*Biostata 212: lecture 3
* data cleaning notes


cd "/Users/kristenaiemjoy/Box Sync/_Teaching/Biostat 212/Biostat212.2018/Lectures/3. Cleaning"


*import acupuncture_raw data set 


import delimited acupuncture_raw.csv, clear 


***Rename variable
rename f1 hfreq_bl

* add a label
label variable hfreq_bl "headache score baseline" 

*label values
tab group
label define grouplabel 1 "intervention" 0 "control" 
label values group grouplabel 
tab group


numlabel, add
tab group


labelbook


*Outliers

spikeplot age 

sum age, detail

list id sex age if age >120

*one person's age (id = 363) is actually 52, i checked his original file
replace age = 52 if id==363

spikeplot age 

sum age 

*missing data
misstable sum 
sum posths

mvdecode _all, mv(-99)
sum posths


*Generagte new variables

gen one = 1

gen newid = _n, before(id)

drop newid


gen blank = .


gen severemigraine = (migraine==1 & basehs>50) 

browse migraine basehs severemigraine


gen severemigrainepost = (migraine==1 & posths>50) 
replace severemigrainepost = . if posths==.

browse migraine posths severemigrainepost

**creating quantiles
browse basehs

xtile basehsQ = basehs, nq(4)

bysort basehsQ: sum basehs


**generate row mean
egen meanhs = rowmean(basehs posths oneyrhs)



egen meanhs2 = mean(basehs)


browse basehs posths oneyrhs meanhs


**generate new age variable
recode age (min/49 = 1 "less than 50") (50/max = 2 "50 and older"), gen(age2)




recode age (min/49 = 1 ) (50/max = 2 ), gen(age3)




browse age age2 age3



**string to categorical variables
browse withdrawal_reason

encode withdrawal_reason, gen(dropout)



numlabel, add


tab dropout