|
|
@ -281,7 +281,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
** t-test
|
|
|
|
** t-test for means :slide:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
*** Testing if the mean is different from a specified value (say zero) :slide:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#+name: ttest1
|
|
|
|
|
|
|
|
#+begin_src R :results output list org
|
|
|
|
|
|
|
|
readRDS("plfsdata/plfsacjdata.rds")->worker
|
|
|
|
|
|
|
|
worker$standardwage->worker$wage
|
|
|
|
|
|
|
|
worker->t9
|
|
|
|
|
|
|
|
t.test(t9$wage)
|
|
|
|
|
|
|
|
#+end_src
|
|
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ttest1
|
|
|
|
#+RESULTS: ttest1
|
|
|
|
#+begin_src org
|
|
|
|
#+begin_src org
|
|
|
@ -296,40 +306,38 @@
|
|
|
|
- 291.031
|
|
|
|
- 291.031
|
|
|
|
#+end_src
|
|
|
|
#+end_src
|
|
|
|
|
|
|
|
|
|
|
|
#+name: ttest1
|
|
|
|
|
|
|
|
#+begin_src R :results output list org
|
|
|
|
|
|
|
|
readRDS("plfsdata/plfsacjdata.rds")->worker
|
|
|
|
|
|
|
|
worker$standardwage->worker$wage
|
|
|
|
|
|
|
|
worker->t9
|
|
|
|
|
|
|
|
t.test(t9$wage)
|
|
|
|
|
|
|
|
#+end_src
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
*** Testing equality of means :slide:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
+ Here we test if the mean wages of men and women are equal.
|
|
|
|
|
|
|
|
|
|
|
|
#+name: ttest2
|
|
|
|
#+name: ttest2
|
|
|
|
#+begin_src R :results output
|
|
|
|
#+begin_src R :results output list org
|
|
|
|
subset(worker,sex!=3)->t9
|
|
|
|
subset(worker,sex!=3)->t9
|
|
|
|
factor(t9$sex)->t9$sex
|
|
|
|
factor(t9$sex)->t9$sex
|
|
|
|
t.test(wage~sex,data=t9)
|
|
|
|
t.test(wage~sex,data=t9)
|
|
|
|
#+end_src
|
|
|
|
#+end_src
|
|
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ttest2
|
|
|
|
#+RESULTS: ttest2
|
|
|
|
#+begin_example
|
|
|
|
#+begin_src org
|
|
|
|
|
|
|
|
- Welch Two Sample t-test
|
|
|
|
|
|
|
|
- data: wage by sex
|
|
|
|
|
|
|
|
- t = 79.02, df = 13483, p-value < 0.00000000000000022
|
|
|
|
|
|
|
|
- alternative hypothesis: true difference in means is not equal to 0
|
|
|
|
|
|
|
|
- 95 percent confidence interval:
|
|
|
|
|
|
|
|
- 104.6563 109.9805
|
|
|
|
|
|
|
|
- sample estimates:
|
|
|
|
|
|
|
|
- mean in group 1 mean in group 2
|
|
|
|
|
|
|
|
- 310.8974 203.5790
|
|
|
|
|
|
|
|
#+end_src
|
|
|
|
|
|
|
|
|
|
|
|
Welch Two Sample t-test
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
data: wage by sex
|
|
|
|
** Testing for equality of proportions :slide:
|
|
|
|
t = 79.02, df = 13483, p-value < 0.00000000000000022
|
|
|
|
|
|
|
|
alternative hypothesis: true difference in means is not equal to 0
|
|
|
|
|
|
|
|
95 percent confidence interval:
|
|
|
|
|
|
|
|
104.6563 109.9805
|
|
|
|
|
|
|
|
sample estimates:
|
|
|
|
|
|
|
|
mean in group 1 mean in group 2
|
|
|
|
|
|
|
|
310.8974 203.5790
|
|
|
|
|
|
|
|
#+end_example
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
+ Here we test if proportion of person who have passed high school is different for men and women
|
|
|
|
|
|
|
|
|
|
|
|
#+name: proptest1
|
|
|
|
#+name: proptest1
|
|
|
|
#+begin_src R :results output
|
|
|
|
#+begin_src R :results output list org
|
|
|
|
subset(worker,sex!=3)->t9
|
|
|
|
subset(worker,sex!=3)->t9
|
|
|
|
as.numeric(t9$gen_edu_level)->t9$gen_edu_level
|
|
|
|
as.numeric(t9$gen_edu_level)->t9$gen_edu_level
|
|
|
|
factor(t9$sex)->t9$sex
|
|
|
|
factor(t9$sex)->t9$sex
|
|
|
@ -338,18 +346,18 @@ mean in group 1 mean in group 2
|
|
|
|
prop.test(a$schooled,b$all)
|
|
|
|
prop.test(a$schooled,b$all)
|
|
|
|
#+end_src
|
|
|
|
#+end_src
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#+CAPTION: Results of test for equality of proportions of men and women who have passed secondary school
|
|
|
|
#+CAPTION: Results of test for equality of proportions of men and women who have passed secondary school
|
|
|
|
#+RESULTS: proptest1
|
|
|
|
#+RESULTS: proptest1
|
|
|
|
#+begin_example
|
|
|
|
#+begin_src org
|
|
|
|
|
|
|
|
- 2-sample test for equality of proportions with continuity correction
|
|
|
|
2-sample test for equality of proportions with continuity correction
|
|
|
|
- data: a$schooled out of b$all
|
|
|
|
|
|
|
|
- X-squared = 847.73, df = 1, p-value < 0.00000000000000022
|
|
|
|
data: a$schooled out of b$all
|
|
|
|
- alternative hypothesis: two.sided
|
|
|
|
X-squared = 847.73, df = 1, p-value < 0.00000000000000022
|
|
|
|
- 95 percent confidence interval:
|
|
|
|
alternative hypothesis: two.sided
|
|
|
|
- -0.1694726 -0.1525728
|
|
|
|
95 percent confidence interval:
|
|
|
|
- sample estimates:
|
|
|
|
-0.1694726 -0.1525728
|
|
|
|
- prop 1 prop 2
|
|
|
|
sample estimates:
|
|
|
|
- 0.09245986 0.25348253
|
|
|
|
prop 1 prop 2
|
|
|
|
#+end_src
|
|
|
|
0.09245986 0.25348253
|
|
|
|
|
|
|
|
#+end_example
|
|
|
|
|
|
|
|