A researcher wants to empirically test if a sample of retail borrowers’

debt to income ratio (DEBTINC) significantly differs by their default status (defaulted vs. non- defaulted; coded by 1 and 0). The researcher has performed a paired t- test in STATA. The test result is shown in Table 4.15.

a) How will you interpret the tabulated result? Identify the one- tail and two- tail test results.

b) Read the two- tail test, what will be your conclusion? Whether the difference is statistically significant?

c) Which group has relatively higher debt to income ratio? Is this statistically significant?

d) What are control group and the treatment group? What is the STATA command for running this test?

Transcribed Image Text:

Table 4.15 Reading t-Test Result in STATA Two-sample t-test with equal variances Group | Obs Mean Std. Err. Std. Dev. [95% Conf. Interval] 0| 952 8.076891 .1747247 1 548 13.14745 .3171213 5.391044 7.42362 7.734 8.419781 12.52452 13.77037 Combined 1500 diff -5.070554 diff mean(0)-mean(1) = Ho: diff=0 Pr(T |t|)=0.0000 Pr(T> t)=1.0000 Ha: diff!= 0 t = -15.2254 Degrees of freedom = 1498 Ha: diff> 0