Homework 4

  1. At the top of a new script, include code for importing the nhanes_l.csv data file. Run that code.

    nhanes<-read.csv('~/Downloads/data/nhanes/l/nhanes_l.csv')

  2. Create a box plot of the typical number of sleep hours (sld012) versus occupation status (ocd150). Label the y axis and optionally remove the label for the x axis. The occupation variable codes groups using numbers; a description is available here. We’ll talk in Session 7 about how to “label” categorical variables that use numeric codes.

    You may notice that 9 codes people who indicated that they don’t know how much sleep they typically get. We’ll talk in Session 6 about how to properly encode missing values.

    boxplot(nhanes$sld012~nhanes$ocd150,ylab='Hours of sleep',xlab='')

  3. Create a box plot of the typical number of sleep hours (sld012) versus gender (gender). Label the y axis and optionally remove the label for the x axis.

    boxplot(nhanes$sld012~nhanes$gender,ylab='Hours of sleep',xlab='')

  4. Conduct a t-test for the association between the typical number of sleep hours (sld012) and gender (gender).

    t.test(nhanes$sld012~nhanes$gender)
#|  
#|   Welch Two Sample t-test
#|  
#|  data:  nhanes$sld012 by nhanes$gender
#|  t = 4.8356, df = 7638.6, p-value = 1.353e-06
#|  alternative hypothesis: true difference in means between group Female and group Male is not equal to 0
#|  95 percent confidence interval:
#|   0.1044477 0.2468641
#|  sample estimates:
#|  mean in group Female   mean in group Male 
#|              7.820103             7.644448

  5. Create a contingency table for country of birth (dmdborn4) and asthma (asthma), with country of birth placed along the rows.

    The country variable codes groups using numbers; a description is available here. We’ll talk in Session 7 about how to “label” categorical variables that use numeric codes.

    table(nhanes$dmdborn4,nhanes$asthma)
#|     
#|      History of asthma   No
#|    1              1286 5226
#|    2               198 1417

  6. Find the row-wise percents.

    prop.table(table(nhanes$dmdborn4,nhanes$asthma),1)*100
#|     
#|      History of asthma       No
#|    1          19.74816 80.25184
#|    2          12.26006 87.73994

  7. Conduct a chi-squared test for the association between the two variables.

    chisq.test(table(nhanes$dmdborn4,nhanes$asthma))
#|  
#|   Pearson's Chi-squared test with Yates' continuity correction
#|  
#|  data:  table(nhanes$dmdborn4, nhanes$asthma)
#|  X-squared = 48.114, df = 1, p-value = 4.022e-12