{smcl}
{com}{sf}{ul off}{txt}{.-}
      name:  {res}<unnamed>
       {txt}log:  {res}/Users/eric/Work/MB/ATCR/200/Labs/Lab 1 exercises 2018.smcl
  {txt}log type:  {res}smcl
 {txt}opened on:  {res} 5 Jul 2018, 05:33:02
{txt}
{com}. 
. /* Read in the lab1 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 Uganda. */
. 
. use lab1.dta, clear
{txt}
{com}. 
. /* We will 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 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 sex "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). */
. 
. label define sex 1 "Male" 2 "Female"
{txt}
{com}. label values sex sex
{txt}
{com}. label define hiv 0 "HIV-" 1 "HIV+"
{txt}
{com}. label values hiv hiv
{txt}
{com}. 
. * Stata lets us look at a spreadsheet of the data
. 
. browse
{txt}
{com}. 
. /* Exploratory data analysis -- descriptive statistics.  
> 
> First see what variables are in the dataset.  Check how many observations 
> and variables the dataset includes. */
. 
. describe

{txt}Contains data from {res}lab1.dta
{txt}  obs:{res}         3,389                          
{txt} vars:{res}            12                          4 Jul 2018 08:10
{txt} size:{res}        44,057                          
{txt}{hline}
              storage   display    value
variable name   type    format     label      variable label
{hline}
{p 0 48}{res}{bind:age            }{txt}{bind: byte    }{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}AUDITC, past 3 mos{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: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}Sex{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    31.72808    9.850006         18         80
{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 9}hiv {c |}{res}      3,389    .2959575    .4565393          0          1
{txt}{hline 13}{c +}{hline 57}
{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}{space 3}n_support {c |}{res}      3,372    3.907177    3.227549          0         20
{txt}{hline 13}{c +}{hline 57}
{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}. 
. /* 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             18
{txt} 5%    {res}       20             18
{txt}10%    {res}       21             18       {txt}Obs         {res}      3,387
{txt}25%    {res}       24             18       {txt}Sum of Wgt. {res}      3,387

{txt}50%    {res}       30                      {txt}Mean          {res} 31.72808
                        {txt}Largest       Std. Dev.     {res} 9.850006
{txt}75%    {res}       38             75
{txt}90%    {res}       46             75       {txt}Variance      {res} 97.02261
{txt}95%    {res}       50             78       {txt}Skewness      {res} 1.030799
{txt}99%    {res}       60             80       {txt}Kurtosis      {res} 3.975972

                          {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}. 
. /* The tabstat command also 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}      18         1
{txt}{ralign 8:p25} {...}
{c |}{...}
  {res}      24       130
{txt}{ralign 8:p50} {...}
{c |}{...}
  {res}      30       283
{txt}{ralign 8:p75} {...}
{c |}{...}
  {res}      38       463
{txt}{ralign 8:max} {...}
{c |}{...}
  {res}      80      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        18        24        30        38
{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}      80
{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        18        23        28        38        80
{space 6} {...}
{txt}{c |}{...}
  {res}       0         .         .         .         .         .         .         .
{txt}{hline 7}{c +}{hline 80}
{ralign 6:HIV+} {...}
{c |}{...}
  {res}    1003      32.6      8.05        18        27        31        38        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        18        24        30        38        80
{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 stratify by one by variable at a time; to 
> stratify by >1 variables, use the table command.*/
. table hiv sex hungry, by(religion) c(mean age) format(%8.1f)

{txt}{hline 11}{c TT}{hline 69}
Religion   {c |}            How often household members go hungry and Sex            
and HIV    {c |} {hline 4} Often {hline 3}    {hline 2} Sometimes {hline 1}    {hline 3} Seldom {hline 3}    {hline 4} Never {hline 3}
status     {c |}   Male  Female      Male  Female      Male  Female      Male  Female
{hline 11}{c +}{hline 69}
Protestant {c |}
      HIV- {c |}   {res}35.0    32.2      33.9    34.9      29.9    32.6      31.9    31.9
      {txt}HIV+ {c |}   {res}38.0    32.4      33.4    31.0      39.6    34.2      35.5    31.4
{txt}{hline 11}{c +}{hline 69}
Catholic   {c |}
      HIV- {c |}   {res}33.5    38.7      29.2    34.2      32.5    33.4      31.3    31.2
      {txt}HIV+ {c |}   {res}33.7    36.3      33.9    29.8      33.8    31.1      34.1    30.5
{txt}{hline 11}{c +}{hline 69}
Saved      {c |}
      HIV- {c |}   {res}24.5    34.4      30.1    28.4      26.1    32.4      29.5    30.3
      {txt}HIV+ {c |}   {res}38.0    27.0      36.0    30.6      31.7    32.4      35.8    30.9
{txt}{hline 11}{c +}{hline 69}
Moslem     {c |}
      HIV- {c |}   {res}37.7    36.2      30.0    34.0      27.7    31.2      31.1    31.2
      {txt}HIV+ {c |}   {res}44.0    33.4      35.9    32.9      38.5    31.8      34.9    30.1
{txt}{hline 11}{c +}{hline 69}
Other      {c |}
      HIV- {c |}       {res}              28.0    28.0      26.2    24.0      29.5    31.3
      {txt}HIV+ {c |}       {res}    40.0      39.0              46.0    37.0      34.8    32.7
{txt}{hline 11}{c BT}{hline 69}

{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}18{txt}, width={res}1.7714286{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}18{txt}, width={res}1.7714286{txt})
{res}{txt}
{com}.         
. /* By default, the Y-axis shows the "density", which sums to one for all bars.
> Instead we can 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}18{txt}, width={res}1.7714286{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}. 
. * save this as a PDF file
. 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 nb in the first line, pasting those values as so-called local 
> variables `nb' into the histogram command in several places.  Learning to use 
> loops can make your programming a lot less tedious. Recall that you will need 
> to run the four lines of code defining the loop together. */
. 
. foreach nb in 5 10 25 50 {c -(}
{txt}  2{com}.         histogram age, fcolor(blue) percent  bin(`nb') ///
>                 title(`nb' bins) xtitle(Age) name(hanb`nb', replace)
{txt}  3{com}.         {c )-}
{txt}(bin={res}5{txt}, start={res}18{txt}, width={res}12.4{txt})
{res}{txt}(bin={res}10{txt}, start={res}18{txt}, width={res}6.2{txt})
{res}{txt}(bin={res}25{txt}, start={res}18{txt}, width={res}2.48{txt})
{res}{txt}(bin={res}50{txt}, start={res}18{txt}, width={res}1.24{txt})
{res}{txt}
{com}. graph combine hanb5 hanb10 hanb25 hanb50, name(hist_age_bins, replace)
{res}{txt}
{com}. graph export hist_age_bins.pdf, replace
{txt}(file /Users/eric/Work/MB/ATCR/200/Labs/hist_age_bins.pdf written in PDF format)

{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}62{txt}, start={res}18{txt}, width={res}1{txt})
{res}{txt}(bin={res}31{txt}, start={res}18{txt}, width={res}2{txt})
{res}{txt}(bin={res}13{txt}, start={res}18{txt}, width={res}5{txt})
{res}{txt}(bin={res}7{txt}, start={res}18{txt}, width={res}10{txt})
{res}{txt}
{com}. graph combine habw1 habw2 habw5 habw10, name(hist_age_widths, replace)
{res}{txt}
{com}. graph export hist_age_widths.pdf, replace
{txt}(file /Users/eric/Work/MB/ATCR/200/Labs/hist_age_widths.pdf written in PDF format)

{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 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}. graph export box_age_stratified.pdf, replace
{txt}(file /Users/eric/Work/MB/ATCR/200/Labs/box_age_stratified.pdf written in PDF format)

{com}. 
. /* 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 up to 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. Here, we have to define a 
> second local variable for the bandwidth, based on looping variable pct, 
> because the plot name can't include decimals. Note that the first line uses
> a somewhat different syntax than the previous loops.
> */
. 
. foreach pct of numlist 80(-20)20 10 1 {c -(}
{txt}  2{com}.         local bw = `pct'/100
{txt}  3{com}.         lowess n_support age, ///
>                 bwidth(`bw') msize(tiny) lineopts(lwidth(thick)) title("") ///
>                 name(bw`pct', replace)
{txt}  4{com}.         {c )-}
{res}{txt}
{com}. graph combine bw80 bw60 bw40 bw20 bw10 bw1, name(lowess_combined, replace)
{res}{txt}
{com}. graph export lowess_combined.pdf, replace
{txt}(file /Users/eric/Work/MB/ATCR/200/Labs/lowess_combined.pdf written in PDF format)

{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(thick)) title("") ///
>         name(lowess_restricted, replace)
{res}{txt}
{com}. graph export lowess_restricted.pdf, replace
{txt}(file /Users/eric/Work/MB/ATCR/200/Labs/lowess_restricted.pdf written in PDF format)

{com}.         
. /* Finally we can also use tabstat and box plots to look at the 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}. graph export ins_alc.pdf, replace
{txt}(file /Users/eric/Work/MB/ATCR/200/Labs/ins_alc.pdf written in PDF format)

{com}. 
. /* Now close the log file.*/
.         
. log close
      {txt}name:  {res}<unnamed>
       {txt}log:  {res}/Users/eric/Work/MB/ATCR/200/Labs/Lab 1 exercises 2018.smcl
  {txt}log type:  {res}smcl
 {txt}closed on:  {res} 5 Jul 2018, 05:33:30
{txt}{.-}
{smcl}
{txt}{sf}{ul off}