated to a different group (the experimental or the control group); also called matched-subjects or matched-groups design

Types of sampling Sampling: the process of selecting a representative group from the population under study. A sample is the group of people who take part in the investigation. The people who take part are referred to as “participants”. Convenience sampling: A convenience sample is a matter of taking what you can get. It is an accidental sample. Although selection may be unguided, it probably is not random, using the correct definition of everyone in the population having an equal chance of being selected. Volunteers would constitute a convenience sample.

Simple Random sampling: This method gives every member of the target group an equal chance of being selected for the sample (e.g. by assigning a number to each member, and then selecting from the pool at using a random number generator). Cluster sampling: Cluster sampling refers to a sampling method wherein the members of the population are selected at random, from naturally occurring groups called 'cluster'. Stratified sampling: Here the sampler divides or 'stratifies' the target group into sections, each showing a key characteristic which should be present in the final sample. Then each of those sections is sampled individually. The sample thus created should contain members from each key characteristic in a proportion representative of the target population. Random Assignment: A technique for assigning participants to different conditions in an experiment. Ordinal interaction: This describes the situation in which an independent variable has an effect at one level of a second independent variable but has a weaker effect, or no effect, at a different level of the second dependent variable. Disordinal interaction: This describes the situation in which (1) there are no main effects of either independent variable and (2) the effects of each independent variable are opposite at different levels of the other independent variable. Two way factorial designs: a factorial design is a design that consists of two or more factors, each with discrete possible values or "levels", and whose experimental units take on all possible combinations of these levels across all such factors. Independent Variable: Manipulated Dependent Variable: Measured Main effect: does an IV (factor) generally affect the DV? Interaction effect: an interaction occurs when the effect of one factor on the dv is not the same at all levels of the other factor Simple main effect: how does an IV affect the DV at one level of another IV Observational Study: means that researchers record information about their subjects without manipulating the study environment. Non-experimental (observational) Designs Cross sequential: A prospective study, meaning that the researcher monitors performance of the participants over a period of time. Time consuming but allows you to follow a developmental trajectory. Case-Control (longitudinal): A retrospective study. Two groups differing in outcomes where the researcher retrospectively investigates backwards in order to identify what one group may have been exposed to that caused the differing outcomes. Cross Sectional (differential): Snapshot in time. Results are received from one quick questionnaire/study/test.

Verificationism – we can only investigate what can be observed. Defines the boundaries of what can and can’t be tested scientifically. This takes the form of adherence to the... Verifiability Principle – a statement is only meaningful if it can be verified through direct empirical observation or through logic Mean: a score that is the arithmetical average of all the individual scores (or measures) in a set of scores Median: the middle score (or midpoint) of a set of scores Mode: the most frequently occurring score in a set of scores Beneficence: ethical value promoting research that maximises possible benefits of the research, while minimising risks of harm or discomfort to the participants...