infer (version 0.5.4)

get_confidence_interval: Compute confidence interval

Description

Compute a confidence interval around a summary statistic. Currently, only simulation-based methods are supported.

Learn more in vignette("infer").

Usage

get_confidence_interval(
  x,
  level = 0.95,
  type = "percentile",
  point_estimate = NULL
)
get_ci(x, level = 0.95, type = "percentile", point_estimate = NULL)

Arguments

x

Data frame of calculated statistics or containing attributes of theoretical distribution values. Currently, dependent on statistics being stored in stat column as created in calculate() function.

level

A numerical value between 0 and 1 giving the confidence level. Default value is 0.95.

type

A string giving which method should be used for creating the confidence interval. The default is "percentile" with "se" corresponding to (multiplier * standard error) and "bias-corrected" for bias-corrected interval as other options.

point_estimate

A numeric value or a 1x1 data frame set to NULL by default. Needed to be provided if type is "se" or "bias-corrected".

Value

A 1 x 2 tibble with 'lower_ci' and 'upper_ci' columns. Values correspond to lower and upper bounds of the confidence interval.

Aliases

get_ci() is an alias of get_confidence_interval(). conf_int() is a deprecated alias of get_confidence_interval().

Details

A null hypothesis is not required to compute a confidence interval, but including hypothesize() in a chain leading to get_confidence_interval() will not break anything. This can be useful when computing a confidence interval after previously computing a p-value.

Examples

# NOT RUN {
boot_distr <- gss %>%
  # We're interested in the number of hours worked per week
  specify(response = hours) %>%
  # Generate bootstrap samples
  generate(reps = 1000, type = "bootstrap") %>%
  # Calculate mean of each bootstrap sample
  calculate(stat = "mean")

boot_distr %>%
  # Calculate the confidence interval around the point estimate
  get_confidence_interval(
    # At the 95% confidence level; percentile method
    level = 0.95
  )

# For type = "se" or type = "bias-corrected" we need a point estimate
sample_mean <- gss %>%
  specify(response = hours) %>%
  calculate(stat = "mean") %>%
  dplyr::pull()

boot_distr %>%
  get_confidence_interval(
    point_estimate = sample_mean,
    # At the 95% confidence level
    level = 0.95,
    # Using the standard error method
    type = "se"
  )

# More in-depth explanation of how to use the infer package
# }
# NOT RUN {
vignette("infer")
# }
# NOT RUN {
# }