Correlational finding on Happiness and Change in source of income
Subject code: I01aa02d

StudyHanda et al. (2014): study KE 2007
TitleSubjective Well-Being, Risk perceptions and Time Discounting: Evidence from a Large-Scale Cash Transfer Programme.
SourceUnicef WorkingPaper, 2014, No. 2014-02, Florence, Italy
URLhttp://www.unicef-irc.org/publications/717
PublicPoor households: benefactories of a welfare program and controls, Kenya, 2007
SampleProbability multi-stage cluster sample
Non-ResponseAttrition: 2007-2009:17%;2009-2011 5%
Respondents N =1805

Correlate
Author's labelTreatment
Page in Source 29,30,39
Our classificationChange in source of income, code I01aa02d
Operationalization
Inclusion in income support programme for poor 
households with vulnerable
1 yes (Treatment)
0  no (Control)
Within each of seven districts two locations were 
randomized for immediate implementation and the 
remaining two served as control sites.
Remarks
The support programme aims at encouraging fostering and 
retention of children and promoting human capital 
development by providing regular cash transfers to 
families living with OVC  (Orphans and vulnerable 
children). The programme is being abbreviated to CT-OVC 
(Cash Transfer programmes for OVC).

Observed Relation with Happiness
Happiness
Measure
StatisticsElaboration/Remarks
M-PL-u-sq-v-5-aD%=+ p < .01
% happy (strongly agree and agree)

- Treatment (inclusion) 49,6%
- Control               42,2%
Difference              +7,4%
M-PL-u-sq-v-5-dD%=+ p < .025
- Treatment (inclusion) 49,5%
- Control               43,4%
Difference              +6,1%
O-SLu-u-sq-v-5-bD%=+ p < .025
- Treatment (inclusion) 44,4%
- Control               38,6%
Difference              +5,8%
M-PL-u-sq-v-5-ab=+.07 p < .05
Weighted linear probability regression (WLS).
M-PL-u-sq-v-5-db=+.06 ns
O-SLu-u-sq-v-5-bb=+.06 ns
M-PL-u-sq-v-5-ab=+.03 ns
Ordinary linear probability least squares 
regression. (OLS)
M-PL-u-sq-v-5-db=+.03 ns
O-SLu-u-sq-v-5-bb=+.06 p < .05
b's are controlled for 
- Age (x100), Age squared (x1000)
- Sex
- Household position
- Literacy
- Chronic Illness
- Current Handicap


Appendix 1: Happiness measures used
CodeFull Text
M-PL-u-sq-v-5-aSelfreport on single question:

I enjoy life
5 strongly agree
4
3
2
1 strongly disagree
M-PL-u-sq-v-5-dSelfreport on sing;e question:

I experience positive feelings in my life
5 strongly agree
4
3
2
1 strongly disagree
O-SLu-u-sq-v-5-bSelfreport on single question:

I am satisfied with my life
1 fully disagree
2 disagree
3 don't know
4 agree
5 fully agree


Appendix 2: Statistics used
SymbolExplanation
bREGRESSION COEFFICIENT (non-standardized) by LEAST SQUARES (OLS)
Type: test statistic
Measurement level: Correlate: metric, Happiness: metric
Theoretical range: unlimited

Meaning:
b > 0 A higher correlate level corresponds with a higher happiness rating on average.
B < 0 A higher correlate level corresponds with a lower happiness rating on average.
B = 0 Not any correlation with the relevant correlate.
D%DIFFERENCE in PERCENTAGES
Type: descriptive statistic only.
Measurement level: Correlate level: dichotomous, but nominal or ordinal theoretically possible as well. Happiness level: dichotomous
Range: [-100; +100]

Meaning: the difference of the percentages happy people at two correlate levels.
Source:
Ruut Veenhoven, World Database of Happiness, Collection of Correlational Findings, Erasmus University Rotterdam.
https://worlddatabaseofhappiness.eur.nl