Correlational finding on Happiness and Change over life time
Subject code: H04ab02a

StudyThurnher (1983): study US 1969
TitleTurning Points and Developmental Change: Subjective and 'Objective' Assessments.
SourceAmerican Journal of Orthopsychiatry, 1983, Vol. 53, 52 - 60
PublicPeople in transition, followed 8 years, Metropolis USA, 1969-77
Non-ResponseSample attrition: 17%
Respondents N =180

Author's labelChange in happiness
Page in Source 56
Our classificationChange over life time, code H04ab02a
Index (HAP 3.2) consisting of:
- "Dissatisfied" and "unhappy"   responses on the Block 
(1961)     Adjective Rating List
-  Overall happiness
-  Present-year score on the   Life-Evaluation Chart
Assessed at T1 (1969) and T2 (1977)

Observed Relation with Happiness
O-Sum-u-mq-*-0-aAoV= ns
T2 Happiness by change in happiness (T2-T1).
Change in happiness over the 8 years period 
indicated by including 'time' in ANOVA.
No interaction with age and sex.

A-BB-cw-mq-v-4-dAoV=+ p < .01
T2 Happiness by change in happiness (T2-T1).
Change in happiness over the 8 years period 
indicated by including 'time' in ANOVA.
No interaction with age and sex.

A-BB-cw-mq-v-4-dE=+.18 p < .01

Appendix 1: Happiness measures used
CodeFull Text
A-BB-cw-mq-v-4-dSelfreport on 8 questions.

"During the past week, did you ever feel.....?"
A very lonely
B restless
C bored
D depressed
E on top of the world
F exited or interested
G pleased about accomplishment
H proud

Answer options:
1 never
2 once
3 several times
4 often

-Positive Affect Score (PAS): E+F+G+H
-Negative Affect Score (NAS): A+B+C+D
-Affect Balance Score (ABS): PAS-NAS+13

Name: Bradburn's Affect Balance Scale (modified version)
O-Sum-u-mq-*-0-aSelfreport on 3 questions:

A. " Dissatisfied" and "Unhappy" responses on the Block (1961) Adjective Rating List.

B. Overall happiness. Single direct question: "Taking all things together, how would you say things are these days? Would you say you are .......?"
3 very happy
2 pretty happy
1 not too happy

C. Present-year score on Life-Evaluation Chart, ranging from:
1 low
9 high

Appendix 2: Statistics used
Type: statistical procedure
Measurement level: Correlate(s): nominal, Happiness: metric.
In an ANOVA, the total happiness variability, expressed as the sum of squares, is split into two or more parts, each of which is assigned to a source of variability. At least one of those sources is the variability of the correlate, in case there is only one, and always one other is the residual variability, which includes all unspecified influences on the happiness variable. Each sum of squares has its own number of degrees of freedom (df), which sum up to Ne -1 for the total variability. If a sum of squares (SS) is divided by its own number of df, a mean square (MS) is obtained. The ratio of two correctly selected mean squares has an F-distribution under the hypothesis that the corresponding association has a zero-value.

NOTE: A significantly high F-value only indicates that, in case of a single correlate, the largest of the c mean values is systematically larger than the smallest one. Conclusions about the other pairs of means require the application of a Multiple Comparisons Procedure (see e.g. BONFERRONI's MULTIPLE COMPARISON TEST, DUNCAN's MULTIPLE RANGE TEST or STUDENT-NEWMAN-KEULS)
ECORRELATION RATIO (Elsewhere sometimes called h or ETA)
Type: test statistic
Measurement level: Correlate: nominal or ordinal, Happiness: metric
Range: [0; 1]

Meaning: correlate is accountable for E x 100 % of the variation in happiness.
E = 0 knowledge of the correlate value does not improve the prediction quality of the happiness rating.
E = 1 knowledge of the correlate value enables an exact prediction of the happiness rating
Ruut Veenhoven, World Database of Happiness, Collection of Correlational Findings, Erasmus University Rotterdam.