prop_test {quest}

Test for Sample Proportion Against Pi (chi-square test of goodness of fit)

Description

prop_test tests for a sample proportion difference from a population proportion with a chi-square test of goodness of fit. The default is that the goodness of fit is consistent with a population proportion Pi of 0.50. The function also calculates the descriptive statistics, various standardized effect sizes (e.g., Cramer's V), and can provide the 1x2 contingency tables. prop_test is simply a wrapper for prop.test plus some extra calculations.

Usage

prop_test(
  x,
  pi = 0.5,
  yates = TRUE,
  ci.level = 0.95,
  rtn.table = TRUE,
  check = TRUE
)

Arguments

x

numeric vector that only has values of 0 or 1 (or missing values), otherwise known as a dummy variable.

pi

numeric vector of length 1 specifying the population proportion value to compare the sample proportion against.

yates

logical vector of length 1 specifying whether the Yate's continuity correction should be applied for small samples. See chisq.test for details.

ci.level

numeric vector of length 1 specifying the confidence level. ci.level must range from 0 to 1.

rtn.table

logical vector of lengh 1 specifying whether the return object should include the 1x2 contingency table of counts with totals and the 1x2 overall percentages table. If TRUE, then the last two elements of the return object are "count" containing a vector of counts and "percent" containing a vector of overall percentages.

check

logical vector of length 1 specifying whether the input arguments should be checked for errors. For example, if x is a dummy variable that only takes on value of 0 or 1 (or missing values). This is a tradeoff between computational efficiency (FALSE) and more useful error messages (TRUE).

Value

list of numeric vectors containing statistical information about the proportion difference from pi: 1) nhst = chi-square test of goodness of fit stat info in a numeric vector, 2) desc = descriptive statistics stat info in a numeric vector, 3) std = various standardized effect sizes in a numeric vector, 4) count = numeric vector of length 3 with table of counts with an additional element for the total (if rtn.table = TRUE), 5) percent = numeric vector of length 3 with table of overall percentages with an element for the total (if rtn.table = TRUE)

1) nhst = chi-square test of goodness of fit stat info in a numeric vector

est

proportion difference estimate (i.e., sample proportion - pi)

se

NA (to remind the user there is no standard error for the test)

X2

chi-square value

df

degrees of freedom (will always be 1)

p

two-sided p-value

2) desc = descriptive statistics stat info in a numeric vector

prop

sample proportion

pi

popularion proportion provided by the user (or 0.50 by default)

sd

standard deviation

n

sample size

lwr

lower bound of the confidence interval of the sample proportion itself

upr

upper bound of the confidence interval of the sample proportion itself

3) std = various standardized effect sizes in a numeric vector

cramer

Cramer's V estimate

h

Cohen's h estimate

4) count = numeric vector of length 3 with table of counts with an additional element for the total (if rtn.table = TRUE). The names are 1. "0", 2. "1", 3. "total"

5) percent = numeric vector of length 3 with table of overall percentages with an element for the total (if rtn.table = TRUE). The names are 1. "0", 2. "1", 3. "total"

See Also

prop.test the workhorse for prop_test, props_test for multiple dummy variables, prop_diff for chi-square test of independence,

Examples

# chi-square test of goodness of fit
table(mtcars$"am")
prop_test(mtcars$"am")
prop_test(ifelse(mtcars$"am" == 1, yes = 0, no = 1))

# different than intercept only logistic regression
summary(glm(am ~ 1, data = mtcars, family = binomial(link = "logit")))

# error from non-dummy variable
## Not run: 
prop_test(ifelse(mtcars$"am" == 1, yes = "1", no = "0"))
prop_test(ifelse(mtcars$"am" == 1, yes = 2, no = 1))

## End(Not run)