Stata Introduction , Short

1
Stata Introduction , Short

• Hein Stigum
• Presentation, data and programs at
• http//folk.uio.no/heins/

Dec-09
H.S.
1
2
Why Stata

• Pro
• Aimed at epidemiology
• Many methods, growing
• Graphics
• Structured, Programmable
• Coming soon to a course near you
• Con
• Memorygtfile size
• Copy tables

Dec-09
H.S.
2
3
Interface
4
Interface
Dec-09
H.S.
4
5
Menu
Dec-09
H.S.
5
6
Do Editor

• New
• Ctrl-8, doedit or
• Run
• Mark commands, Ctrl-D to do (execute)

Dec-09
H.S.
6
7
Do-file example
Dec-09
H.S.
7
8
Syntax

• Syntax
• bysort varlist command varlist if exp in
  range, opts
• Examples
• mean age
• mean age if sex1
• bysort sex summarize age
• summarize age ,detail

Dec-09
H.S.
8
9
Data handling
10
Import data

• Using SPSS 14.0
• Save as, Stata Version 8 SE

Dec-09
H.S.
10
11
Use and save data

• Open data
• set memory 200m
• use C\Course\Myfile.dta, clear
• Describe
• describe describe all variables
• list x1 x2 in 1/20 list obs nr 1 to 20
• Save data
• save C\Course\Myfile.dta ,replace

Dec-09
H.S.
11
12
Use data from web

• webuse file use data from Stata homepage
• webuse set http//www.med.uio.no/imb/stat/kursfil
  er/
• set homepage
• webuse birth1 data for exercise 1

Dec-09
H.S.
12
13
Generate, replace

• Index
• generate index0
• replace index1 if sex1 agegt30
• Young/Old
• generate old(agegt50)
• Serial numbers, lags
• gen id_n
• gen lagage _n-1

if agelt.
Dec-09
H.S.
13
14
Dates

• From numeric to date
• ex m12, d2, y1987
• generate bdatemdy(m,d,y)
• format bdate td
• From string to date
• ex bstr01.12.1987
• generate bdatedate(bstr,DMY)
• format bdate td

Dec-09
H.S.
14
15
Missing

• Obs!!!
• Missing values are large numbers
• agegt30 will include missing.
• agegt30 if agelt. will not.
• Test
• replace x0 if (x.)
• Remove
• drop if age.
• Change
• replace educ. if educ99

Dec-09
H.S.
15
16
Describe missing

• Summarize variables
• Missing in tables

Dec-09
H.S.
16
17
Help

• General
• help command
• findit keyword search Statanet
• Examples
• help table
• findit aflogit

Dec-09
H.S.
17
18
Summing up

• Use do files
• Mark, Ctrl-D to do (execute)
• Syntax
• command varlist if exp in range , options
• Missing
• agegt30 if agelt.
• generate old(agegt50) if agelt.
• Help
• help describe

Dec-09
H.S.
18
19
Descriptive
20
Descriptive

• Continuous

summarize weight, det details

• Categorical

tabulate bullied, nolab show coding
21
Other descriptives
tabstat mAge, stat( N min p50 mean max)
by(parity)
Dec-09
H.S.
21
22
Graphics
23
Twoway plots

• Syntax
• twoway (plot1, opts) (plot2, opts), opts
• One plot
• kdensity x Distribution plot
• scatter y x Scatter plot
• Overlaid plots
• twoway (kdensity y if x1) (kdensity y if x2)
• twoway (scatter y x) (fpfitci y x) (lfit y x)

Dec-09
H.S.
23
24
twoway ( kdensity weight if sex1, lcolor(blue)
) /// ( kdensity weight if sex2, lcolor(red
) )
Dec-09
H.S.
24
25
twoway (scatter y x) (fpfitci y x) (lfit y x)
Dec-09
H.S.
25
26
Titles
scatter weight gest, title("title")
subtitle("subtitle") /// xtitle("xtitle")
ytitle("ytitle") note("note")
Dec-09
H.S.
26
27
Bivariate analysis
28
2 independent samples
Do boys and girls have the same mean birth weight?
twoway ( kdensity weight if sex1, lcolor(blue)
) /// ( kdensity weight if sex2,
lcolor(red) )
Equal means? Equal variance?
Dec-09
H.S.
28
29
2 independent samples test
ttest weight, by(sex) unequal ttest w1 w2, paired
Dec-09
H.S.
29
30
Crosstables
Are boys bullied as much as girls?
Dec-09
H.S.
30