Type: Package
Title: Inferential Statistics
Version: 0.3.2
Description: Select set of parametric and non-parametric statistical tests. 'inferr' builds upon the solid set of statistical tests provided in 'stats' package by including additional data types as inputs, expanding and restructuring the test results. The tests included are t tests, variance tests, proportion tests, chi square tests, Levene's test, McNemar Test, Cochran's Q test and Runs test.
Depends: R(≥ 3.2)
License: MIT + file LICENSE
URL: https://rsquaredacademy.github.io/inferr/, https://github.com/rsquaredacademy/inferr
BugReports: https://github.com/rsquaredacademy/inferr/issues
Imports: data.table, magrittr, Rcpp, stats, utils
Suggests: covr, knitr, rmarkdown, testthat (≥ 3.0.0), xplorerr
Encoding: UTF-8
LazyData: true
VignetteBuilder: knitr
RoxygenNote: 7.3.2
LinkingTo: Rcpp
Config/testthat/edition: 3
NeedsCompilation: yes
Packaged: 2024-11-11 11:22:15 UTC; HP
Author: Aravind Hebbali ORCID iD [aut, cre]
Maintainer: Aravind Hebbali <hebbali.aravind@gmail.com>
Repository: CRAN
Date/Publication: 2024-11-11 12:10:06 UTC

inferr package

Description

Parametric and non parametric statistical tests

Details

See the README on GitHub

Author(s)

Maintainer: Aravind Hebbali hebbali.aravind@gmail.com (ORCID)

See Also

Useful links:

Dummy data set for Cochran's Q test

Description

A dataset containing information about results of three exams.

Usage

exam

Format

A data frame with 15 rows and 3 variables:

exam1

result of exam1

exam2

result of exam2

exam3

result of exam3

Source

https://www.spss-tutorials.com/spss-cochran-q-test/

High School and Beyond Data Set

Description

A dataset containing demographic information and standardized test scores of high school students.

Usage

hsb

Format

A data frame with 200 rows and 10 variables:

id

id of the student

female

gender of the student

race

ethnic background of the student

ses

socio-economic status of the student

schtyp

school type

prog

program type

read

scores from test of reading

write

scores from test of writing

math

scores from test of math

science

scores from test of science

socst

scores from test of social studies

Source

https://nces.ed.gov/surveys/hsb/

Binomial Test

Description

Test whether the proportion of successes on a two-level categorical dependent variable significantly differs from a hypothesized value.

Usage

ifr_binom_calc(n, success, prob = 0.5, ...)

ifr_binom_test(data, variable, prob = 0.5)

Arguments

n

number of observations

success

number of successes

prob

assumed probability of success on a trial

...

additional arguments passed to or from other methods

data

a data.frame or a tibble

variable

factor; column in data

Value

ifr_binom_test returns an object of class "ifr_binom_test". An object of class "ifr_binom_test" is a list containing the following components:

exp_k

expected number of successes

exp_p

expected probability of success

k

number of successes

n

number of observations

obs_p

assumed probability of success

pval_lower

lower one sided p value

pval_upper

upper one sided p value

Deprecated Functions

infer_binom_calc() and infer_binom_test() have been deprecated. Instead use ifr_binom_cal() and ifr_binom_test().

References

Hoel, P. G. 1984. Introduction to Mathematical Statistics. 5th ed. New York: Wiley.

See Also

binom.test

Examples

# using calculator
ifr_binom_calc(32, 13, prob = 0.5)

# using data set
ifr_binom_test(hsb, female, prob = 0.5)

Chi Square Test of Association

Description

Chi Square test of association to examine if there is a relationship between two categorical variables.

Usage

ifr_chisq_assoc_test(data, x, y)

Arguments

data

a data.frame or tibble

x

factor; column in data

y

factor; column in data

Value

ifr_chisq_assoc_test returns an object of class "ifr_chisq_assoc_test". An object of class "ifr_chisq_assoc_test" is a list containing the following components:

chisquare

chi square

chisquare_lr

likelihood ratio chi square

chisquare_mantel_haenszel

mantel haenszel chi square

chisquare_adjusted

continuity adjusted chi square

contingency_coefficient

contingency coefficient

cramers_v

cramer's v

df

degrees of freedom

ds

product of dimensions of the table of x and y

phi_coefficient

phi coefficient

pval_chisquare

p-value of chi square

pval_chisquare_adjusted

p-value of continuity adjusted chi square

pval_chisquare_lr

p-value of likelihood ratio chi square

pval_chisquare_mantel_haenszel

p-value of mantel haenszel chi square

Deprecated Function

infer_chisq_assoc_test() has been deprecated. Instead use ifr_chisq_assoc_test().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

chisq.test

Examples

ifr_chisq_assoc_test(hsb, female, schtyp)

ifr_chisq_assoc_test(hsb, female, ses)

Chi Square Goodness of Fit Test

Description

Test whether the observed proportions for a categorical variable differ from hypothesized proportions

Usage

ifr_chisq_gof_test(data, x, y, correct = FALSE)

Arguments

data

a data.frame or tibble

x

factor; column in data

y

expected proportions

correct

logical; if TRUE continuity correction is applied

Value

ifr_chisq_gof_test returns an object of class "ifr_chisq_gof_test". An object of class "ifr_chisq_gof_test" is a list containing the following components:

categories

levels of x

chisquare

chi square statistic

deviation

deviation of observed from frequency

degrees_of_freedom

chi square degrees of freedom

expected_frequency

expected frequency/proportion

n_levels

number of levels of x

observed_frequency

observed frequency/proportion

pvalue

p-value

sample_size

number of observations

std_residuals

standardized residuals

varname

name of categorical variable

Deprecated Function

infer_chisq_gof_test() has been deprecated. Instead use ifr_chisq_gof_test()

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

chisq.test

Examples

ifr_chisq_gof_test(hsb, race, c(20, 20, 20, 140))

# apply continuity correction
ifr_chisq_gof_test(hsb, race, c(20, 20, 20, 140), correct = TRUE)

Cochran Q Test

Description

Test if the proportions of 3 or more dichotomous variables are equal in the same population.

Usage

ifr_cochran_qtest(data, ...)

Arguments

data

a data.frame or tibble

...

columns in data

Value

ifr_cochran_qtest returns an object of class "ifr_cochran_qtest". An object of class "ifr_cochran_qtest" is a list containing the following components:

df

degrees of freedom

n

number of observations

pvalue

p value

q

cochran's q statistic

Deprecated Function

infer_cochran_test() has been deprecated. Instead use ifr_cochran_qtest().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

Examples

ifr_cochran_qtest(exam, exam1, exam2, exam3)

Launch Shiny App

Description

Launches shiny app

Usage

ifr_launch_shiny_app()

Deprecated Function

infer_launch_shiny_app() has been deprecated. Instead use ifr_launch_shiny_app().

Examples

## Not run: 
ifr_launch_shiny_app()

## End(Not run)

Levene's test for equality of variances

Description

ifr_levene_test reports Levene's robust test statistic for the equality of variances and the two statistics proposed by Brown and Forsythe that replace the mean in Levene's formula with alternative location estimators. The first alternative replaces the mean with the median. The second alternative replaces the mean with the 10

Usage

ifr_levene_test(data, ...)

## Default S3 method:
ifr_levene_test(data, ..., group_var = NULL, trim_mean = 0.1)

Arguments

data

a data.frame or tibble

...

numeric; columns in data

group_var

factor; column in data

trim_mean

trimmed mean

Value

ifr_levene_test returns an object of class "ifr_levene_test". An object of class "ifr_levene_test" is a list containing the following components:

bf

Brown and Forsythe f statistic

p_bf

p-value for Brown and Forsythe f statistic

lev

Levene's f statistic

p_lev

p-value for Levene's f statistic

bft

Brown and Forsythe f statistic using trimmed mean

p_bft

p-value for Brown and Forsythe f statistic using trimmed mean

avgs

mean for each level of the grouping variable

sds

standard deviations for each level of the grouping variable

avg

combined mean

sd

combined standard deviation

n

number of observations

n_df

numerator degrees of freedom

d_df

denominator degrees of freedom

levs

levels of the grouping variable

lens

number of observations for each level of the grouping variable

type

alternative hypothesis

Deprecated Function

infer_levene_test() has been deprecated. Instead use ifr_levene_test().

References

Bland, M. 2000. An Introduction to Medical Statistics. 3rd ed. Oxford: Oxford University Press.

Brown, M. B., and A. B. Forsythe. 1974. Robust tests for the equality of variances. Journal of the American Statistical Association 69: 364–367.

Carroll, R. J., and H. Schneider. 1985. A note on Levene’s tests for equality of variances. Statistics and Probability Letters 3: 191–194.

Examples

# using grouping variable
ifr_levene_test(hsb, read, group_var = race)

# using  variables
ifr_levene_test(hsb, read, write, socst)

McNemar Test

Description

Test if the proportions of two dichotomous variables are equal in the same population.

Usage

ifr_mcnemar_test(data, x = NULL, y = NULL)

Arguments

data

a data.frame or tibble

x

factor; column in data

y

factor; column in data

Value

ifr_mcnemar_test returns an object of class "ifr_mcnemar_test". An object of class "ifr_mcnemar_test" is a list containing the following components:

statistic

chi square statistic

df

degrees of freedom

pvalue

p-value

exactp

exact p-value

cstat

continuity correction chi square statistic

cpvalue

continuity correction p-value

kappa

kappa coefficient; measure of interrater agreement

std_err

asymptotic standard error

kappa_cil

95% kappa lower confidence limit

kappa_ciu

95% kappa upper confidence limit

cases

cases

controls

controls

ratio

ratio of proportion with factor

odratio

odds ratio

tbl

two way table

Deprecated Function

infer_mcnermar_test() has been deprecated. Instead use ifr_mcnemar_test().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

mcnemar.test

Examples

# using variables from data
hb <- hsb
hb$himath <- ifelse(hsb$math > 60, 1, 0)
hb$hiread <- ifelse(hsb$read > 60, 1, 0)
ifr_mcnemar_test(hb, himath, hiread)

# test if the proportion of students in himath and hiread group is same
himath <- ifelse(hsb$math > 60, 1, 0)
hiread <- ifelse(hsb$read > 60, 1, 0)
ifr_mcnemar_test(table(himath, hiread))

# using matrix
ifr_mcnemar_test(matrix(c(135, 18, 21, 26), nrow = 2))

One Way ANOVA

Description

One way analysis of variance

Usage

ifr_oneway_anova(data, x, y, ...)

Arguments

data

a data.frame or a tibble

x

numeric; column in data

y

factor; column in data

...

additional arguments passed to or from other methods

Value

ifr_oneway_anova returns an object of class "ifr_oneway_anova". An object of class "ifr_oneway_anova" is a list containing the following components:

adjusted_r2

adjusted r squared value

df_btw

between groups degress of freedom

df_within

within groups degress of freedom

df_total

total degress of freedom

fstat

f value

group_stats

group statistics

ms_btw

between groups mean square

ms_within

within groups mean square

obs

number of observations

pval

p value

r2

r squared value

rmse

root mean squared error

ss_between

between group sum of squares

ss_within

within group sum of squares

ss_total

total sum of squares

Deprecated Function

infer_oneway_anova() has been deprecated. Instead use ifr_oneway_anova()

References

Kutner, M. H., Nachtsheim, C., Neter, J., & Li, W. (2005). Applied linear statistical models. Boston: McGraw-Hill Irwin.

See Also

anova

Examples

ifr_oneway_anova(mtcars, mpg, cyl)
ifr_oneway_anova(hsb, write, prog)

One Sample Test of Proportion

Description

ifr_os_prop_test compares proportion in one group to a specified population proportion.

Usage

ifr_os_prop_test(
  data,
  variable = NULL,
  prob = 0.5,
  phat = 0.5,
  alternative = c("both", "less", "greater", "all")
)

## Default S3 method:
ifr_os_prop_test(
  data,
  variable = NULL,
  prob = 0.5,
  phat = 0.5,
  alternative = c("both", "less", "greater", "all")
)

Arguments

data

numeric vector of length 1 or a data.frame or tibble

variable

factor; column in data

prob

hypothesised proportion

phat

observed proportion

alternative

a character string specifying the alternative hypothesis, must be one of "both" (default), "greater", "less" or "all". You can specify just the initial letter.

Value

ifr_os_prop_test returns an object of class "ifr_os_prop_test". An object of class "ifr_os_prop_test" is a list containing the following components:

n

number of observations

phat

proportion of 1's

p

assumed probability of success

z

z statistic

sig

p-value for z statistic

alt

alternative hypothesis

obs

observed number of 0's and 1's

exp

expected number of 0's and 1's

deviation

deviation of observed from expected

std

standardized resiudals

Deprecated Function

infer_os_prop_test() has been deprecated. Instead use ifr_os_prop_test().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

prop.test binom.test

Examples

# use as a calculator
ifr_os_prop_test(200, prob = 0.5, phat = 0.3)

# using data set
ifr_os_prop_test(hsb, female, prob = 0.5)

One Sample t Test

Description

ifr_os_t_test performs t tests on the equality of means. It tests the hypothesis that a sample has a mean equal to a hypothesized value.

Usage

ifr_os_t_test(
  data,
  x,
  mu = 0,
  alpha = 0.05,
  alternative = c("both", "less", "greater", "all"),
  ...
)

Arguments

data

a data.frame or tibble

x

numeric; column in data

mu

a number indicating the true value of the mean

alpha

acceptable tolerance for type I error

alternative

a character string specifying the alternative hypothesis, must be one of "both" (default), "greater", "less" or "all". You can specify just the initial letter

...

additional arguments passed to or from other methods

Value

ifr_os_t_test returns an object of class "ifr_os_t_test". An object of class "ifr_os_t_test" is a list containing the following components:

mu

a number indicating the true value of the mean

n

number of observations

df

degrees of freedom

Mean

observed mean of x

stddev

standard deviation of x

std_err

estimate of standard error

test_stat

t statistic

confint

confidence interval for the mean

mean_diff

mean difference

mean_diff_l

lower confidence limit for mean difference

mean_diff_u

upper confidence limit for mean difference

p_l

lower one-sided p-value

p_u

upper one-sided p-value

p

two sided p-value

conf

confidence level

type

alternative hypothesis

var_name

name of x

Deprecated Function

infer_os_t_test() has been deprecated. Instead use ifr_os_t_test().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

t.test

Examples

# lower tail
ifr_os_t_test(hsb, write, mu = 50, alternative = 'less')

# upper tail
ifr_os_t_test(hsb, write, mu = 50, alternative = 'greater')

# both tails
ifr_os_t_test(hsb, write, mu = 50, alternative = 'both')

# all tails
ifr_os_t_test(hsb, write, mu = 50, alternative = 'all')

One Sample Variance Comparison Test

Description

ifr_os_var_test performs tests on the equality of standard deviations (variances).It tests that the standard deviation of a sample is equal to a hypothesized value.

Usage

ifr_os_var_test(
  data,
  x,
  sd,
  confint = 0.95,
  alternative = c("both", "less", "greater", "all"),
  ...
)

Arguments

data

a data.frame or tibble

x

numeric; column in data

sd

hypothesised standard deviation

confint

confidence level

alternative

a character string specifying the alternative hypothesis, must be one of "both" (default), "greater", "less" or "all". You can specify just the initial letter

...

additional arguments passed to or from other methods

Value

ifr_os_var_test returns an object of class "ifr_os_var_test". An object of class "ifr_os_var_test" is a list containing the following components:

n

number of observations

sd

hypothesised standard deviation of x

sigma

observed standard deviation

se

estimated standard error

chi

chi-square statistic

df

degrees of freedom

p_lower

lower one-sided p-value

p_upper

upper one-sided p-value

p_two

two-sided p-value

xbar

mean of x

c_lwr

lower confidence limit of standard deviation

c_upr

upper confidence limit of standard deviation

var_name

name of x

conf

confidence level

type

alternative hypothesis

Deprecated Function

infer_os_var_test() has been deprecated. Instead use ifr_os_var_test().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

var.test

Examples

# lower tail
ifr_os_var_test(mtcars, mpg, 5, alternative = 'less')

# upper tail
ifr_os_var_test(mtcars, mpg, 5, alternative = 'greater')

# both tails
ifr_os_var_test(mtcars, mpg, 5, alternative = 'both')

# all tails
ifr_os_var_test(mtcars, mpg, 5, alternative = 'all')

Test for Random Order

Description

runtest tests whether the observations of x are serially independent i.e. whether they occur in a random order, by counting how many runs there are above and below a threshold. By default, the median is used as the threshold. A small number of runs indicates positive serial correlation; a large number indicates negative serial correlation.

Usage

ifr_runs_test(
  data,
  x,
  drop = FALSE,
  split = FALSE,
  mean = FALSE,
  threshold = NA
)

Arguments

data

a data.frame or tibble

x

numeric; column in data

drop

logical; if TRUE, values equal to the threshold will be dropped from x

split

logical; if TRUE, data will be recoded in binary format

mean

logical; if TRUE, mean will be used as threshold

threshold

threshold to be used for counting runs, specify 0 if data is coded as a binary.

Value

infer_runs_test returns an object of class "ifr_runs_test". An object of class "ifr_runs_test" is a list containing the following components:

n

number of observations

threshold

within group sum of squares

n_below

number below the threshold

n_above

number above the threshold

mean

expected number of runs

var

variance of the number of runs

n_runs

number of runs

z

z statistic

p

p-value of z

Deprecated Function

runs_test() has been deprecated. Instead use ifr_runs_test().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

Edgington, E. S. 1961. Probability table for number of runs of signs of first differences in ordered series. Journal of the American Statistical Association 56: 156–159.

Madansky, A. 1988. Prescriptions for Working Statisticians. New York: Springer.

Swed, F. S., and C. Eisenhart. 1943. Tables for testing randomness of grouping in a sequence of alternatives. Annals of Mathematical Statistics 14: 66–87.

Examples

ifr_runs_test(hsb, read)

ifr_runs_test(hsb, read, drop = TRUE)

ifr_runs_test(hsb, read, split = TRUE)

ifr_runs_test(hsb, read, mean = TRUE)

ifr_runs_test(hsb, read, threshold = 0)

Two Independent Sample t Test

Description

ifr_ts_ind_ttest compares the means of two independent groups in order to determine whether there is statistical evidence that the associated population means are significantly different.

Usage

ifr_ts_ind_ttest(
  data,
  x,
  y,
  confint = 0.95,
  alternative = c("both", "less", "greater", "all"),
  ...
)

Arguments

data

a data frame

x

factor; a column in data

y

numeric; a column in data

confint

confidence level

alternative

a character string specifying the alternative hypothesis, must be one of "both" (default), "greater", "less" or "all". You can specify just the initial letter

...

additional arguments passed to or from other methods

Value

ifr_ts_ind_ttest returns an object of class "ifr_ts_ind_ttest". An object of class "ifr_ts_ind_ttest" is a list containing the following components:

levels

levels of x

obs

number of observations of y for each level of x

n

total number of observations

mean

mean of y for each level of x

sd

standard deviation of y for each level of x

se

estimate of standard error of y for each level of x

lower

lower limit for the mean of y for each level of x

upper

upper limit for the mean of y for each level of x

combined

a data frame; mean, standard deviation, standard error and confidence limit of mean of y

mean_diff

difference in mean of y for the two groups of x

se_dif

estimate of the standard error for difference in mean of y for the two groups of x

sd_dif

degrees of freedom

conf_diff

confidence interval for mean_diff

df_pooled

degrees of freedom for the pooled method

df_satterthwaite

degrees of freedom for the Satterthwaite method

t_pooled

t statistic for the pooled method

t_satterthwaite

t statistic for the Satterthwaite method

sig_pooled

two-sided p-value for the pooled method

sig_pooled_l

lower one-sided p-value for the pooled method

sig_pooled_u

upper one-sided p-value for the pooled method

sig

two-sided p-value for the Satterthwaite method

sig_l

lower one-sided p-value for the Satterthwaite method

sig_u

upper one-sided p-value for the Satterthwaite method

num_df

numerator degrees of freedom for folded f test

den_df

denominator degrees of freedom for folded f test

f

f value for the equality of variances test

f_sig

p-value for the folded f test

var_y

name of y

confint

confidence level

alternative

alternative hypothesis

Deprecated Function

infer_ts_ind_ttest() has been deprecated. Instead use ifr_ts_ind_ttest().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

t.test

Examples

# lower tail
ifr_ts_ind_ttest(hsb, female, write, alternative = 'less')

# upper tail
ifr_ts_ind_ttest(hsb, female, write, alternative = 'greater')

# both tails
ifr_ts_ind_ttest(hsb, female, write, alternative = 'both')

# all tails
ifr_ts_ind_ttest(hsb, female, write, alternative = 'all')

Paired t test

Description

ifr_ts_paired_ttest tests that two samples have the same mean, assuming paired data.

Usage

ifr_ts_paired_ttest(
  data,
  x,
  y,
  confint = 0.95,
  alternative = c("both", "less", "greater", "all")
)

Arguments

data

a data.frame or tibble

x

numeric; column in data

y

numeric; column in data

confint

confidence level

alternative

a character string specifying the alternative hypothesis, must be one of "both" (default), "greater", "less" or "all". You can specify just the initial letter.

Value

ifr_ts_paired_ttest returns an object of class "ifr_ts_paired_ttest". An object of class "ifr_ts_paired_ttest" is a list containing the following components:

Obs

number of observations

b

mean, standard deviation and standard error of x, y and their difference

tstat

t statistic

p_lower

lower one-sided p-value

p_upper

upper one-sided p-value

p_two_tail

two sided p-value

corr

Correlation of x and y

corsig

p-value of correlation test

conf_int1

confidence interval for mean of x

conf_int2

confidence interval for mean of y

conf_int_diff

confidence interval for mean of difference of x and y

df

degrees of freedom

confint

confidence level

alternative

alternative hypothesis

var_names

names of x and y

xy

string used in printing results of the test

Deprecated Function

infer_ts_paired_ttest() has been deprecated. Instead use ifr_ts_paired_ttest().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

t.test

Examples

# lower tail
ifr_ts_paired_ttest(hsb, read, write, alternative = 'less')

# upper tail
ifr_ts_paired_ttest(hsb, read, write, alternative = 'greater')

# both tails
ifr_ts_paired_ttest(hsb, read, write, alternative = 'both')

# all tails
ifr_ts_paired_ttest(hsb, read, write, alternative = 'all')

Two Sample Test of Proportion

Description

Tests on the equality of proportions using large-sample statistics. It tests that a sample has the same proportion within two independent groups or two samples have the same proportion.

Usage

ifr_ts_prop_test(
  data,
  var1,
  var2,
  alternative = c("both", "less", "greater", "all"),
  ...
)

ifr_ts_prop_group(
  data,
  var,
  group,
  alternative = c("both", "less", "greater", "all")
)

ifr_ts_prop_calc(
  n1,
  n2,
  p1,
  p2,
  alternative = c("both", "less", "greater", "all"),
  ...
)

Arguments

data

a data.frame or tibble

var1

factor; column in data

var2

factor; column in data

alternative

a character string specifying the alternative hypothesis, must be one of "both" (default), "greater", "less" or "all". You can specify just the initial letter

...

additional arguments passed to or from other methods

var

factor; column in data

group

factor; column in data

n1

sample 1 size

n2

sample 2 size

p1

sample 1 proportion

p2

sample 2 proportion

Value

an object of class "ifr_ts_prop_test". An object of class "ifr_ts_prop_test" is a list containing the following components:

n1

sample 1 size

n2

sample 2 size

phat1

sample 1 proportion

phat2

sample 2 proportion

z

z statistic

sig

p-value for z statistic

alt

alternative hypothesis

Deprecated Functions

infer_ts_prop_test(), infer_ts_prop_grp() and infer_ts_prop_calc() have been deprecated. Instead use ifr_ts_prop_test(), ifr_ts_prop_group() and ifr_ts_prop_calc().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

prop.test

Examples

# using variables
# lower tail
ifr_ts_prop_test(treatment, treatment1, treatment2,
alternative = 'less')

# using groups
# lower tail
ifr_ts_prop_group(treatment2, outcome, female,
alternative = 'less')

# using sample size and proportions
# lower tail
ifr_ts_prop_calc(n1 = 30, n2 = 25, p1 = 0.3, p2 = 0.5, alternative = 'less')

Two Sample Variance Comparison Test

Description

ifr_ts_var_test performs tests on the equality of standard deviations (variances).

Usage

ifr_ts_var_test(
  data,
  ...,
  group_var = NULL,
  alternative = c("less", "greater", "all")
)

Arguments

data

a data.frame or tibble

...

numeric; column(s) in data

group_var

factor; column in data

alternative

a character string specifying the alternative hypothesis, must be one of "both" (default), "greater", "less" or "all". You can specify just the initial letter.

Value

ifr_ts_var_test returns an object of class "ifr_ts_var_test". An object of class "ifr_ts_var_test" is a list containing the following components:

f

f statistic

lower

lower one-sided p-value

upper

upper one-sided p-value

two_tail

two-sided p-value

vars

variances for each level of the grouping variable

avgs

means for each level of the grouping variable

sds

standard deviations for each level of the grouping variable

ses

standard errors for each level of the grouping variable

avg

combined mean

sd

combined standard deviation

se

estimated combined standard error

n1

numerator degrees of freedom

n2

denominator degrees of freedom

lens

number of observations for each level of grouping variable

len

number of observations

lev

levels of the grouping variable

type

alternative hypothesis

Deprecated Function

infer_ts_var_test() has been deprecated. Instead use ifr_ts_var_test().

References

Sheskin, D. J. 2007. Handbook of Parametric and Nonparametric Statistical Procedures, 4th edition. : Chapman & Hall/CRC.

See Also

var.test

Examples

# using grouping variable
ifr_ts_var_test(hsb, read, group_var = female, alternative = 'less')

# using two variables
ifr_ts_var_test(hsb, read, write, alternative = 'less')

Dummy data set for 2 Sample Proportion test

Description

A dataset containing information about two treatments

Usage

treatment

Format

A data frame with 50 rows and 2 variables:

treatment1

result of treatment type 1

treatment2

result of treatment type 2

Dummy data set for 2 Sample Proportion test

Description

A dataset containing information about treatment outcomes

Usage

treatment2

Format

A data frame with 200 rows and 2 variables:

outcome

outcome of treatment

female

gender of patient, 0 for male and 1 for female