| Type: | Package |
| Title: | Calculate Crosstab and Topline Tables of Weighted Survey Data |
| Version: | 0.1.6 |
| Author: | John D. Johnson [aut, cre] |
| Maintainer: | John D. Johnson <john.d.johnson@marquette.edu> |
| Description: | Calculate common types of tables for weighted survey data. Options include topline and (2-way and 3-way) crosstab tables of categorical or ordinal data as well as summary tables of weighted numeric variables. Optionally, include the margin of error at selected confidence intervals including the design effect. The design effect is calculated as described by Kish (1965) <doi:10.1002/bimj.19680100122> beginning on page 257. Output takes the form of tibbles (simple data frames). This package conveniently handles labelled data, such as that commonly used by 'Stata' and 'SPSS.' Complex survey design is not supported at this time. |
| Depends: | R (≥ 2.10) |
| Imports: | dplyr (≥ 0.8.0), stringr (≥ 1.0.0), tidyr (≥ 1.1.0), labelled (≥ 2.0.0), forcats (≥ 1.0.0), rlang (≥ 0.4.5) |
| Suggests: | ggplot2 (≥ 3.3.0), knitr, rmarkdown |
| License: | CC0 |
| Encoding: | UTF-8 |
| LazyData: | true |
| RoxygenNote: | 7.2.0 |
| VignetteBuilder: | knitr |
| NeedsCompilation: | no |
| Packaged: | 2023-05-12 18:43:13 UTC; johnsonjoh |
| Repository: | CRAN |
| Date/Publication: | 2023-05-12 19:00:05 UTC |
weighted crosstabs
Description
crosstab returns a tibble containing a weighted crosstab of two variables
Usage
crosstab(
df,
x,
y,
weight,
remove = "",
n = TRUE,
pct_type = "row",
format = "wide",
unwt_n = FALSE
)
Arguments
df |
The data source |
x |
The independent variable |
y |
The dependent variable |
weight |
The weighting variable |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE numeric totals are included. They are included in a separate column for row and cell percentages, but in a separate row for wide format column percentages. |
pct_type |
Controls the kind of percentage values returned. One of "row," "cell," or "column." |
format |
one of "long" or "wide" |
unwt_n |
logical, if TRUE a column "unweighted_n" is included containing the unweighted frequency count. It is not available when pct_type is "column" |
Details
Options include row, column, or cell percentages. The tibble can be in long or wide format.
Value
a tibble
Examples
crosstab(df = illinois, x = voter, y = raceethnic, weight = weight)
crosstab(df = illinois, x = voter, y = raceethnic, weight = weight, n = FALSE)
weighted 3-way crosstabs
Description
crosstab_3way returns a tibble containing a weighted crosstab of two variables by a third variable
Usage
crosstab_3way(
df,
x,
y,
z,
weight,
remove = c(""),
n = TRUE,
pct_type = "row",
format = "wide",
unwt_n = FALSE
)
Arguments
df |
The data source |
x |
The independent variable |
y |
The dependent variable |
z |
The second control variable |
weight |
The weighting variable |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE numeric totals are included. |
pct_type |
Controls the kind of percentage values returned. One of "row" or "cell." |
format |
one of "long" or "wide" |
unwt_n |
logical, if TRUE a column is added containing unweighted frequency counts |
Details
Options include row or cell percentages. The tibble can be in long or wide format. These tables are ideal for use with small multiples created with ggplot2::facet_wrap.
Value
a tibble
Examples
crosstab_3way(df = illinois, x = sex, y = educ6, z = maritalstatus, weight = weight)
crosstab_3way(df = illinois, x = sex, y = educ6, z = maritalstatus, weight = weight,
format = "wide")
Calculate the design effect of a sample
Description
deff_calc returns a single number
Usage
deff_calc(w)
Arguments
w |
a vector of weights |
Details
This function returns the design effect of a given sample using the formula length(w)*sum(w^2)/(sum(w)^2). It is designed for use in the moe family of functions. If any weights are equal to 0, they are removed prior to calculation.
Value
A number
Examples
deff_calc(illinois$weight)
Illinois respondents to the Voting and Registration Supplement for the Current Population Survey
Description
A dataset containing the responses of 36,207 Illinois respondents to the Current Population Survey's biennial Voting and Registration Supplement for the Current Population Survey, 1996-2018.
Usage
illinois
Format
A data frame with 36207 rows and 9 variables:
- year
year of survey
- fips
the state fips code
- sex
sex of the respondent, labelled value
- educ6
highest level of education for respondent, labelled values
- raceethnic
one of white, black, Hispanic, or other, labelled values
- maritalstatus
one of Married, Widowed/divorced/Sep, or Never Married, labelled values
- rv
indicates if the respondent is registered to vote, labelled values
- voter
indicates if the respondent voted, labelled values
- age
the age of the respondent, numeric values
- weight
the number of people each respondent is calculated to represent
Source
https://www.census.gov/topics/public-sector/voting.html
weighted crosstabs with margin of error
Description
moe_crosstab returns a tibble containing a weighted crosstab of two variables with margin of error
Usage
moe_crosstab(
df,
x,
y,
weight,
remove = c(""),
n = TRUE,
pct_type = "row",
format = "long",
zscore = 1.96,
unwt_n = FALSE
)
Arguments
df |
The data source |
x |
The independent variable |
y |
The dependent variable |
weight |
The weighting variable, defaults to zwave_weight |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE numeric totals are included. |
pct_type |
Controls the kind of percentage values returned. One of "row" or "cell." Column percents are not supported. |
format |
one of "long" or "wide" |
zscore |
defaults to 1.96, consistent with a 95% confidence interval |
unwt_n |
logical, if TRUE it adds a column with unweighted frequency values |
Details
Options include row or cell percentages. The tibble can be in long or wide format. The margin of error includes the design effect of the weights.
Value
a tibble
Examples
moe_crosstab(df = illinois, x = voter, y = raceethnic, weight = weight)
moe_crosstab(df = illinois, x = voter, y = raceethnic, weight = weight, n = FALSE)
weighted 3-way crosstabs with margin of error
Description
moe_crosstab_3way returns a tibble containing a weighted crosstab of two variables by a third variable with margin of error
Usage
moe_crosstab_3way(
df,
x,
y,
z,
weight,
remove = c(""),
n = TRUE,
pct_type = "row",
format = "long",
zscore = 1.96,
unwt_n = FALSE
)
Arguments
df |
The data source |
x |
The independent variable |
y |
The dependent variable |
z |
The second control variable |
weight |
The weighting variable |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE numeric totals are included. |
pct_type |
Controls the kind of percentage values returned. One of "row" or "cell." |
format |
one of "long" or "wide" |
zscore |
defaults to 1.96, consistent with a 95% confidence interval |
unwt_n |
logical, if TRUE it adds a column with unweighted frequency values |
Details
Options include row or cell percentages. The tibble can be in long or wide format. These tables are ideal for use with small multiples created with ggplot2::facet_wrap.
Value
a tibble
Examples
moe_crosstab_3way(df = illinois, x = sex, y = educ6, z = maritalstatus, weight = weight)
moe_crosstab_3way(df = illinois, x = sex, y = educ6, z = maritalstatus, weight = weight,
format = "wide")
weighted topline with margin of error
Description
moe_topline returns a tibble containing a weighted topline of one variable with margin of error
Usage
moe_topline(
df,
variable,
weight,
remove = c(""),
n = TRUE,
pct = TRUE,
valid_pct = TRUE,
cum_pct = TRUE,
zscore = 1.96
)
Arguments
df |
The data source |
variable |
the variable name |
weight |
The weighting variable, defaults to zwave_weight |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE a frequency column is included percentages, but in a separate row for column percentages. |
pct |
logical, if TRUE a column of percents is included |
valid_pct |
logical, if TRUE a column of valid percents is included |
cum_pct |
logical, if TRUE a column of cumulative percents is included |
zscore |
defaults to 1.96, consistent with a 95% confidence interval |
Details
By default the table includes a column for frequency count, percent, valid percent, and cumulative percent.
Value
a tibble
Examples
moe_topline(df = illinois, variable = educ6, weight = weight)
moe_topline(df = illinois, variable = educ6, weight = weight, remove = c("LT HS"))
weighted crosstabs with margin of error, where the x-variable identifies different survey waves
Description
moe_wave_crosstab returns a tibble containing a weighted crosstab of two variables
with margin of error. Use this function when the x-variable indicates different survey
waves for which weights were calculated independently.
Usage
moe_wave_crosstab(
df,
x,
y,
weight,
remove = c(""),
n = TRUE,
pct_type = "row",
format = "long",
zscore = 1.96,
unwt_n = FALSE
)
Arguments
df |
The data source |
x |
The independent variable, which uniquely identifies survey waves |
y |
The dependent variable |
weight |
The weighting variable, defaults to zwave_weight |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE numeric totals are included. |
pct_type |
Controls the kind of percentage values returned. One of "row" or "cell." Column percents are not supported. |
format |
one of "long" or "wide" |
zscore |
defaults to 1.96, consistent with a 95% confidence interval |
unwt_n |
logical, if TRUE it adds a column with unweighted frequency values |
Details
Options include row or cell percentages. The tibble can be in long or wide format. The margin of error includes the design effect of the weights, calculated separately for each survey wave.
Value
a tibble
Examples
moe_wave_crosstab(df = illinois, x = year, y = maritalstatus, weight = weight)
moe_wave_crosstab(df = illinois, x = year, y = maritalstatus, weight = weight, format = "wide")
weighted 3-way crosstabs with margin of error, where the z-variable identifies different survey waves
Description
moe_wave_crosstab_3way returns a tibble containing a weighted crosstab of two variables by a third variable with margin of error.
Use this function when the z-variable indicates different survey
waves for which weights were calculated independently.
Usage
moe_wave_crosstab_3way(
df,
x,
y,
z,
weight,
remove = c(""),
n = TRUE,
pct_type = "row",
format = "long",
zscore = 1.96,
unwt_n = FALSE
)
Arguments
df |
The data source |
x |
The independent variable |
y |
The dependent variable |
z |
The second control variable, uniquely identifies survey waves |
weight |
The weighting variable |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE numeric totals are included. |
pct_type |
Controls the kind of percentage values returned. One of "row" or "cell." |
format |
one of "long" or "wide" |
zscore |
defaults to 1.96, consistent with a 95% confidence interval |
unwt_n |
logical, if TRUE it adds a column with unweighted frequency values |
Details
Options include row or cell percentages. The tibble can be in long or wide format. These tables are ideal for use with small multiples created with ggplot2::facet_wrap.
Value
a tibble
Examples
moe_crosstab_3way(df = illinois, x = sex, y = educ6, z = year, weight = weight)
moe_crosstab_3way(df = illinois, x = sex, y = educ6, z = year, weight = weight, format = "wide")
Calculate the margin of error (including design effect) of a sample
Description
moedeff_calc returns a single number. It is designed for use in the moe family of functions.
Usage
moedeff_calc(pct, deff, n, zscore = 1.96)
Arguments
pct |
a proportion |
deff |
a design effect |
n |
the sample size |
zscore |
defaults to 1.96, consistent with a 95% confidence interval. |
Details
This function returns the margin of error including design effect of a given sample of weighted data using the formula sqrt(deff)*zscore*sqrt((pct*(1-pct))/(n-1))*100
Value
A percentage
Examples
moedeff_calc(pct = 0.515, deff = 1.6, n = 214)
weighted summary table
Description
summary_table returns a tibble containing a weighted summary table of a single variable.
Usage
summary_table(df, variable, weight, name_style = "clean")
Arguments
df |
The data source |
variable |
the variable to summarize, it should be numeric |
weight |
The weighting variable |
name_style |
the style of the column names–one of "clean" or "pretty." Clean names are all lower case and words are separated by an underscore. Pretty names begin with a capital letter are words a separated by a space. |
Details
The resulting tible includes columns for the variable name, unweighted observations, weighted observations, weighted mean, minimum value, maximum value, unweighted missing values, and weighted missing values
Value
a tibble
Examples
summary_table(illinois, age, weight)
summary_table(illinois, age, weight, name_style = "pretty")
weighted topline
Description
topline returns a tibble containing a weighted topline of one variable
Usage
topline(
df,
variable,
weight,
remove = c(""),
n = TRUE,
pct = TRUE,
valid_pct = TRUE,
cum_pct = TRUE
)
Arguments
df |
The data source |
variable |
the variable name |
weight |
The weighting variable, defaults to zwave_weight |
remove |
An optional character vector of values to remove from final table (e.g. "refused"). This will not affect any calculations made. The vector is not case-sensitive. |
n |
logical, if TRUE a frequency column is included percentages, but in a separate row for column percentages. |
pct |
logical, if TRUE a column of percents is included |
valid_pct |
logical, if TRUE a column of valid percents is included |
cum_pct |
logical, if TRUE a column of cumulative percents is included |
Details
By default the table includes a column for frequency count, percent, valid percent, and cumulative percent.
Value
a tibble
Examples
topline(illinois, sex, weight)
topline(illinois, sex, weight, pct = FALSE)
weighted mean
Description
wtd_mean returns the weighted mean of a variable. It's a tidy-compatible
wrapper around stats::weighted.mean().
Usage
wtd_mean(df, variable, weight)
Arguments
df |
The data source |
variable |
the variable, it should be numeric |
weight |
The weighting variable |
Value
a numeric value
Examples
wtd_mean(illinois, age, weight)
library(dplyr)
illinois %>% wtd_mean(age, weight)