Table 6

Results of logistic regression of equation (1) including the square term for age

VariablesCoefficientMarginal effects
Age0.050**0.001**
(0.025)(0.001)
Age squared−0.000***−0.000***
(0.000)(0.000)
Bank trust – yes0.303**0.0065**
(0.124)(0.003)
High school0.905**0.0142***
(0.362)(0.004)
Tertiary education1.761***0.045***
(0.380)(0.008)
Coloured−0.421**−0.008***
(0.172)(0.003)
Asian−0.767***−0.013***
(0.238)(0.003)
White−0.318**−0.007**
(0.159)(0.003)
Female−0.170*−0.004*
(0.098)(0.002)
Rural−0.041−0.001
(0.160)(0.003)
R1–R1,9991.169***0.016***
(0.259)(0.002)
R2,000–R5,9992.410***0.055***
(0.262)(0.006)
R6,000 and above2.805***0.081***
(0.280)(0.012)
LSM 3–4−0.810*−0.013
(0.484)(0.011)
LSM 5–6−0.105−0.002
(0.449)(0.011)
LSM 7–80.4450.013
(0.464)(0.012)
LSM 9–100.803*0.029**
(0.481)(0.015)
Married0.0090.001
(0.112)(0.003)
2010 year2.421***0.040***
(0.211)(0.006)
2012 year2.413***0.039***
(0.199)(0.004)
2016 year2.449***0.040***
(0.189)(0.004)
Constant−8.084*** 
(0.637) 
Observations11,76211,762
Region FEYesYes
Year FEYesYes
Pseudo R-squared0.310 

Note(s): Robust standard errors are reported in parentheses. *, **, and *** denote significance at the 10%, 5% and 1% level, respectively. Reference categories: No trust in banks, primary school education, Black, male, urban, no income, LSM 1–2, unmarried

Source(s): Authors’ own work

or Create an Account

Close Modal
Close Modal