In elinw/lehmansociology: Tools for Sociology Students Using R

# Load your libraries here
library(aws.s3)
library('lehmansociology')

Type your text here.

#type your code here
s3load('gss.Rda', bucket = 'lehmansociologydata')
#View(GSS)

table(GSS$sex)
crosstab(GSS, row.vars = "sex")
summary(GSS$sex)

table(GSS$health)
crosstab(GSS, row.vars = "health")
summary(GSS$health)

table(GSS$childs)
crosstab(GSS, row.vars = "childs")
summary(GSS$childs)

table(GSS$age)
crosstab(GSS, row.vars = "age")
summary(GSS$age)
median(GSS$age)

IF YOU DID NOT ANSWER THE QUESTIONS ABOUT THE ABOVE CHUNK PREVIOUSLY, YOU SHOULD TYPE NOTES HERE TO ANSWER THOSE QUESTIONS.

#[CHANGE THIS TEXT TO A NOTE WHERE YOU DESCRIBE WHAT THE LINE OF CODE BELOW DOES]
GSS$nochild <-as.numeric(GSS$childs) <= 0
crosstab(GSS, row.vars = "nochild")

#[CHANGE THIS TEXT TO A NOTE WHERE YOU DESCRIBE WHAT THE LINE OF CODE BELOW DOES]
GSS$youngadult <- as.numeric(GSS$age) <= 25
crosstab(GSS, row.vars = "youngadult")

#[CHANGE THIS TEXT TO A NOTE WHERE YOU DESCRIBE WHAT THE LINE OF CODE BELOW DOES]
crosstab(GSS, row.vars = "nochild", col.vars = "youngadult")
crosstab(GSS, row.vars = "nochild", col.vars = "youngadult", type = "c")

*WRITE A SENTENCE INTERPRETING THE RESULT FROM CROSSTAB OF NOCHILD.

*WRITE A SENTENCE INTERPRETING THE RESULT FROM CROSSTAB OF YOUNGADULT.

*WRITE 1-2 SENTENCES INTERPRETING THE RESULTS FROM THE CROSSTAB OF NOCHILD BY YOUNGADULT.

median(GSS$childs)
mean(GSS$childs)
min(GSS$childs)
max(GSS$childs)
range(GSS$childs)

Remember that we can get a median for an ordinal variable. However, when we ran summary(GSS$health) above, R did not give us the median of health. This is because we need to tell R to treat health as a numeric variable because it thinks health is a factor/character variable. Recall from swirl lesson that we've done this using as.numeric. Also, when R thinks health is a factor/character variable, it does not know that NA is not a valid value for the variable. Also recall from the swirl that we use na.rm=TRUE for missing values.

GSS$health.numeric <-as.numeric(GSS$health)
summary(GSS$health.numeric, na.rm=TRUE)
median(GSS$health.numeric, na.rm=TRUE)

WHAT HAPPENS IF YOU LEAVE na.rm=TRUE OUT OF THE MEDIAN STATEMENT ABOVE. WHY?

NOW ADD A CHUNK AND GET APPROPRIATE DESCRIPTIVE STATISTICS FOR 2 GSS VARIABLES THAT WE HAVE NOT USED IN THIS LAB. WRITE A FEW SENTENCES TO INTERPRET THE STATISTICS THAT YOU GET.

elinw/lehmansociology documentation built on May 16, 2019, 3 a.m.