PSY 3128 Lecture Notes - Lecture 4: Discriminant Validity, Convergent Validity, Structural Equation Modeling
5 Jun 2018
School
Department
Course
Professor
Multiple Regression Analysis: the predictor variables are regarded as equivalent to the independent
variables, and the variable that is predicted is regarded as eqivalent to a dependent variable. Can
still not determine causality but you can make stronger inferences. (Core establishment of
Logistic Regression: researchers test the likelihood of an individual reciving a score on a discrete
yes-no variable. A group of investigators may want to test out the probability that a person will
recive a diagnosis of cardiovascular disease or not.
Mediation: which the correlation between two variables ic compared with and without their joint
correlation to a third variable. (ie. Edication, life satisfaction, and health status).
Moderation: when two variables both have an influence on the third but not with eachother.
Path Analysis: researchers test all possible correlations among a set of variables to see if they can
be explained by a single model.
Latent variable: which is a statistical composite of several variables that were actually measured.
(ie. Three measures of life satisfaction rather than one)
In structural equation modelling (SEM), researchers test models involving relationships that
include latent variables. As in path analysis, they propse a set of relationships among variables,
but some are directily measured and others are constructed as latent variables.
- Used to assess the relationships among variables collected at one point in time.
Hierarchaical Linear Modelling, individual patterns of change are examined over time rather than
simply comparing mean scores of people at different ages. This is important in longitudinal
research.
- Soley looking at overall mean scores fail to capture the individual variation.
Types of Research Methods
Laboratory Studies: participants are tested in a systematic fashion using standardized procedures.
- Ability to control for extraneous variables.
- A limitation of the laboratory study is the inability to apply the stimuli presented to
real-life experiences of most adults.
- High on internal validity, low on external validity.
Qualitative Studies
Researchers explore a phenomeonon of interest in an open ended fashion. The qualitative method
allows for the exploration of such complex relationships outside of the narrow restrictions and
assumptions of quantitative methods.
- An analysis of life history information
- Provides resarchers with an alternative wy to test their hpothesis
Archival Research: investigators use existing resources that contain data relevant to aquestion
about aging.
Survey Method: to gain information about a sample that can then be generalized to a larger
population. Survey are typically short and easily administered with simple rating scales to use for
answers.
Epidemiology is the study of the distribution and determinants of health-related states or events
(including disease), and the application of this study to the control of diseases and other health
problems.
Prevelance statistics provide estimates of the percentage of people who have ever had symptoms
in a particular period.
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Multiple regression analysis: the predictor variables are regarded as equivalent to the independent variables, and the variable that is predicted is regarded as eqivalent to a dependent variable. Can still not determine causality but you can make stronger inferences. (core establishment of. Logistic regression: researchers test the likelihood of an individual reciving a score on a discrete yes-no variable. A group of investigators may want to test out the probability that a person will recive a diagnosis of cardiovascular disease or not. Mediation: which the correlation between two variables ic compared with and without their joint correlation to a third variable. (ie. edication, life satisfaction, and health status). Moderation: when two variables both have an influence on the third but not with eachother. Path analysis: researchers test all possible correlations among a set of variables to see if they can be explained by a single model.
