Textbook Notes (363,094)
Canada (158,187)
Psychology (3,263)
PSYC 3380 (4)
Chapter 3

Chapter 3 Notes - The Research Trinity

5 Pages
Unlock Document

University of Guelph
PSYC 3380
Jeffrey Spence

Chapter 3 Notes: The Research Trinity Trinity Overview Internal Validity: approximate truth of inferences about causal relations External Validity: whether inferences hold across variations in cases, treatments, settings, or measures - mainly a function of sampling and if sampling is representative Construct Validity: the correct measurement of variables that the researcher intends to study Conclusion Validity (statistical conclusion validity): the appropriate use of statistical methods in the analysis to estimate relations between variables of interest Design ­ if cases are randomly assigned to either treatment or control conditions, the design is an experimental design ­ if either (1) cases are divided into groups that do or do not receive treatment using any other method (i.e. non random assignment) or (2) there is no control group but there is a treatment group, then the design is quasi-experimental Case-probing designs: inferences about cause-effect relations (i.e. internal validity) are of paramount interest ­ studies about gender difference are non-experimental because researchers cannot somehow assign participants to be either male or female ­ the term criterion variable is used instead of dependent variable in nonexperimental designs ­ experimental, nonexperimental and quasi-experimental designs are not mutually exclusive Nuisance (noise) variables: introduce irrelevant or error variance that reduces measurement precision Ex: testing grade 1 students in a chilly, noisy room may not yield precise reading scores Confounding variables: the effects of two variables on the dependent variable cannot be distinguish from each other Independence of Observation: the score of one case does not influence the score of another case ­ 3 general principles must be met before one can reasonably infer a cause-effect relation: 1) temporal precedence: the presumed cause must occur before the presumed effect 2) association: there is observed covariation-variation in the presumed cause must be related to that in the presumed effect 3) isolation: there are no other plausible alternative explanations (i.e. extraneous variables) of the covariation between the presumed cause and the presumed effect Measurement ­ measurement serve three essential purposes: 1) identification and definition of variables of interest 2) an operational definition 3) scores ­ construct validity is the main focus of measurement – whether the scores reflect the variables of interests, or what the researcher intended to measure Analysis ­ three main goals in analysis: 1) estimating covariances between variables of interest, controlling for the influence of other relevant, measured variables 2) estimating the degree of sampling error associated with this covariance 3) evaluating (test) the hypothesis in light of the results Internal Estimation: estimation of the degree of sampling error associated with the covariance Confidence Interval: a range of values that may include that of the population covariance within a specified level of uncertainty Covariate: a variable that predicts outcome but is ideally unrelated to the independent variable ­ in ANCOVA, the variance explained by a continuous covariate is statistically removed, which reduces error variance Homogeneity of Regression: the slope of the within-group regression lines for the association between the dependent variable and the covariate is the same across all groups Internal Validity ­ critical issue about validity is the requirement there should be no other plausible explanation of the results other than the presumed causes measured in your study ­ 6 ways to control for extraneous variables (and therefore help ensure internal validity): 1) direct manipulation 2) random assignment (randomization) 3) elimination or exclusion of extraneous variables 4) statistical control (covariate analysis) 5) through rational argument 6) analyze reliable scores Descriptions of Major Threats to Internal Validity Threat Description General Ambiguous temporal Lack of understanding about which of two variables precedence occurred first (i.e., which is cause and which is effect) History Specific events that take place concurrently with treatments Maturation Naturally occurring changes are confounded with treatment Testing Exposure to a test affects later scores on outcome variable Instrumentation The nature of measurement changes over time or conditions Attrition Loss of cases over conditions, groups, or time Regression When cases selected for extreme scores obtain less extreme scores on the outcome variable Multiple-group Studies Selection Groups differ before treatment is given Treatment diffusion or Control cases learn about treatment or try to imitate imitation experiences of treated cases Compensatory rivalry Control cases learn about treatment and become competitive with treated cases Compensatory equalization Cases in one condition demand to be assigned to the of treatment other condition or be compensated Resentful demoralization Control cases learn about treatment and become resentful or withdraw from study Novelty and disruption Cases respond extraordinarily well to a novel treatment, or effects
More Less

Related notes for PSYC 3380

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.