Stata 1, Graphics

1
Stata 1, Graphics

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

2
Why use graphs?
3
Problem example

• Lunch meals per week
• Table of means (around 5 per week)
• Linear regression

4
Problem example 2

• Iron level
• Both linear and logistic regression
• Opposite results

5
Structure of talk

• Order
• Work/presentation plots
• Plot types
• Outcome type
• Focus
• The right plot
• The commands

6
Plot types
7
Plottypes
8
Continuous outcome
9
Univariate

• Density
• kdensity weight

• Boxplot
• graph hbox weight

10
Density with box information
11
Bivariate

• Scatter
• scatter weight gest

12
Scatter and density plots for many types of data
13
Twoway density

• Syntax
• graph twoway (plot1, opts) (plot2, opts), opts
• One plot
• kdensity x
• Two plots overlaid
• twoway ( kdensity weight if sex1, lcolor(blue)
  ) ///
• ( kdensity weight if sex2, lcolor(red) )
• Side by side
• twoway ( kdensity weight ), by(sex)

14
Twoway scatter fit

• Syntax
• graph twoway (plot1, opts) (plot2, opts), opts
• Examples
• scatter y x
• twoway (scatter y x) (fpfitci y x) (lfit y x)

Fitlines
15
Continuous by 3 categories

• Is birth weight the same over parity?

Density plot
Scatterplot
Equal means? Linear effect? Outliers?
Equal variances?
16
Continuous by 3 categories
Scatterplot

• twoway (scatter weight parity3) (fpfitci
  weight parity3) (lfit weight
  parity3) , legend(off)
• Look for
• Outliers (all analyses)
• Non-linear effects (regression)

17
Continuous by 3 categories
Density plot

• twoway
• (kdensity weight if parity30, lcol(black))
• (kdensity weight if parity31, lcol(blue))
• (kdensity weight if parity32, lcol(red))
• , yscale(off)
• Look for
• Different locations
• Different shapes (ANOVA, regression)

18
Twoway density options

• kdensity x, normal add normal curve
• kdensity x, area(400) frequency, N400
• display r(width) previous width
• kdensity x, width(80) less smoothing

19
Twoway options

• Syntax
• graph twoway (plot1, opts) (plot2, opts), opts
• Options
• lcolor(red) line color
• lpattern(.-) line pattern
• lwidth(2) line width 2
• legend(
• ring(0) legend inside plot
• pos(2) legend at 2 oclock position
• col(1) legends in 1 column
• label(1 First) legend label plot 1
• label(2 Second) legend label plot 2
• )

20
Continuous by continuous

• twoway (scatter weight gest) (fpfitci weight
  gest) (lfit weight gest)
• Look for
• Main effect (line)
• Non-linearity (smooth)
• outliers

21
More twoway options

• Syntax
• graph twoway (plot1, opts) (plot2, opts), opts
• Options
• msize(0.5) marker size
• mlabel(id) marker label variable id
• xline(24) line at x24
• scale(1.5) all elements 1.5larger

22
Mark outliers

• twoway (scatter weight gest) (scatter weight
  gest if gestgt400, mlabel(id))

23
Titles, legend, labels and scale
24
Titles
scatter weight gest, title("title")
subtitle("subtitle") /// xtitle("xtitle")
ytitle("ytitle") note("note")
25
Legend

• , legend( ring(0) pos(11) col(1) label(1
  Boys, N283) label(2 Girls, N270) )
• , legend(off)

26
Axis scale and label
scatter weight gest, xscale(range(250 310))
/// xlabel( 250(20)310 281)
27
Categorical outcome
28
Comparing means or proportions
29
Comparing means/prop. better

• preserve save data
• collapse (mean) v1 v2 v3, by(parity) aggregate
• list list the new data
• twoway (scatter v1 parity) (line v1 parity) ///
• (scatter v2 parity) (line v2 parity) ///
• (scatter v3 parity) (line v3 parity)
• restore restore original data

30
Binary outcome
31
Scatter binary by countinuous
32
Binary with rug and smooth

• gen yy.
• replace yy 0.02(lowbw0) 0.98(lowbw1)
• twoway (rspike yy lowbw gest) (fpfit
  lowbw gest)

33
Regression results