{smcl}
{com}{sf}{ul off}{txt}{.-}
      name:  {res}<unnamed>
       {txt}log:  {res}/Users/eric/Work/MB/ATCR/200/Labs/lab 1.smcl
  {txt}log type:  {res}smcl
 {txt}opened on:  {res}18 Sep 2018, 06:54:15
{txt}
{com}. 
. /* Read in the data posted on the class web site.  These data come from a 
> study of voluntary counseling and testing (VCT) for HIV at Mulago Hospital 
> in Kampala, Uganda. */
. 
. use vct.dta, clear
{txt}
{com}. 
. *Stata lets us look at a spreadsheet of the data: */
. 
. browse
{txt}
{com}. 
. /* First see what variables are in the dataset.  Check how many observations 
> and variables the dataset includes. */
. 
. describe

{txt}Contains data from {res}vct.dta
{txt}  obs:{res}         3,389                          
{txt} vars:{res}            13                          23 Jul 2018 10:11
{txt} size:{res}        71,169                          
{txt}{hline}
              storage   display    value
variable name   type    format     label      variable label
{hline}
{p 0 48}{res}{bind:age            }{txt}{bind: double  }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:auditc         }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:cd4            }{txt}{bind: int     }{bind:{txt}%11.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:cd4_cat        }{txt}{bind: byte    }{bind:{txt}%11.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:female         }{txt}{bind: byte    }{bind:{txt}%9.0g     }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:hiv            }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:hungry         }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:lastalc        }{txt}{bind: byte    }{bind:{txt}%20.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:n_adults       }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:n_child        }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:n_support      }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:religion       }{txt}{bind: byte    }{bind:{txt}%10.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{p 0 48}{bind:sex            }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}{p_end}
{txt}{hline}
Sorted by: {res}hiv
{txt}
{com}. 
. /* Now get brief summary statistics for all the variables in the dataset. The 
> full command we'll use is summarize, but we can shorten that to save typing. */
. 
. sum

{txt}    Variable {c |}        Obs        Mean    Std. Dev.       Min        Max
{hline 13}{c +}{hline 57}
{space 9}age {c |}{res}      3,387    31.73267    9.846937      17.52      79.85
{txt}{space 6}auditc {c |}{res}      3,244    .6390259    1.483416          0         12
{txt}{space 9}cd4 {c |}{res}        999    329.2332    266.1177          1       1932
{txt}{space 5}cd4_cat {c |}{res}        999    1.618619    .9377913          0          3
{txt}{space 6}female {c |}{res}      3,389    .5417527    .4983272          0          1
{txt}{hline 13}{c +}{hline 57}
{space 9}hiv {c |}{res}      3,389    .2959575    .4565393          0          1
{txt}{space 6}hungry {c |}{res}      3,321    3.603132    .7817434          1          4
{txt}{space 5}lastalc {c |}{res}      3,377    .9227125    .9101892          0          2
{txt}{space 4}n_adults {c |}{res}      3,384    1.664598    1.737786          0         12
{txt}{space 5}n_child {c |}{res}      3,382    1.850089    1.924868          0         12
{txt}{hline 13}{c +}{hline 57}
{space 3}n_support {c |}{res}      3,372    3.907177    3.227549          0         20
{txt}{space 4}religion {c |}{res}      3,387    3.781518    1.994997          1          8
{txt}{space 9}sex {c |}{res}      3,389    1.541753    .4983272          1          2
{txt}
{com}. 
. /* Now do a little data management to make the data easier to use. First assign some variable labels */
. 
. label var age "Age"
{txt}
{com}. label var auditc "Audit score, last 3 months"
{txt}
{com}. label var cd4 "CD4 count"
{txt}
{com}. label var cd4_cat "CD4 count"
{txt}
{com}. label var hiv "HIV status"
{txt}
{com}. label var hungry "How often household members go hungry"
{txt}
{com}. label var lastalc "Last time used alcohol"
{txt}
{com}. label var female "female sex"
{txt}
{com}. label var n_adults "# adults in household"
{txt}
{com}. label var n_child "# people <18yo in household"
{txt}
{com}. label var n_support "# people supported financially"
{txt}
{com}. label var religion "Religion"
{txt}
{com}. 
. /* Now add some missing value labels. A easy-to-remember convention is to use 
> the variable name as the name of the value label. (Stata doesn't have any 
> problem with this). Other easy-to-remember conventions will also work (e.g., 
> add an underscore to the variable name).*/
. 
. label define yesno 0 "no" 1 "yes"
{txt}
{com}. label values female yesno
{txt}
{com}. label define sex 1 "men" 2 "women"
{txt}
{com}. label values sex sex
{txt}
{com}. label define hiv 0 "HIV-" 1 "HIV+"
{txt}
{com}. label values hiv hiv
{txt}
{com}. label define cd4_cat 0 "<50" 1 "51-250" 2 "251-500" 3 ">500"
{txt}
{com}. label values cd4_cat cd4_cat
{txt}
{com}. label define hungry 1 "often" 2 "sometimes" 3 "seldom" 4 "never"
{txt}
{com}. label values hungry hungry
{txt}
{com}. label define lastalc 0 "never" 1 ">1 year ago" 2 "within last year"
{txt}
{com}. label values lastalc lastalc
{txt}
{com}. label define religion 1 "Protestant" 2 "Catholic" 3 "Saved" 4 "Moslem" 8 "Other"
{txt}
{com}. label values religion religion
{txt}
{com}. 
. /* You can use these commands to get information about the values labels for 
> a variable:*/
. 
. codebook religion

{txt}{hline}
{res}religion{right:Religion}
{txt}{hline}

{col 19}type:  numeric ({res}byte{txt})
{ralign 22:label}:  {res:religion}, but {res:2} nonmissing values are not labeled

{col 18}range:  [{res}1{txt},{res}8{txt}]{col 55}units:  {res}1
{col 10}{txt}unique values:  {res}5{col 51}{txt}missing .:  {res}2{txt}/{res}3,389

{txt}{col 13}tabulation:  Freq.   Numeric  Label
{col 21}{res}     1,002{col 33}       1{col 43}{txt}Protestant
{col 21}{res}     1,047{col 33}       4{col 43}{txt}Moslem
{col 21}{res}       576{col 33}       5{col 43}
{col 21}       679{col 33}       6{col 43}
{col 21}        83{col 33}       8{col 43}{txt}Other
{col 21}{res}         2{col 33}       .{col 43}
{txt}
{com}. label list religion
{txt}religion:
{res}           1 Protestant
           2 Catholic
           3 Saved
           4 Moslem
           8 Other
{txt}
{com}. 
. /* Note the use of the indicator female for sex, coded 0 = no and 1 = yes. 
> Indicators coded like this have several advantages:
>         * the mean value of the indicator gives the proportion of women in the dataset
>         * this is the coding required for binary outcomes in logistic models
>         * unlike a variable for sex, coded 1 = male 2 = female, the indicator does 
>           not require us to remember the coding and value labels
>         
> Now take another look at what we have. The value labels should show up in the 
> browser. */
. 
. des

{txt}Contains data from {res}vct.dta
{txt}  obs:{res}         3,389                          
{txt} vars:{res}            13                          23 Jul 2018 10:11
{txt} size:{res}        71,169                          
{txt}{hline}
              storage   display    value
variable name   type    format     label      variable label
{hline}
{p 0 48}{res}{bind:age            }{txt}{bind: double  }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}Age{p_end}
{p 0 48}{bind:auditc         }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}Audit score, last 3 months{p_end}
{p 0 48}{bind:cd4            }{txt}{bind: int     }{bind:{txt}%11.0g    }{space 1}{bind:         }{bind:  }{res}{res}CD4 count{p_end}
{p 0 48}{bind:cd4_cat        }{txt}{bind: byte    }{bind:{txt}%11.0g    }{space 1}{bind:cd4_cat  }{bind:  }{res}{res}CD4 count{p_end}
{p 0 48}{bind:female         }{txt}{bind: byte    }{bind:{txt}%9.0g     }{space 1}{bind:yesno    }{bind:  }{res}{res}female sex{p_end}
{p 0 48}{bind:hiv            }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:hiv      }{bind:  }{res}{res}HIV status{p_end}
{p 0 48}{bind:hungry         }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:hungry   }{bind:  }{res}{res}How often household members go hungry{p_end}
{p 0 48}{bind:lastalc        }{txt}{bind: byte    }{bind:{txt}%20.0g    }{space 1}{bind:lastalc  }{bind:  }{res}{res}Last time used alcohol{p_end}
{p 0 48}{bind:n_adults       }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}# adults in household{p_end}
{p 0 48}{bind:n_child        }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}# people <18yo in household{p_end}
{p 0 48}{bind:n_support      }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}# people supported financially{p_end}
{p 0 48}{bind:religion       }{txt}{bind: byte    }{bind:{txt}%10.0g    }{space 1}{bind:religion }{bind:  }{res}{res}Religion{p_end}
{p 0 48}{bind:sex            }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:sex      }{bind:  }{res}{res}{p_end}
{txt}{hline}
Sorted by: {res}hiv
{txt}
{com}. sum

{txt}    Variable {c |}        Obs        Mean    Std. Dev.       Min        Max
{hline 13}{c +}{hline 57}
{space 9}age {c |}{res}      3,387    31.73267    9.846937      17.52      79.85
{txt}{space 6}auditc {c |}{res}      3,244    .6390259    1.483416          0         12
{txt}{space 9}cd4 {c |}{res}        999    329.2332    266.1177          1       1932
{txt}{space 5}cd4_cat {c |}{res}        999    1.618619    .9377913          0          3
{txt}{space 6}female {c |}{res}      3,389    .5417527    .4983272          0          1
{txt}{hline 13}{c +}{hline 57}
{space 9}hiv {c |}{res}      3,389    .2959575    .4565393          0          1
{txt}{space 6}hungry {c |}{res}      3,321    3.603132    .7817434          1          4
{txt}{space 5}lastalc {c |}{res}      3,377    .9227125    .9101892          0          2
{txt}{space 4}n_adults {c |}{res}      3,384    1.664598    1.737786          0         12
{txt}{space 5}n_child {c |}{res}      3,382    1.850089    1.924868          0         12
{txt}{hline 13}{c +}{hline 57}
{space 3}n_support {c |}{res}      3,372    3.907177    3.227549          0         20
{txt}{space 4}religion {c |}{res}      3,387    3.781518    1.994997          1          8
{txt}{space 9}sex {c |}{res}      3,389    1.541753    .4983272          1          2
{txt}
{com}. browse
{txt}
{com}. 
. /* Note that CD4 count is present only for the 30% of participants who are HIV+.
> 
> ********************************************************************************
> Creating and modifying new variables 
> 
> To create a new variable, use the generate command; to modify it, use the 
> replace command, and to drop a variable, use the drop command. In making 
> variables, you will often need to use so-called logical operators:
>         equal:                          ==
>         not equal:              ~= or ~=
>         and:                                    &
>         or:                                             |
>         greater:                        > or >=
>         less:                                   < or <=
> Missing numeric values are denoted . (for missing character strings use "").  
> Note that missing numeric values are stored as a very large number, (always 
> the largest in the dataset).  As a result, if you are missing age values for 
> 2 persons in the data set, and you create a new variable that includes all 
> participants with age>30, you will include the 2 with missing data.
> 
> Example: AUDIT-C is a scale measuring alcohol consumption, ranging from 0-12.  
> For those not currently drinking (on this survey it is the past 3 months) the 
> score is 0, for those drinking the score is 1-12.  To make a new variable that
> represents any alcohol consumption we can use this following code:  */
. 
. gen alc_any=0 if auditc==0
{txt}(966 missing values generated)

{com}. replace alc_any=1 if auditc>0 & auditc !=. 
{txt}(821 real changes made)

{com}. label var alc_any "Any alcohol use"
{txt}
{com}. label values alc_any yesno // value label yesno is already part of the dataset 
{txt}
{com}. * check to make sure this worked
. tab auditc alc_any, missing     

     {txt}Audit {c |}
    score, {c |}
    last 3 {c |}         Any alcohol use
    months {c |}        no        yes          . {c |}     Total
{hline 11}{c +}{hline 33}{c +}{hline 10}
         0 {c |}{res}     2,423          0          0 {txt}{c |}{res}     2,423 
{txt}         1 {c |}{res}         0        363          0 {txt}{c |}{res}       363 
{txt}         2 {c |}{res}         0        134          0 {txt}{c |}{res}       134 
{txt}         3 {c |}{res}         0        118          0 {txt}{c |}{res}       118 
{txt}         4 {c |}{res}         0        108          0 {txt}{c |}{res}       108 
{txt}         5 {c |}{res}         0         44          0 {txt}{c |}{res}        44 
{txt}         6 {c |}{res}         0         13          0 {txt}{c |}{res}        13 
{txt}         7 {c |}{res}         0         10          0 {txt}{c |}{res}        10 
{txt}         8 {c |}{res}         0          7          0 {txt}{c |}{res}         7 
{txt}         9 {c |}{res}         0         15          0 {txt}{c |}{res}        15 
{txt}        10 {c |}{res}         0          4          0 {txt}{c |}{res}         4 
{txt}        11 {c |}{res}         0          3          0 {txt}{c |}{res}         3 
{txt}        12 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}         . {c |}{res}         0          0        145 {txt}{c |}{res}       145 
{txt}{hline 11}{c +}{hline 33}{c +}{hline 10}
     Total {c |}{res}     2,423        821        145 {txt}{c |}{res}     3,389 
{txt}
{com}. 
. /* The second condition ensures that missings are kept as missing.  A better 
> way to do this is to use the recode command, which will handle the missing 
> values correctly: */
. 
. drop alc_any
{txt}
{com}. recode auditc (0=0 "no") (2/max=1 "yes"), gen(alc_any)
{txt}(458 differences between auditc and alc_any)

{com}. label var alc_any "Any alcohol use" 
{txt}
{com}. * check to make sure this worked
. tab auditc alc_any, missing   

     {txt}Audit {c |}
    score, {c |}
    last 3 {c |}         Any alcohol use
    months {c |}        no        yes          . {c |}     Total
{hline 11}{c +}{hline 33}{c +}{hline 10}
         0 {c |}{res}     2,423          0          0 {txt}{c |}{res}     2,423 
{txt}         1 {c |}{res}         0        363          0 {txt}{c |}{res}       363 
{txt}         2 {c |}{res}         0        134          0 {txt}{c |}{res}       134 
{txt}         3 {c |}{res}         0        118          0 {txt}{c |}{res}       118 
{txt}         4 {c |}{res}         0        108          0 {txt}{c |}{res}       108 
{txt}         5 {c |}{res}         0         44          0 {txt}{c |}{res}        44 
{txt}         6 {c |}{res}         0         13          0 {txt}{c |}{res}        13 
{txt}         7 {c |}{res}         0         10          0 {txt}{c |}{res}        10 
{txt}         8 {c |}{res}         0          7          0 {txt}{c |}{res}         7 
{txt}         9 {c |}{res}         0         15          0 {txt}{c |}{res}        15 
{txt}        10 {c |}{res}         0          4          0 {txt}{c |}{res}         4 
{txt}        11 {c |}{res}         0          3          0 {txt}{c |}{res}         3 
{txt}        12 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}         . {c |}{res}         0          0        145 {txt}{c |}{res}       145 
{txt}{hline 11}{c +}{hline 33}{c +}{hline 10}
     Total {c |}{res}     2,423        821        145 {txt}{c |}{res}     3,389 
{txt}
{com}. 
. /* We can also use recode and replace to make a more complex indicator for 
> unhealthy alcohol consumption, using different cutoff for men (>=4) and 
> women (>=3): */
. 
. recode auditc (min/2=0 "no") (3/max=1 "yes"), gen(alc_unh)
{txt}(821 differences between auditc and alc_unh)

{com}. replace alc_unh = 0 if female==0 & auditc==3
{txt}(69 real changes made)

{com}. label var alc_unh "Unhealthy alcohol use"
{txt}
{com}. * check to make sure this worked
. bysort female: tab auditc alc_unh, m

{txt}{hline}
-> female = no

     Audit {c |}
    score, {c |}
    last 3 {c |}      Unhealthy alcohol use
    months {c |}        no        yes          . {c |}     Total
{hline 11}{c +}{hline 33}{c +}{hline 10}
         0 {c |}{res}     1,042          0          0 {txt}{c |}{res}     1,042 
{txt}         1 {c |}{res}       166          0          0 {txt}{c |}{res}       166 
{txt}         2 {c |}{res}        57          0          0 {txt}{c |}{res}        57 
{txt}         3 {c |}{res}        69          0          0 {txt}{c |}{res}        69 
{txt}         4 {c |}{res}         0         71          0 {txt}{c |}{res}        71 
{txt}         5 {c |}{res}         0         34          0 {txt}{c |}{res}        34 
{txt}         6 {c |}{res}         0          9          0 {txt}{c |}{res}         9 
{txt}         7 {c |}{res}         0          8          0 {txt}{c |}{res}         8 
{txt}         8 {c |}{res}         0          5          0 {txt}{c |}{res}         5 
{txt}         9 {c |}{res}         0         12          0 {txt}{c |}{res}        12 
{txt}        10 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}        11 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}        12 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}         . {c |}{res}         0          0         74 {txt}{c |}{res}        74 
{txt}{hline 11}{c +}{hline 33}{c +}{hline 10}
     Total {c |}{res}     1,334        145         74 {txt}{c |}{res}     1,553 

{txt}{hline}
-> female = yes

     Audit {c |}
    score, {c |}
    last 3 {c |}      Unhealthy alcohol use
    months {c |}        no        yes          . {c |}     Total
{hline 11}{c +}{hline 33}{c +}{hline 10}
         0 {c |}{res}     1,381          0          0 {txt}{c |}{res}     1,381 
{txt}         1 {c |}{res}       197          0          0 {txt}{c |}{res}       197 
{txt}         2 {c |}{res}        77          0          0 {txt}{c |}{res}        77 
{txt}         3 {c |}{res}         0         49          0 {txt}{c |}{res}        49 
{txt}         4 {c |}{res}         0         37          0 {txt}{c |}{res}        37 
{txt}         5 {c |}{res}         0         10          0 {txt}{c |}{res}        10 
{txt}         6 {c |}{res}         0          4          0 {txt}{c |}{res}         4 
{txt}         7 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}         8 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}         9 {c |}{res}         0          3          0 {txt}{c |}{res}         3 
{txt}        10 {c |}{res}         0          2          0 {txt}{c |}{res}         2 
{txt}        11 {c |}{res}         0          1          0 {txt}{c |}{res}         1 
{txt}         . {c |}{res}         0          0         71 {txt}{c |}{res}        71 
{txt}{hline 11}{c +}{hline 33}{c +}{hline 10}
     Total {c |}{res}     1,655        110         71 {txt}{c |}{res}     1,836 

{txt}
{com}. 
. /* Note the abbreviated name for the unhealthy alcohol use indicator.  Stata 
> does allow long, explicit variable names, with some limits, but they can be 
> tedious to use in programming; better to encode the extra information in the 
> variable label.   Note also that all the alcohol variables we have made start 
> with the same stem alc_, also with a view towards making them easier to remember.  
> 
> Finally, we can use recode to categorize the continuous variable, age.  In 
> doing this, we can use the ordering of the elements of the command to control 
> whether the values at each cutpoint are put into the lower or upper category. 
> Specifically, values equal to a cutpoint get put into the class defined by the 
> element where the cutpoint is first encountered. We will first code age 
> categories <=20, >20 to <=30, >30 to <=40, >40 to <=50, and >50. */
. 
. qui recode age (min/20=1 "<=20") (20/30=2 ">20 to 30") (30/40=3 ">30 to 40") ///
>         (40/50=4 ">40 to 50") (50/max=5 ">50"), gen(age_cat)
{txt}
{com}. label var age_cat "Age"
{txt}
{com}. * check this
. tabstat age, by(age_cat) s(min max)

{txt}Summary for variables: age
{col 6}by categories of: age_cat (Age)

{ralign 9:age_cat} {...}
{c |}       min       max
{hline 10}{c +}{hline 20}
{ralign 9:<=20} {...}
{c |}{...}
 {res}    17.52        20
{txt}{ralign 9:>20 to 30} {...}
{c |}{...}
 {res}    20.01        30
{txt}{ralign 9:>30 to 40} {...}
{c |}{...}
 {res}    30.01        40
{txt}{ralign 9:>40 to 50} {...}
{c |}{...}
 {res}    40.01     49.99
{txt}{ralign 9:>50} {...}
{c |}{...}
 {res}    50.01     79.85
{txt}{hline 10}{c +}{hline 20}
{ralign 9:Total} {...}
{c |}{...}
 {res}    17.52     79.85
{txt}{hline 10}{c BT}{hline 20}

{com}. 
. /* To include the cutpoints in the upper category, we can reverse the order of 
> the elements of the command: */
. 
. drop age_cat
{txt}
{com}. qui recode age  (50/max=5 "50+") (40/50=4 "40 to <50") (30/40=3 "30 to <40") ///
>         (20/30=2 "20 to <30") (min/20=1 "<20") , gen(age_cat)
{txt}
{com}. label var age_cat "Age"
{txt}
{com}. * check this
. tabstat age, by(age_cat) s(min max)

{txt}Summary for variables: age
{col 6}by categories of: age_cat (Age)

{ralign 9:age_cat} {...}
{c |}       min       max
{hline 10}{c +}{hline 20}
{ralign 9:<20} {...}
{c |}{...}
 {res}    17.52     19.98
{txt}{ralign 9:20 to <30} {...}
{c |}{...}
 {res}       20     29.99
{txt}{ralign 9:30 to <40} {...}
{c |}{...}
 {res}       30     39.99
{txt}{ralign 9:40 to <50} {...}
{c |}{...}
 {res}       40     49.99
{txt}{ralign 9:50+} {...}
{c |}{...}
 {res}    50.01     79.85
{txt}{hline 10}{c +}{hline 20}
{ralign 9:Total} {...}
{c |}{...}
 {res}    17.52     79.85
{txt}{hline 10}{c BT}{hline 20}

{com}. 
. /* Put the variables in alphabetical order, compress anything stored wastefully, 
> get a final look at the dataet, and save the modified dataset. */
. 
. compress
  {txt}variable {bf}age_cat{sf} was {bf}{res}double{sf}{txt} now {bf}{res}byte{sf}
{txt}  (23,723 bytes saved)

{com}. aorder
{txt}
{com}. 
. /* Finally, save the revised dataset.  It's good practice never to write over 
> the input dataset. */
. 
. save vct_revised, replace
{txt}file vct_revised.dta saved

{com}. 
. /* Now we will use the revised dataset to do more exploration. */
. 
. use vct_revised.dta, clear
{txt}
{com}. 
. /* Briefly remind yourself of what is in the dataset. Check how many observations 
> and variables the dataset includes. */
. 
. describe

{txt}Contains data from {res}vct_revised.dta
{txt}  obs:{res}         3,389                          
{txt} vars:{res}            16                          18 Sep 2018 06:54
{txt} size:{res}        81,336                          
{txt}{hline}
              storage   display    value
variable name   type    format     label      variable label
{hline}
{p 0 48}{res}{bind:age            }{txt}{bind: double  }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}Age{p_end}
{p 0 48}{bind:age_cat        }{txt}{bind: byte    }{bind:{txt}%9.0g     }{space 1}{bind:age_cat  }{bind:  }{res}{res}Age{p_end}
{p 0 48}{bind:alc_any        }{txt}{bind: byte    }{bind:{txt}%9.0g     }{space 1}{bind:alc_any  }{bind:  }{res}{res}Any alcohol use{p_end}
{p 0 48}{bind:alc_unh        }{txt}{bind: byte    }{bind:{txt}%9.0g     }{space 1}{bind:alc_unh  }{bind:  }{res}{res}Unhealthy alcohol use{p_end}
{p 0 48}{bind:auditc         }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}Audit score, last 3 months{p_end}
{p 0 48}{bind:cd4            }{txt}{bind: int     }{bind:{txt}%11.0g    }{space 1}{bind:         }{bind:  }{res}{res}CD4 count{p_end}
{p 0 48}{bind:cd4_cat        }{txt}{bind: byte    }{bind:{txt}%11.0g    }{space 1}{bind:cd4_cat  }{bind:  }{res}{res}CD4 count{p_end}
{p 0 48}{bind:female         }{txt}{bind: byte    }{bind:{txt}%9.0g     }{space 1}{bind:yesno    }{bind:  }{res}{res}female sex{p_end}
{p 0 48}{bind:hiv            }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:hiv      }{bind:  }{res}{res}HIV status{p_end}
{p 0 48}{bind:hungry         }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:hungry   }{bind:  }{res}{res}How often household members go hungry{p_end}
{p 0 48}{bind:lastalc        }{txt}{bind: byte    }{bind:{txt}%20.0g    }{space 1}{bind:lastalc  }{bind:  }{res}{res}Last time used alcohol{p_end}
{p 0 48}{bind:n_adults       }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}# adults in household{p_end}
{p 0 48}{bind:n_child        }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}# people <18yo in household{p_end}
{p 0 48}{bind:n_support      }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:         }{bind:  }{res}{res}# people supported financially{p_end}
{p 0 48}{bind:religion       }{txt}{bind: byte    }{bind:{txt}%10.0g    }{space 1}{bind:religion }{bind:  }{res}{res}Religion{p_end}
{p 0 48}{bind:sex            }{txt}{bind: byte    }{bind:{txt}%12.0g    }{space 1}{bind:sex      }{bind:  }{res}{res}{p_end}
{txt}{hline}
Sorted by: {res}female
{txt}
{com}. 
. /* Now get brief summary statistics for all the variables in the dataset. The 
> full command we'll use is summarize, but we can shorten to save typing. */
. 
. sum

{txt}    Variable {c |}        Obs        Mean    Std. Dev.       Min        Max
{hline 13}{c +}{hline 57}
{space 9}age {c |}{res}      3,387    31.73267    9.846937      17.52      79.85
{txt}{space 5}age_cat {c |}{res}      3,387    2.653085    .9790142          1          5
{txt}{space 5}alc_any {c |}{res}      3,244    .2530826    .4348449          0          1
{txt}{space 5}alc_unh {c |}{res}      3,244    .0786067    .2691653          0          1
{txt}{space 6}auditc {c |}{res}      3,244    .6390259    1.483416          0         12
{txt}{hline 13}{c +}{hline 57}
{space 9}cd4 {c |}{res}        999    329.2332    266.1177          1       1932
{txt}{space 5}cd4_cat {c |}{res}        999    1.618619    .9377913          0          3
{txt}{space 6}female {c |}{res}      3,389    .5417527    .4983272          0          1
{txt}{space 9}hiv {c |}{res}      3,389    .2959575    .4565393          0          1
{txt}{space 6}hungry {c |}{res}      3,321    3.603132    .7817434          1          4
{txt}{hline 13}{c +}{hline 57}
{space 5}lastalc {c |}{res}      3,377    .9227125    .9101892          0          2
{txt}{space 4}n_adults {c |}{res}      3,384    1.664598    1.737786          0         12
{txt}{space 5}n_child {c |}{res}      3,382    1.850089    1.924868          0         12
{txt}{space 3}n_support {c |}{res}      3,372    3.907177    3.227549          0         20
{txt}{space 4}religion {c |}{res}      3,387    3.781518    1.994997          1          8
{txt}{hline 13}{c +}{hline 57}
{space 9}sex {c |}{res}      3,389    1.541753    .4983272          1          2
{txt}
{com}. 
. /* Note how many people had CD4 counts.  Why is this less than the number of 
> observations? 
> 
> To get more information about continuous variables, add the detail option to 
> the summarize command. */
. 
. sum age cd4, detail

                             {txt}Age
{hline 61}
      Percentiles      Smallest
 1%    {res}    18.04          17.52
{txt} 5%    {res}    19.65          17.56
{txt}10%    {res}    21.15          17.57       {txt}Obs         {res}      3,387
{txt}25%    {res}    24.25           17.6       {txt}Sum of Wgt. {res}      3,387

{txt}50%    {res}    29.53                      {txt}Mean          {res} 31.73267
                        {txt}Largest       Std. Dev.     {res} 9.846937
{txt}75%    {res}    37.73          74.62
{txt}90%    {res}    45.89          75.33       {txt}Variance      {res} 96.96217
{txt}95%    {res}    50.42          78.29       {txt}Skewness      {res} 1.029901
{txt}99%    {res}    60.01          79.85       {txt}Kurtosis      {res} 3.974463

                          {txt}CD4 count
{hline 61}
      Percentiles      Smallest
 1%    {res}        5              1
{txt} 5%    {res}       14              2
{txt}10%    {res}       36              2       {txt}Obs         {res}        999
{txt}25%    {res}      130              2       {txt}Sum of Wgt. {res}        999

{txt}50%    {res}      283                      {txt}Mean          {res} 329.2332
                        {txt}Largest       Std. Dev.     {res} 266.1177
{txt}75%    {res}      463           1461
{txt}90%    {res}      659           1601       {txt}Variance      {res} 70818.64
{txt}95%    {res}      866           1804       {txt}Skewness      {res} 1.444705
{txt}99%    {res}     1182           1932       {txt}Kurtosis      {res} 6.518639
{txt}
{com}. 
. 
. ********************************************************************************
. 
. /* Exploratory analysis using descriptive statistics
> 
> The tabstat command gives easy summaries. Here we use the stat() option 
> to obtain the number of observations, mean, SD, minimum, 25th percentile, 
> median, 75th percentile, and maximum. The format option controls rounding of 
> the statistics. */
. 
. tabstat age cd4, stat(n mean sd min p25 p50 p75 max) format(%8.3g)

{txt}   stats {...}
{c |}{...}
       age       cd4
{hline 9}{c +}{hline 20}
{ralign 8:N} {...}
{c |}{...}
  {res}    3387       999
{txt}{ralign 8:mean} {...}
{c |}{...}
  {res}    31.7       329
{txt}{ralign 8:sd} {...}
{c |}{...}
  {res}    9.85       266
{txt}{ralign 8:min} {...}
{c |}{...}
  {res}    17.5         1
{txt}{ralign 8:p25} {...}
{c |}{...}
  {res}    24.3       130
{txt}{ralign 8:p50} {...}
{c |}{...}
  {res}    29.5       283
{txt}{ralign 8:p75} {...}
{c |}{...}
  {res}    37.7       463
{txt}{ralign 8:max} {...}
{c |}{...}
  {res}    79.9      1932
{txt}{hline 9}{c BT}{hline 20}

{com}. 
. /* Adding the option col(statistics) transposes the results. Also, we can use 
> the line break marker /// to tell stata that command continues after a hard 
> return. This is handy if you want to use a relatively narrow do-file editor 
> window. (Note that you can't use /// in the command window.) */
. 
. tabstat age cd4, stat(n mean sd min p25 p50 p75 max) ///
>         col(statistics) format(%8.3g)

{txt}{ralign 12:variable} {...}
{c |}         N      mean        sd       min       p25       p50       p75
{hline 13}{c +}{hline 70}
{ralign 12:age} {...}
{c |}{...}
  {res}    3387      31.7      9.85      17.5      24.3      29.5      37.7
{txt}{ralign 12:cd4} {...}
{c |}{...}
  {res}     999       329       266         1       130       283       463
{txt}{hline 13}{c BT}{hline 70}

{ralign 12:variable} {...}
{c |}       max
{hline 13}{c +}{hline 10}
{ralign 12:age} {...}
{c |}{...}
  {res}    79.9
{txt}{ralign 12:cd4} {...}
{c |}{...}
  {res}    1932
{txt}{hline 13}{c BT}{hline 10}

{com}.         
. * Add the by() option to see the statistics stratified by HIV status.
. tabstat age cd4, by(hiv) stat(n mean sd min p25 p50 p75 max) ///
>         col(statistics) format(%8.3g)

{txt}Summary for variables: age cd4
{col 6}by categories of: hiv (HIV status)

{ralign 6:hiv} {...}
{c |}         N      mean        sd       min       p25       p50       p75       max
{hline 7}{c +}{hline 80}
{ralign 6:HIV-} {...}
{c |}{...}
  {res}    2384      31.3      10.5      17.5      23.4      28.3      37.5      79.9
{space 6} {...}
{txt}{c |}{...}
  {res}       0         .         .         .         .         .         .         .
{txt}{hline 7}{c +}{hline 80}
{ralign 6:HIV+} {...}
{c |}{...}
  {res}    1003      32.7      8.05      17.6      26.8      31.4      38.1        70
{space 6} {...}
{txt}{c |}{...}
  {res}     999       329       266         1       130       283       463      1932
{txt}{hline 7}{c +}{hline 80}
{ralign 6:Total} {...}
{c |}{...}
  {res}    3387      31.7      9.85      17.5      24.3      29.5      37.7      79.9
{space 6} {...}
{txt}{c |}{...}
  {res}     999       329       266         1       130       283       463      1932
{txt}{hline 7}{c BT}{hline 80}

{com}. 
. /* The tabstat command can only be used to stratify by one by variable at a 
> time; tostratify by >1 variables, use the table command. */
. 
. table hiv female hungry, by(religion) c(mean age) format(%8.1f)

{txt}{hline 11}{c TT}{hline 53}
Religion   {c |} How often household members go hungry and female sex
and HIV    {c |} {hline 2} often {hline 1}    {hline 1} someti {hline 1}    {hline 1} seldom {hline 1}    {hline 2} never {hline 1}
status     {c |}   no   yes      no   yes      no   yes      no   yes
{hline 11}{c +}{hline 53}
Protestant {c |}
      HIV- {c |} {res}34.9  32.3    33.9  34.9    29.8  32.5    31.9  31.9
      {txt}HIV+ {c |} {res}38.3  32.6    33.5  31.1    39.5  34.2    35.4  31.4
{txt}{hline 11}{c +}{hline 53}
Moslem     {c |}
      HIV- {c |} {res}33.4  38.7    29.2  34.2    32.5  33.3    31.3  31.2
      {txt}HIV+ {c |} {res}34.0  36.2    33.9  29.9    33.8  31.1    34.1  30.5
{txt}{hline 11}{c +}{hline 53}
5          {c |}
      HIV- {c |} {res}24.9  34.4    30.1  28.4    26.1  32.5    29.5  30.3
      {txt}HIV+ {c |} {res}38.3  26.9    35.9  30.5    31.5  32.4    35.8  30.9
{txt}{hline 11}{c +}{hline 53}
6          {c |}
      HIV- {c |} {res}37.8  36.2    30.0  34.0    27.7  31.3    31.1  31.2
      {txt}HIV+ {c |} {res}43.6  33.4    35.9  33.1    38.7  31.8    34.9  30.0
{txt}{hline 11}{c +}{hline 53}
Other      {c |}
      HIV- {c |}     {res}          27.9  28.0    26.1  24.2    29.5  31.3
      {txt}HIV+ {c |}     {res}  39.6    39.5          46.5  37.1    35.0  32.8
{txt}{hline 11}{c BT}{hline 53}

{com}. 
. * To see how categorical variables relate to each other, use the tab command.  
. tab age_cat hiv, row
{txt}
{c TLC}{hline 16}{c TRC}
{c |} Key{col 18}{c |}
{c LT}{hline 16}{c RT}
{c |}{space 3}{it:frequency}{col 18}{c |}
{c |}{space 1}{it:row percentage}{col 18}{c |}
{c BLC}{hline 16}{c BRC}

           {c |}      HIV status
       Age {c |}      HIV-       HIV+ {c |}     Total
{hline 11}{c +}{hline 22}{c +}{hline 10}
       <20 {c |}{res}       196         24 {txt}{c |}{res}       220 
           {txt}{c |}{res}     89.09      10.91 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
 20 to <30 {c |}{res}     1,150        412 {txt}{c |}{res}     1,562 
           {txt}{c |}{res}     73.62      26.38 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
 30 to <40 {c |}{res}       576        394 {txt}{c |}{res}       970 
           {txt}{c |}{res}     59.38      40.62 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
 40 to <50 {c |}{res}       302        141 {txt}{c |}{res}       443 
           {txt}{c |}{res}     68.17      31.83 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
       50+ {c |}{res}       160         32 {txt}{c |}{res}       192 
           {txt}{c |}{res}     83.33      16.67 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
     Total {c |}{res}     2,384      1,003 {txt}{c |}{res}     3,387 
           {txt}{c |}{res}     70.39      29.61 {txt}{c |}{res}    100.00 
{txt}
{com}. tab female hiv, row
{txt}
{c TLC}{hline 16}{c TRC}
{c |} Key{col 18}{c |}
{c LT}{hline 16}{c RT}
{c |}{space 3}{it:frequency}{col 18}{c |}
{c |}{space 1}{it:row percentage}{col 18}{c |}
{c BLC}{hline 16}{c BRC}

           {c |}      HIV status
female sex {c |}      HIV-       HIV+ {c |}     Total
{hline 11}{c +}{hline 22}{c +}{hline 10}
        no {c |}{res}     1,175        378 {txt}{c |}{res}     1,553 
           {txt}{c |}{res}     75.66      24.34 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
       yes {c |}{res}     1,211        625 {txt}{c |}{res}     1,836 
           {txt}{c |}{res}     65.96      34.04 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
     Total {c |}{res}     2,386      1,003 {txt}{c |}{res}     3,389 
           {txt}{c |}{res}     70.40      29.60 {txt}{c |}{res}    100.00 
{txt}
{com}. tab hungry hiv, row
{txt}
{c TLC}{hline 16}{c TRC}
{c |} Key{col 18}{c |}
{c LT}{hline 16}{c RT}
{c |}{space 3}{it:frequency}{col 18}{c |}
{c |}{space 1}{it:row percentage}{col 18}{c |}
{c BLC}{hline 16}{c BRC}

 How often {c |}
 household {c |}
members go {c |}      HIV status
    hungry {c |}      HIV-       HIV+ {c |}     Total
{hline 11}{c +}{hline 22}{c +}{hline 10}
     often {c |}{res}        49         30 {txt}{c |}{res}        79 
           {txt}{c |}{res}     62.03      37.97 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
 sometimes {c |}{res}       246        134 {txt}{c |}{res}       380 
           {txt}{c |}{res}     64.74      35.26 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
    seldom {c |}{res}       209        112 {txt}{c |}{res}       321 
           {txt}{c |}{res}     65.11      34.89 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
     never {c |}{res}     1,841        700 {txt}{c |}{res}     2,541 
           {txt}{c |}{res}     72.45      27.55 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
     Total {c |}{res}     2,345        976 {txt}{c |}{res}     3,321 
           {txt}{c |}{res}     70.61      29.39 {txt}{c |}{res}    100.00 
{txt}
{com}. tab alc_any hiv, row
{txt}
{c TLC}{hline 16}{c TRC}
{c |} Key{col 18}{c |}
{c LT}{hline 16}{c RT}
{c |}{space 3}{it:frequency}{col 18}{c |}
{c |}{space 1}{it:row percentage}{col 18}{c |}
{c BLC}{hline 16}{c BRC}

       Any {c |}
   alcohol {c |}      HIV status
       use {c |}      HIV-       HIV+ {c |}     Total
{hline 11}{c +}{hline 22}{c +}{hline 10}
        no {c |}{res}     1,753        670 {txt}{c |}{res}     2,423 
           {txt}{c |}{res}     72.35      27.65 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
       yes {c |}{res}       540        281 {txt}{c |}{res}       821 
           {txt}{c |}{res}     65.77      34.23 {txt}{c |}{res}    100.00 
{txt}{hline 11}{c +}{hline 22}{c +}{hline 10}
     Total {c |}{res}     2,293        951 {txt}{c |}{res}     3,244 
           {txt}{c |}{res}     70.68      29.32 {txt}{c |}{res}    100.00 
{txt}
{com}. 
. /* Taking advantage of the 0-1 coding of the HIV indicator, we can use the 
> table command get HIV prevalence by several other variables at once; here we 
> do just age and sex. */
. 
. table age_cat female, c(mean hiv) format(%8.2f)

{txt}{hline 10}{c TT}{hline 11}
          {c |} female sex
      Age {c |}   no   yes
{hline 10}{c +}{hline 11}
      <20 {c |} {res}0.03  0.18
{txt}20 to <30 {c |} {res}0.15  0.35
{txt}30 to <40 {c |} {res}0.40  0.42
{txt}40 to <50 {c |} {res}0.35  0.29
      {txt}50+ {c |} {res}0.20  0.13
{txt}{hline 10}{c BT}{hline 11}

{com}. 
. ********************************************************************************
. 
. /* We can also use the Stata means command to calculate confidence intervals 
> for the means of continuous variables, both overall and within strata. */
. 
. mean age, cformat(%8.2f)
{res}
{txt}Mean estimation{col 35}Number of obs{col 51}= {res}     3,387

{txt}{hline 13}{c TT}{hline 11}{hline 11}{hline 14}{hline 12}
{col 14}{c |}       Mean{col 26}   Std. Err.{col 38}     [95% Con{col 51}f. Interval]
{hline 13}{c +}{hline 11}{hline 11}{hline 14}{hline 12}
{space 9}age {c |}{col 14}{res}{space 2}    31.73{col 26}{space 2}     0.17{col 37}{space 5}    31.40{col 51}{space 3}    32.06
{txt}{hline 13}{c BT}{hline 11}{hline 11}{hline 14}{hline 12}

{com}. mean age, over(female hiv) cformat(%8.2f)
{res}
{txt}Mean estimation{col 35}Number of obs{col 51}= {res}     3,387

         {txt}Over: female hiv
    _subpop_1: {res}no HIV-
    {txt}_subpop_2: {res}no HIV+
    {txt}_subpop_3: {res}yes HIV-
    {txt}_subpop_4: {res}yes HIV+

{txt}{hline 13}{c TT}{hline 11}{hline 11}{hline 14}{hline 12}
{col 1}        Over{col 14}{c |}       Mean{col 26}   Std. Err.{col 38}     [95% Con{col 51}f. Interval]
{hline 13}{c +}{hline 11}{hline 11}{hline 14}{hline 12}
{res}age          {txt}{c |}
{space 3}_subpop_1 {c |}{col 14}{res}{space 2}    30.99{col 26}{space 2}     0.31{col 37}{space 5}    30.39{col 51}{space 3}    31.60
{txt}{space 3}_subpop_2 {c |}{col 14}{res}{space 2}    35.17{col 26}{space 2}     0.39{col 37}{space 5}    34.39{col 51}{space 3}    35.94
{txt}{space 3}_subpop_3 {c |}{col 14}{res}{space 2}    31.68{col 26}{space 2}     0.30{col 37}{space 5}    31.10{col 51}{space 3}    32.27
{txt}{space 3}_subpop_4 {c |}{col 14}{res}{space 2}    31.15{col 26}{space 2}     0.32{col 37}{space 5}    30.53{col 51}{space 3}    31.77
{txt}{hline 13}{c BT}{hline 11}{hline 11}{hline 14}{hline 12}

{com}. 
. * To get, say, 90% confidence intervals, we can use the level option
. mean age, over(female hiv) level(90) cformat(%8.2f)
{res}
{txt}Mean estimation{col 35}Number of obs{col 51}= {res}     3,387

         {txt}Over: female hiv
    _subpop_1: {res}no HIV-
    {txt}_subpop_2: {res}no HIV+
    {txt}_subpop_3: {res}yes HIV-
    {txt}_subpop_4: {res}yes HIV+

{txt}{hline 13}{c TT}{hline 11}{hline 11}{hline 14}{hline 12}
{col 1}        Over{col 14}{c |}       Mean{col 26}   Std. Err.{col 38}     [90% Con{col 51}f. Interval]
{hline 13}{c +}{hline 11}{hline 11}{hline 14}{hline 12}
{res}age          {txt}{c |}
{space 3}_subpop_1 {c |}{col 14}{res}{space 2}    30.99{col 26}{space 2}     0.31{col 37}{space 5}    30.48{col 51}{space 3}    31.50
{txt}{space 3}_subpop_2 {c |}{col 14}{res}{space 2}    35.17{col 26}{space 2}     0.39{col 37}{space 5}    34.52{col 51}{space 3}    35.81
{txt}{space 3}_subpop_3 {c |}{col 14}{res}{space 2}    31.68{col 26}{space 2}     0.30{col 37}{space 5}    31.19{col 51}{space 3}    32.18
{txt}{space 3}_subpop_4 {c |}{col 14}{res}{space 2}    31.15{col 26}{space 2}     0.32{col 37}{space 5}    30.63{col 51}{space 3}    31.67
{txt}{hline 13}{c BT}{hline 11}{hline 11}{hline 14}{hline 12}

{com}. 
. /* The means command could also be used to get means and confidence intervals 
> for binary variables coded 0-1, but a better approach is the ci prop command, 
> with the exact option.  This avoids confidence limits less than 0 or more 
> than 1. */ 
. 
. ci prop hiv, exact

{txt}{col 58}{hline 2} Binomial Exact {hline 2}
    Variable {c |}        Obs  Proportion    Std. Err.       [95% Conf. Interval]
{hline 13}{c +}{hline 63}
         hiv {c |}{col 16}{res}     3,389{col 29} .2959575{col 41} .0078411{col 57} .2806231{col 69} .3116447{txt}

{com}. ci prop hiv, exact level(90)

{txt}{col 58}{hline 2} Binomial Exact {hline 2}
    Variable {c |}        Obs  Proportion    Std. Err.       [90% Conf. Interval]
{hline 13}{c +}{hline 63}
         hiv {c |}{col 16}{res}     3,389{col 29} .2959575{col 41} .0078411{col 57} .2830462{col 69} .3091298{txt}

{com}. 
. /* The ci command does not allow stratification, but we can get around that 
> using the bysort prefix: */
. 
. bysort female: ci prop hiv, exact

{txt}{hline}
-> female = no

{col 58}{hline 2} Binomial Exact {hline 2}
    Variable {c |}        Obs  Proportion    Std. Err.       [95% Conf. Interval]
{hline 13}{c +}{hline 63}
         hiv {c |}{col 16}{res}     1,553{col 29} .2433999{col 41} .0108895{col 57} .2222362{col 69} .2655381{txt}

{hline}
-> female = yes

{col 58}{hline 2} Binomial Exact {hline 2}
    Variable {c |}        Obs  Proportion    Std. Err.       [95% Conf. Interval]
{hline 13}{c +}{hline 63}
         hiv {c |}{col 16}{res}     1,836{col 29} .3404139{col 41} .0110587{col 57} .3187364{col 69} .3626026{txt}

{com}. 
. * The ci command also works for continous and Poisson-distributed count varibles 
. ci means age

{txt}    Variable {c |}        Obs        Mean    Std. Err.       [95% Conf. Interval]
{hline 13}{c +}{hline 63}
         age {c |}{col 16}{res}     3,387{col 29} 31.73267{col 41} .1691974{col 57} 31.40093{col 69} 32.06441{txt}

{com}. ci means n_adults, poisson

{txt}{col 58}{hline 2} Poisson  Exact {hline 2}
    Variable {c |}   Exposure        Mean    Std. Err.       [95% Conf. Interval]
{hline 13}{c +}{hline 63}
    n_adults {c |}{col 17}{res}     3384{col 29} 1.664598{col 41} .0221789{col 57} 1.621409{col 69} 1.708646{txt}

{com}. 
. ********************************************************************************
. 
. /* Exploratory data analysis using graphical means.  First make a histogram of 
> the age distribution.  We can use the name option so that multiple graphs can 
> be shown in the viewer.  The replace option is needed to prevent Stata from 
> stopping if the graph already exists -- again, this is useful if you are 
> rerunning a do-file to debug it. */
. 
. histogram age, fcolor(blue) name(hist_age_00, replace)
{txt}(bin={res}35{txt}, start={res}17.52{txt}, width={res}1.7808571{txt})
{res}{txt}
{com}. 
. /* Now add titles to the histogram. */
. 
. histogram age, fcolor(blue) title(Histogram of age) ///
>         xtitle(Age) name(hist_age_01, replace)
{txt}(bin={res}35{txt}, start={res}17.52{txt}, width={res}1.7808571{txt})
{res}{txt}
{com}.         
. /* By default, the Y-axis shows the "density", which sums to one for all bars. 
> Alternatively, we could get a histogram of frequencies. */
. 
. histogram age, fcolor(blue) frequency ///
>         title(Histogram of age) xtitle(Age) name(hist_age_02, replace)
{txt}(bin={res}35{txt}, start={res}17.52{txt}, width={res}1.7808571{txt})
{res}{txt}
{com}. 
. /* Now combine the two histograms into a single plot. Note that he histograms 
> are identical in shape, and both show that age is somewhat skewed to the right. */ 
. 
. graph combine hist_age_01 hist_age_02, name(hist_age_combined, replace)
{res}{txt}
{com}. 
. /* To save this as a PDF file, we can use the following command.  Other options 
> include saving as png, wmf, tif, eps (encapsulated postscript), and svg 
> (scalable vector graphics), which some journals prefer.  See help graph export 
> for more information. */
. 
. graph export hist_age_combined.pdf, replace
{txt}(file /Users/eric/Work/MB/ATCR/200/Labs/hist_age_combined.pdf written in PDF format)

{com}. 
. /* Now we will change the number of bars in the histogram, leaving Stata to 
> decide on their widths.
> 
> We will do this using "loops." Specifically, the program will loop over the 4 
> values of nbins (i.e., # of bins) in the first line, pasting those values as 
> so-called local variables `nbins' into the histogram command in several places. 
> Learning to use loops can make programming a lot less tedious. You will need 
> to run the four lines of code defining the loop together. */
. 
. foreach nbins in 5 10 25 50 {c -(}
{txt}  2{com}.         histogram age, fcolor(blue) percent  bin(`nbins') ///
>                 title("`nbins' bins") xtitle(Age) name(hanb`nbins', replace)
{txt}  3{com}.         {c )-}
{txt}(bin={res}5{txt}, start={res}17.52{txt}, width={res}12.466{txt})
{res}{txt}(bin={res}10{txt}, start={res}17.52{txt}, width={res}6.233{txt})
{res}{txt}(bin={res}25{txt}, start={res}17.52{txt}, width={res}2.4932{txt})
{res}{txt}(bin={res}50{txt}, start={res}17.52{txt}, width={res}1.2466{txt})
{res}{txt}
{com}. graph combine hanb5 hanb10 hanb25 hanb50, name(hist_age_bins, replace)
{res}{txt}
{com}. 
. /* As an alternative, we can vary the width of the bins, again using a loop. */
. 
. foreach bw in 1 2 5 10 {c -(}
{txt}  2{com}.         histogram age, fcolor(blue) percent width(`bw') ///
>                 title(bin width `bw') xtitle(Age) name(habw`bw', replace)
{txt}  3{com}.         {c )-}
{txt}(bin={res}63{txt}, start={res}17.52{txt}, width={res}1{txt})
{res}{txt}(bin={res}32{txt}, start={res}17.52{txt}, width={res}2{txt})
{res}{txt}(bin={res}13{txt}, start={res}17.52{txt}, width={res}5{txt})
{res}{txt}(bin={res}7{txt}, start={res}17.52{txt}, width={res}10{txt})
{res}{txt}
{com}. graph combine habw1 habw2 habw5 habw10, name(hist_age_widths, replace)
{res}{txt}
{com}. 
. ********************************************************************************
. 
. /* Box plots are also useful for assessing the distribution of continuous 
> variables.  The box runs from the 25th to the 75th percentile, and includes a 
> line at the median.  The so-called whiskers extend 1.5 IQRs from the bottom 
> and top of the box, or to the most extreme value, whichever is closer to the 
> box. Any outliers more than 1.5 IQRs from the box are plotted separately. */
.         
. graph box age, name(box_age, replace)
{res}{txt}
{com}. 
. /* The boxplot also shows that age is somewhat right skewed, as we saw in the 
> histograms.  
> 
> We can stratify the boxplot by up to three other factors. Note that the value 
> labels we added in lab 1 to sex and hiv make this plot easier to understand */
. 
. graph box age, over(sex) over(hiv) name(box_age_stratified, replace)
{res}{txt}
{com}. 
. /* Finally, Q-Q (quantile-quantile) plots are a good way to assess Normality.  
> We will use a loop to look at them within groups, using some new commands to 
> control the loops and title the plots: */
. 
. qui levelsof sex, local(sl) // extracts distinct values of sex
{txt}
{com}. foreach i in `sl' {c -(}
{txt}  2{com}.         local sex : label(sex) `i' // gets value label for level i of sex 
{txt}  3{com}.         forvalues j = 0/1 {c -(}
{txt}  4{com}.                 local stat : label(hiv) `j'  // gets value label for level j of hiv 
{txt}  5{com}.                 qnorm age if sex==`i' & hiv==`j', ///
>                         title("`stat' `sex'") name(qq_age`i'`j', replace)
{txt}  6{com}.                 {c )-}
{txt}  7{com}.         {c )-}
{res}{txt}
{com}. graph combine qq_age10 qq_age11 qq_age20 qq_age21, name(qq_age, replace)
{res}{txt}
{com}. 
. /* With the exception of HIV positive men, these plots all show the same right 
> skewness we observed in the box plots and histograms. */
. 
. ********************************************************************************
. 
. /* Now we will use scatter plots to look at the association of a continuous 
> outcome with a continuous predictor. */
. 
. scatter n_support age, name(scatter_age, replace)
{res}{txt}
{com}. 
. /* Now we add a Lowess smooth through the data. Essentially this is a regression 
> of n_support on age, without making the assumption that the regression line is linear. The bwidth option controls the smoothness of the line.  The default is 
> 0.8, which means that Stata uses the nearest 80% of the data to determine the 
> vertical location of the smooth at each value of the independent variable. The 
> lineopts() option allows us to control the thickness of the line, and could 
> also be used to reset its color and whether the line is solid, dashed, etc. 
> 
> We will again using loops to explore the bandwidth. The looping variable is a 
> percentage, because the plot name can't include decimals. This means that we 
> have to use some arcane code to convert `pct' to a proportion for use in the 
> bw() option in the lowess command.  Note that the first line of the loop uses 
> a somewhat different syntax than the previous loops.  */
. 
. foreach pct of numlist 80(-20)20 10 1 {c -(}
{txt}  2{com}.         lowess n_support age, ///
>                 bwidth(`=`pct'/100') msize(tiny) lineopts(lwidth(medthick)) title("") ///
>                 name(bw`pct', replace)
{txt}  3{com}.         {c )-}
{res}{txt}
{com}. graph combine bw80 bw60 bw40 bw20 bw10 bw1, name(lowess_combined, replace)
{res}{txt}
{com}. 
. /* Reducing the bandwith imposes less smoothness, but clearly the smallest  
> bandwidth is going too far! 
> 
> We can also focus on a certain age range by adding an if statement. */
. 
. lowess n_support age if age<60, ///
>         msize(tiny) lineopts(lwidth(medthick)) title("") ///
>         name(lowess_restricted, replace)
{res}{txt}
{com}.         
. /* Finally, we can use tabstat and box plots to look at the conditional 
> distribution of a continuous outcome when the independent variable is 
> categorical. */
. 
. tabstat n_support, by(hungry) stat(n mean sd min p25 p50 p75 max) format(%8.3g)

{txt}Summary for variables: n_support
{col 6}by categories of: hungry (How often household members go hungry)

{ralign 9:hungry} {...}
{c |}         N      mean        sd       min       p25       p50       p75
{hline 10}{c +}{hline 70}
{ralign 9:often} {...}
{c |}{...}
  {res}      77      4.38      3.36         0         1         4         6
{txt}{ralign 9:sometimes} {...}
{c |}{...}
  {res}     378      4.18      3.18         0         2         4         6
{txt}{ralign 9:seldom} {...}
{c |}{...}
  {res}     319       4.2      3.34         0         2         4         6
{txt}{ralign 9:never} {...}
{c |}{...}
  {res}    2530      3.81      3.21         0         1         3         5
{txt}{hline 10}{c +}{hline 70}
{ralign 9:Total} {...}
{c |}{...}
  {res}    3304      3.91      3.22         0         1         3         5
{txt}{hline 10}{c BT}{hline 70}

{ralign 9:hungry} {...}
{c |}       max
{hline 10}{c +}{hline 10}
{ralign 9:often} {...}
{c |}{...}
  {res}      13
{txt}{ralign 9:sometimes} {...}
{c |}{...}
  {res}      16
{txt}{ralign 9:seldom} {...}
{c |}{...}
  {res}      20
{txt}{ralign 9:never} {...}
{c |}{...}
  {res}      20
{txt}{hline 10}{c +}{hline 10}
{ralign 9:Total} {...}
{c |}{...}
  {res}      20
{txt}{hline 10}{c BT}{hline 10}

{com}. 
. graph box n_support, over(hungry) name(ins_alc, replace)
{res}{txt}
{com}. 
. /* Now close the log file.*/
.         
. log close
      {txt}name:  {res}<unnamed>
       {txt}log:  {res}/Users/eric/Work/MB/ATCR/200/Labs/lab 1.smcl
  {txt}log type:  {res}smcl
 {txt}closed on:  {res}18 Sep 2018, 06:54:49
{txt}{.-}
{smcl}
{txt}{sf}{ul off}