Gereltuya Altankhuyag, LecturerStatistician, UNSIAP

1
STATA Third group training course in application
of information and communication technology to
production and dissemination of official
statistics 10 May 11July 2007
Gereltuya Altankhuyag, Lecturer/Statistician,
UNSIAP gereltuya_at_unsiap.or.jp
2
Getting Started

• There are three ways of executing commands
• Using menu-bar
• Using dialog box (db)
• Using Syntax
• It is preferable to use Syntax

3
Getting Started dialog box

• Dialog box db is the command-line way to launch a
  dialog for a Stata command.
• Syntax
• db varname
• For instance db sum

4
Getting Started dialog box
5
Basic commands to inspect datasets

• The following commands are used to inspect
  datasets
• codebook
• count
• describe
• list
• summarize
• table
• tabstat

6
Basic commands to inspect datasets

• codebook
• It examines
• the variable names,
• labels,
• data to produce a codebook describing the dataset
• It distinguishes/reports the standard missing
  values
• Syntax
• codebook varlist if in , option
• Example codebook
• codebook region

7
Basic commands to inspect datasets

• option
• all provides a complete report excluding mv
• header adds header to the top of the output,
  name, date
• notes lists any notes attached to the variables
• mv determines the pattern of missing values
• Examples codebook region hhlandd famsize, all
• codebook region hhlandd
  famsize, header
• codebook region hhlandd
  famsize, notes
• codebook region hhlandd
  famsize, mv

8
Basic commands to inspect datasets

• count
• It counts the number of observations that satisfy
  the specified conditions. If no conditions are
  specified, count displays the number of
  observations in the data.
• Syntax
• count if in
• For instance count
• count if famsizegt5

9
Basic commands to inspect datasets

• describe
• It produces a summary of the dataset
• In memory
• Of the data stored in a Stata-format dataset
• Syntax
• Data in memory
• describe varlist , describem_options
• Data in file
• describe varlist using filename,
  describef_options
• Example des
• des region famsize toilet

10
Basic commands to inspect datasets

• options
• simple display only variable names
• short display only general information
• detail display additional details
• fullname do not abbreviate variable names
• numbers display vriable number along with name

11
Basic commands to inspect datasets

• list
• It displays values of variables
• Syntax
• list
• list varlist if in , options
• Example list
• list region famsize toilet
• list region famsize toilet in
  1/15
• list region if famsizegt5 in 1/15

12
Basic commands to inspect datasets

• summarize
• It calculates and displays a variety of summary
  statistics. If no varlist is specified, summary
  statistics are calculated for all the variables
  in the dataset.
• Syntax
• summarize
• summarize varlist if in weight ,
  options
• Example sum
• sum in 1/15
• sum region famsize toilet
• sum region famsize toilet awweight

13
Basic commands to inspect datasets

• options
• detail - produces additional statistics
  including skewness, kurtosis, the four smallest
  and four largest values, and various percentiles.
• meanonly - which is allowed only when detail is
  not specified, suppresses the display of results
  and calculation of the variance.
• format - requests that the summary statistics
  be displayed using the display formats associated
  with the variables,
• separator() - specifies how often to insert
  separation lines into the output. The default is
  separator(5), meaning that a line is drawn after
  every 5 variables. separator(10) would draw a
  line after every 10 variables. separator(0)
  suppresses the separation line.

14
Basic commands to inspect datasets

• NOTE
• Commands and output are shown in Results window.

• When MORE message is shown,

press GO to continue display
or X button to stop display
15
Basic commands to inspect datasets

• NOTE
• We may specify a variable list for a range of
  variables
• des region toilet
• sum region hhlandd
• list thana - famsize

16
Basic commands to inspect datasets

• NOTE
• We may use the menus
• for DESCRIBE
• Data ? Describe Data ?Describe Variables in
  Memory
• for SUMMARIZE
• Statistics ? Summaries, Tables Tests?Summary
  Statistics ?Summary Statistics
• Data ? Describe Data ?Summary Statistics

17
Basic commands to inspect datasets

• There are 5 types of table command
• table
• tabstat
• tabulate one-way
• tabulate two-way
• tabulate summarize

18
Basic commands to inspect datasets

• table
• It calculates and displays tables of statistics.
• Syntax
• table rowvar colvar supercolvar if in
  weight , options
• Main options
• contents - specifies the contents of the table's
  cells select up to 5 statistics
• by(superrowvarlist) - superrow variables up to
  4 variables.

19
Basic commands to inspect datasets

• Examples
• table region, c(mean famsize median hhandd)
• table region, by(sexhead) c(mean famsize median
  hhandd)

20
Basic commands to inspect datasets

• tabstat
• It displays table of summary statistics
• Syntax
• tabstat varlist if in weight , options
• Main options
• by(varname) - group statistics by variable
• statistics(statname ...) - report specified
  statistics

21
Basic commands to inspect datasets

• Examples
• tabstat region, stats(mean range)
• tabstat region, by( sexhead) stat(min mean max)
  col (stat)

22
Basic commands to inspect datasets

• tabulate one-way (tab1)
• It produces one-way tables of frequency counts.
• Syntax
• tabulate varname if in weight , options
• It produces one-way tables of frequency counts.
• tab1 varlist if in weight , tab1_options
• It produces a one-way tabulation for each
  variable specified in varlist.

23
Basic commands to inspect datasets

• Examples
• tabulate toilet
• tabulate region
• tabulate hhelec
• tabulate sexhead
• tab1 region toilet hhelec sexhead
• Note please see the differences!!

24
Basic commands to inspect datasets

• tabulate two-way (tab2)
• It produces two-way tables of frequencies
• Syntax
• tabulate varname1 varname2 if in weight ,
  options
• It produces two-way tables of frequency counts,
  along with various measures of association,
  including the common Pearson's chi-squared, the
  likelihood-ratio chi-squared, Cramér's V,
  Fisher's exact test, Goodman etc.

25
Basic commands to inspect datasets

• tab2 varlist if in weight , options
• It produces all possible two-way tabulations of
  the variables specified in varlist.
• Examples
• tabulate region toilet, row
• tabulate region sexhead, row col chi2
• tabulate region toilet, all exact
• tab2 region sexhead toilet
• tab2 region sexhead toilet, all exact

26
Basic commands to inspect datasets

• Tabulate summarize
• It produces one- and two-way tables (breakdowns)
  of means and standard deviations.
• Syntax
• tabulate varname1 varname2 if in weight
  , summarize

27
Basic commands to inspect datasets

• Examples
• One-way tables
• tabulate region, summarize( hhlandd)
• tabulate region aweightweight, summarize(
  toilet)
• Two-way tables
• tabulate region sexhead, summarize( hhlandd)
• tabulate region sexhead aweightweight,
  summarize( hhlandd)

28
Basic commands to create and change variables,
labels etc.

• generate
• It creates a new variable. The values of the
  variable are specified by exp.
• Syntax
• generate type newvarlblname exp if in
• Examples
• gen agehead2ageheadagehead
• gen agehead3ageheadagehead if sexhead1

29
Basic commands to create and change variables,
labels etc.

• replace
• It changes the contents of an existing variable.
  Because replace alters data, the command cannot
  be abbreviated.
• Syntax
• replace oldvar exp if in , nopromote
• Examples
• replace agehead30 if region2

30
Basic commands to create and change variables,
labels etc.

• egen
• It creates newvar of the optionally specified
  storage type equal to fcn(arguments). Here fcn()
  is a function specifically written for egen.
• Syntax
• egen type newvar fcn(arguments) if in ,
  options

31
Basic commands to create and change variables,
labels etc.

• Examples
• egen age4mean( agehead)
• egen testmedian( weight- d_bank)

32

• To be continued.

Please perform EXERCISE 2