paradigm shift and measurement issues of subjective well being
TRANSCRIPT
PARADIGM SHIFT AND MEASUREMENT ISSUES OF SUBJECTIVE WELL-BEING.
Debdulal Dutta Roy
Psychology Research Unit
Indian Statistical Institute, Kolkata
WHAT IS SWB ? , DIFFERENTIAL PERSPECTIVES
QOL
SWLS
POS
NEG
HAPPINESS
PWB
Dr. D. Dutta Roy, ISI., Kolkata. Venue: National Seminar on‘Wellbeing across Lifespan’ from 25 – 27 October, 2017
Legend
❏ QOL - WHO
❏ SWLS-Diener and
others (1985)
❏ Positive and Negative
Affect -watson (1988)
❏ Happiness: Peter Hills
and Argyle (2002)
❏ Psychological well being
- Ryff and Ryan Hedonistic distance:
❖ Both QOL and SWLS are
judgment oriented..more
experiential and cognive.
❖ POS and NEG are
affective.
❖ Happiness and PWB are
from humanistic
approach.
Paradigm shift
Hypothesis driven
•Literature Review & Hypothesis formulation•Sampling and structured data collection•Guided data analysis and theory development
Psychoinformatics (Data Driven)
•No Hypothesis but research questions•Data warehouse•Data retrieving•Data cleaning•Data mining•Pattern recognition•Discovery of Knowledge
Hypothesis Driven Model
Reliability
Reliable SWB score = SWB score - Measurement ErrorMeasurement error is broadly classified into two - Systematic and Random. Presence of errors affects the validation of instrument and related theories.
Error margin
Factors affecting the width of the confidence interval include the size of the sample, the confidence level, and the variability in the sample.
A larger sample size normally will lead to a better estimate of the population parameter.
Systematic errors
Items of the instrument may suffer from fixed errors. PANAS is commonly used instrument to assess subjective well-being. It is assumed that SWB has affective component. PANAS measures the positive and negative feeling component of SWB. Confirmatory factor analysis shows good discriminant validity. But some items of PANAS measure motivation not feeling (Diener, 2002).
Random errors
A random error, as the name suggests, is random in nature and very difficult to predict. It occurs because there are a very large number of parameters beyond the control of the experimenter that may interfere with the results of the experiment.
For example, mood and motivation of respondent affects scores.
Minimizing Measurement Error
• Pilot test the instrument, get feedback regarding extent of easiness or difficulty from respondents and how test environment affects the performance.
• Train the interviewers and observers about standard instruction, double check the data whether respondent misses any thing or not.
• Machine checking the data. • Use multiple measures and check relationship.• Random sampling • Increase in sample size.• Good rapport system.
Experimental design
• True experimental designs that involve experimenter manipulation of the independent variable and experimenter control over the assignment of participants to treatment conditions.
• It includes several Randomized group designs like one way group design, Block design, Latin square design, Factorial design.
Study: Effect of muscular relaxation on SWB of Schizophrenia.
Pre-post or post https://www.ncbi.nlm.nih.gov/pubmed/21402653
Quassi-Experimental design
• Ex-post facto research is systematic empirical inquiry in which the scientist does not have direct control of independent variables because their manifestations have already occurred or because they are inherently not manipulated.
Study: Effect of Diabetes Self Management Educational Training Program on patient attitudes to diabetes and their relations with the depression were explored.
Regression
• Regression is a statistical measure to determine the strength of the relationship between one dependent variable (usually denoted by Y) and a series of other changing variables (known as independent variables).
• A. Simple regressionB. Multiple regressionC. Stepwise multiple regressionD. Path analysisE. Structural equation modellingF. Covariates
Path-Analysis: CFA of Positive and Negative affective Schedule
Confirmatory factor analysis and temporal invariance of the Positive and Negative Affect Schedule (PANAS)
Structural equation model
•Structural equation models are often used to assess unobservable 'latent' constructs.
•They often invoke a measurement model that defines latent variables using one or more observed variables, and a structural model that imputes relationships between latent variables.
Path diagram for Mediational Analysis
• A path diagram that illustrates the mediational relationship and indicates beta weights is most useful.
Discriminant function analysis
• Discriminant function analysis is a statistical analysis to predict a categorical dependent variable (called a grouping variable) by one or more continuous or binary independent variables (called predictor variables).
• The main purpose of a discriminant function analysis is to predict group membership based on a linear combination of the interval variables.
• The procedure begins with a set of observations where both group membership and the values of the interval variables are known.
• Discriminant function analysis is reversed of multivariate analysis of variance (MANOVA). In MANOVA, the independent variables are the groups and the dependent variables are the predictors.
The Strong Discriminating Predictors
Categorical grouping
Correspondence map
Data Driven Model
Text Mining
• Research Question
• Data Reservoir: Select noise free search engines where in research answers are available.
• Data Cleaning: Select abstracts using inclusion and exclusion criteria.
• Coding and Node construction.
• Text classification using frequency of research.
• Pattern recognition.
• Discovery of Knowledge.
Thank You