I: Univariate Analysis

1: Examine exposure: food assistance

a: tabulating food security and food assistance

use "NHANES0708_all.dta"

ta food_any foodinsec
           |    RECODE of fsdch
           | (Child food security
           |       category)
  food_any |         0          1 |     Total
-----------+----------------------+----------
         0 |       914        104 |     1,018 
         1 |     2,220      1,056 |     3,276 
-----------+----------------------+----------
     Total |     3,134      1,160 |     4,294

2: Examine outcome: BMI z-score

Analysis limited to food secure boys.

a: Calculate descriptive Statistics

use "NHANES0708_all.dta"

svyset sdmvpsu [pw=wtmec2yr], strata(sdmvstra)

su ridageyr if subpop2==1 & male==1 & foodinsec==0
svy,subpop(if subpop2==1 & male==1 & foodinsec==0): mean ridageyr

tabstat ridageyr [aweight=wtmec2yr] if subpop2==1 & male==1 & foodinsec==0, stat(p50 p10 p90) col(stat)

sktest ridageyr [aweight=wtmec2yr] if subpop2==1 & male==1 & foodinsec==0
      pweight: wtmec2yr
          VCE: linearized
  Single unit: missing
     Strata 1: sdmvstra
         SU 1: sdmvpsu
        FPC 1: <zero>

    Variable |        Obs        Mean    Std. Dev.       Min        Max
-------------+---------------------------------------------------------
    ridageyr |        439    9.168565    3.793628          4         17

(running mean on estimation sample)

Survey: Mean estimation

Number of strata =      16      Number of obs   =       10,149
Number of PSUs   =      32      Population size =  297,136,095
                                Subpop. no. obs =          439
                                Subpop. size    = 8,131,107.05
                                Design df       =           16

--------------------------------------------------------------
             |             Linearized
             |       Mean   Std. Err.     [95% Conf. Interval]
-------------+------------------------------------------------
    ridageyr |   9.582628   .2657403      9.019284    10.14597
--------------------------------------------------------------

    variable |       p50       p10       p90
-------------+------------------------------
    ridageyr |         9         4        15
--------------------------------------------


Skewness and kurtosis tests for normality
                                                         ----- Joint test -----
    Variable |       Obs   Pr(skewness)   Pr(kurtosis)   Adj chi2(2)  Prob>chi2
-------------+-----------------------------------------------------------------
    ridageyr |       439         0.0739         0.0000        107.92     0.0000

b: Create a histogram and box plot

use "NHANES0708_all.dta"

hist bmiz if subpop2==1 & male==1 & foodinsec==0,norm

graph export BMI-z_hist.svg, replace
(bin=20, start=-3.3908119, width=.33581916)

(file BMI-z_hist.svg written in SVG format)
use "NHANES0708_all.dta"

graph box bmiz if subpop2==1 & male==1 & foodinsec==0

graph export BMI-z_boxplot.svg, replace
(file BMI-z_boxplot.svg written in SVG format)

3: Examine other independant variables

Analysis limited to food secure boys.

a: Age

Calculate descriptive statistics

use "NHANES0708_all.dta"

svyset sdmvpsu [pw=wtmec2yr], strata(sdmvstra)

su ridageyr if subpop2==1 & male==1 & foodinsec==0
svy,subpop(if subpop2==1 & male==1 & foodinsec==0): mean ridageyr

tabstat ridageyr [aweight=wtmec2yr] if subpop2==1 & male==1 & foodinsec==0, stat(p50 p10 p90) col(stat)

sktest ridageyr [aweight=wtmec2yr] if subpop2==1 & male==1 & foodinsec==0
      pweight: wtmec2yr
          VCE: linearized
  Single unit: missing
     Strata 1: sdmvstra
         SU 1: sdmvpsu
        FPC 1: <zero>

    Variable |        Obs        Mean    Std. Dev.       Min        Max
-------------+---------------------------------------------------------
    ridageyr |        439    9.168565    3.793628          4         17

(running mean on estimation sample)

Survey: Mean estimation

Number of strata =      16      Number of obs   =       10,149
Number of PSUs   =      32      Population size =  297,136,095
                                Subpop. no. obs =          439
                                Subpop. size    = 8,131,107.05
                                Design df       =           16

--------------------------------------------------------------
             |             Linearized
             |       Mean   Std. Err.     [95% Conf. Interval]
-------------+------------------------------------------------
    ridageyr |   9.582628   .2657403      9.019284    10.14597
--------------------------------------------------------------

    variable |       p50       p10       p90
-------------+------------------------------
    ridageyr |         9         4        15
--------------------------------------------


Skewness and kurtosis tests for normality
                                                         ----- Joint test -----
    Variable |       Obs   Pr(skewness)   Pr(kurtosis)   Adj chi2(2)  Prob>chi2
-------------+-----------------------------------------------------------------
    ridageyr |       439         0.0739         0.0000        107.92     0.0000

Create a histogram and box plot

use "NHANES0708_all.dta"

hist ridageyr if subpop2==1 & male==1 & foodinsec==0,norm

graph export age_hist.svg, replace
(bin=20, start=4, width=.65)

(file age_hist.svg written in SVG format)
use "NHANES0708_all.dta"

graph box ridageyr if subpop2==1 & male==1 & foodinsec==0

graph export age_boxplot.svg, replace
(file age_boxplot.svg written in SVG format)

These exported images displayed using html:

b: categorical variables

use "NHANES0708_all.dta"

ta fpl_2cat if subpop2==1 & male==1 & foodinsec==0

ta hinsur if subpop2==1 & male==1 & foodinsec==0
  RECODE of |
   indfmpir |
  (Ratio of |
     family |
  income to |
   poverty) |      Freq.     Percent        Cum.
------------+-----------------------------------
          0 |        209       47.61       47.61
          1 |        230       52.39      100.00
------------+-----------------------------------
      Total |        439      100.00

     hinsur |      Freq.     Percent        Cum.
------------+-----------------------------------
          0 |         99       22.55       22.55
          1 |        254       57.86       80.41
          2 |         86       19.59      100.00
------------+-----------------------------------
      Total |        439      100.00

II: Bivariate Analysis

For the questions in this section, limit the analyses to food secure boys.

1: cross-tabulation of categorical independent variables with high waist circumfrence

use "NHANES0708_all.dta"

ta food_any wccata if subpop2==1 & male==1 & foodinsec==0

ta hinsur wccata if subpop2==1 & male==1 & foodinsec==0
           |        wccata
  food_any |         0          1 |     Total
-----------+----------------------+----------
         0 |        74         16 |        90 
         1 |       289         60 |       349 
-----------+----------------------+----------
     Total |       363         76 |       439 

           |        wccata
    hinsur |         0          1 |     Total
-----------+----------------------+----------
         0 |        82         17 |        99 
         1 |       213         41 |       254 
         2 |        68         18 |        86 
-----------+----------------------+----------
     Total |       363         76 |       439

2: 10th and 90th percentile values of continuous independent variables within each category of the dependent variable (high waist circumference).

use "NHANES0708_all.dta"

tabstat ridageyr if subpop2==1 & male==1 & foodinsec==0 & wccata==0, stat(p10 p90) col(stat)

tabstat ridageyr if subpop2==1 & male==1 & foodinsec==0 & wccata==1, stat(p10 p90) col(stat)
    variable |       p10       p90
-------------+--------------------
    ridageyr |         4        15
----------------------------------

    variable |       p10       p90
-------------+--------------------
    ridageyr |         5        14
----------------------------------

3: Cross-tabulate example categorical independent variables with the exposure variable, food assistance.

use "NHANES0708_all.dta"

ta fpl_2cat food_any if subpop2==1 & male==1 & foodinsec==0

ta hinsur food_any if subpop2==1 & male==1 & foodinsec==0
 RECODE of |
  indfmpir |
 (Ratio of |
    family |
 income to |       food_any
  poverty) |         0          1 |     Total
-----------+----------------------+----------
         0 |        15        194 |       209 
         1 |        75        155 |       230 
-----------+----------------------+----------
     Total |        90        349 |       439 

           |       food_any
    hinsur |         0          1 |     Total
-----------+----------------------+----------
         0 |        39         60 |        99 
         1 |        22        232 |       254 
         2 |        29         57 |        86 
-----------+----------------------+----------
     Total |        90        349 |       439

4: Calculate 10th and 90th percentile values of an example continuous covariate within each category of the exposure (food assistance), among food secure boys.

use "NHANES0708_all.dta"

tabstat ridageyr if subpop2==1 & male==1 & foodinsec==0 & food_any==0, stat(p10 p90) col(stat)

tabstat ridageyr if subpop2==1 & male==1 & foodinsec==0 & food_any==1, stat(p10 p90) col(stat)
    variable |       p10       p90
-------------+--------------------
    ridageyr |         4        15
----------------------------------

    variable |       p10       p90
-------------+--------------------
    ridageyr |         4        14
----------------------------------