| Title: | Package of the German Book "Statistik mit R und RStudio" by Joerg grosse Schlarmann |
|---|---|
| Description: | All datasets and functions used in the german book "Statistik mit R und RStudio" by grosse Schlarmann (2010-2024) <https://www.produnis.de/R/>. |
| Authors: | Jörg große Schlarmann [aut, cre] |
| Maintainer: | Jörg große Schlarmann <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 1.0.7 |
| Built: | 2024-12-22 06:21:06 UTC |
| Source: | CRAN |
This function fits and compares several models (linear, quadratic, cubic, exponential, logarithmic, sigmoidal, power, logistic) to a given set of dependent and independent variables. It returns either a summary of the models with their R-squared values or predicted values based on the models.
compare.lm(dep, ind, predict = FALSE, steps = 0.01)compare.lm(dep, ind, predict = FALSE, steps = 0.01)
dep |
A numeric vector representing the dependent variable. |
ind |
A numeric vector representing the independent variable. |
predict |
Logical. If TRUE, the function returns predicted values for each model. Defaults to FALSE. |
steps |
Numeric. The step size for generating x-values for predictions. Only used if predict is TRUE. Defaults to 0.01. |
A data frame. If predict is FALSE, returns a data frame with the R-squared values for each model. If predict is TRUE, returns a data frame with the original data and predicted values for each model.
x <- c(6, 9, 12, 14, 30, 35, 40, 47, 51, 55, 60) y <- c(14, 28, 50, 70, 89, 94, 90, 75, 59, 44, 27) compare.lm(y, x) compare.lm(y, x, predict=TRUE)x <- c(6, 9, 12, 14, 30, 35, 40, 47, 51, 55, 60) y <- c(14, 28, 50, 70, 89, 94, 90, 75, 59, 44, 27) compare.lm(y, x) compare.lm(y, x, predict=TRUE)
Datatable of the epa Example
data(epa)data(epa)
A data frame with 620 observations in 6 variables
Variables in the dataset:
sex. a factor with levels m w d, giving the proband's sex
age. a numeric vector
cms. a numeric vector
risk. a dichotome vector, 0 = not at risk, 1 = at risk
expert. a dichotome vector of expert's decision, 0 = not at risk, 1 = at risk
decu. a dichotome vector, 0 = no decubitus, 1 = decubitus
Datatable of the Faktorenbogen Example for factor analysis
data(Faktorenbogen)data(Faktorenbogen)
A data frame with 150 observations in 14 variables
Variables in the dataset:
gender. a factor with levels female male other, giving the proband's gender
age. a numeric vector of proband's age in years
A. Item A of the questionnaire, numeric
B. Item B of the questionnaire, numeric
C. Item C of the questionnaire, numeric
D. Item D of the questionnaire, numeric
E. Item E of the questionnaire, numeric
F. Item F of the questionnaire, numeric
G. Item G of the questionnaire, numeric
H. Item H of the questionnaire, numeric
I. Item I of the questionnaire, numeric
J. Item J of the questionnaire, numeric
K. Item K of the questionnaire, numeric
L. Item L of the questionnaire, numeric
returns a frequency table with absolute and relative frequencies and cumulated frequencies
freqTable(werte)freqTable(werte)
werte |
factor with obeserved data |
dataframe table
x <- ceiling(stats::rnorm(20)) freqTable(x)x <- ceiling(stats::rnorm(20)) freqTable(x)
returns a tibble with all kenngroessen
kenngroessen(werte)kenngroessen(werte)
werte |
numeric vector |
tibble with all kenngroessen
x <- ceiling(stats::rnorm(20)) kenngroessen(x)x <- ceiling(stats::rnorm(20)) kenngroessen(x)
returns borders and length of confidence intervall for binomial proportions
KIbinomial_a(p, n, alpha)KIbinomial_a(p, n, alpha)
p |
proportion obeserved |
n |
number of observations |
alpha |
error niveau |
confidence intervall
KIbinomial_a(0.35, 150, 0.05)KIbinomial_a(0.35, 150, 0.05)
returns borders and length of confidence intervall for difference of binomial proportions
KIbinomial_u(p1, n1, p2, n2, alpha)KIbinomial_u(p1, n1, p2, n2, alpha)
p1 |
proportion obeserved in group 1 |
n1 |
number of observations in group 1 |
p2 |
proportion obeserved in group 2 |
n2 |
number of observations in group 2 |
alpha |
error niveau |
confidence intervall
KIbinomial_u(0.25, 100, 0.4, 150, 0.05)KIbinomial_u(0.25, 100, 0.4, 150, 0.05)
returns borders and length of confidence intervall for mean of normal distributed data
KInormal_a(xquer, s, n, alpha)KInormal_a(xquer, s, n, alpha)
xquer |
mean of obeserved data |
s |
standard deviation of observed data |
n |
number of observations |
alpha |
error niveau |
confidence intervall
KInormal_a(400, 20, 100, 0.05)KInormal_a(400, 20, 100, 0.05)
returns a data.frame with borders and length of confidence intervall for mean of normal distributed data
KInormal_u(x1, s1, n1, x2, s2, n2, alpha)KInormal_u(x1, s1, n1, x2, s2, n2, alpha)
x1 |
mean of obeserved data in group 1 |
s1 |
standard deviation of observed data in group 1 |
n1 |
number of observations in group 1 |
x2 |
mean of obeserved data in group 2 |
s2 |
standard deviation of observed data in group 2 |
n2 |
number of observations in group 2 |
alpha |
error niveau |
data.frame of confidence intervall
KInormal_u(2.22, 0.255, 13, 2.7, 0.306, 10 , 0.05)KInormal_u(2.22, 0.255, 13, 2.7, 0.306, 10 , 0.05)
get longitude and altitude from an address using OpenStreetMap's API at http://nominatim.openstreetmap.org
lon.lat.osm(address = NULL)lon.lat.osm(address = NULL)
address |
a character of an address |
a data.frame containig "address", "lon", "lat"
lon.lat.osm("Eiffeltower")lon.lat.osm("Eiffeltower")
Datatable of the SuperMario Example for Friedman-ANOVA
data(MarioANOVA)data(MarioANOVA)
A data frame with 47 observations in 8 variables
Variables in the dataset:
Name. The characters' name
Alter. The characters' age in years
Kingdom. The characters' home
Geschlecht. The characters' gender (männlich = male, weiblich = female)
BadGuy. Whether the character is a bad guy, logical
t1. Measure at time 1
t2. Measure at time 2
t3. Measure at time 3
Datatable of the Messwiederholung Example for ANOVA
data(Messwiederholung)data(Messwiederholung)
A data frame with 200 observations in 4 variables
Variables in the dataset:
Name. The first name of the probands.
t1. Measure at time 1
t2. Measure at time 2
t3. Measure at time 3
Dataset of a work sampling study
data(mma)data(mma)
A data frame with 9768 observations in 6 variables.
Variables in the dataset:
day. a vector, giving the number of the observation day
time. a factor giving the time of observation
ward. a factor giving the ward under observation
qual. a factor giving the qualification of the nurse
category. a factor of qualification categories
action. a factor giving the observed action
Dataset of the German Nachtwachen study
data(Nachtwachen)data(Nachtwachen)
A data frame with 276 observations in 37 variables.
Dataset of the German Nachtwachen study, labelled version
data(nw)data(nw)
A data frame with 276 observations in 37 variables.
Datatable of an Ordinal Sample
data(OrdinalSample)data(OrdinalSample)
A data frame with 415 observations in 4 variables.
Variables in the dataset:
Konflikt. a numeric vector giving the potential of conflicts.
Zufriedenh. a numeric vector giving the satisfaction of workers
Geschlecht. a factor of proband's sex, 1 = male, 2=female
Stimmung. an ordinal factor of proband's mood
This function performs pairwise Chi-Square tests for two factors.
pairwise.chisq.test(A, B, p.adjust.method = "bonferroni")pairwise.chisq.test(A, B, p.adjust.method = "bonferroni")
A |
A factor with two or moew levels. The first variable. |
B |
A factor with two or more levels. The second variable. |
p.adjust.method |
A string specifying the method for adjusting p-values. Default is "bonferroni". |
This function creates all possible pairs of levels of factor B and performs a Chi-Square test for each pair of B on variable A. The p-values are adjusted according to the specified method.
#' This function is created for educational purposes only. For exact p-values, consider using reporttools::pairwise.fisher.test().
A data frame with the results of the pairwise Chi-Square tests. Includes the groups, Chi-Square statistic, degrees of freedom, p-values, adjusted p-values, and significance stars.
set.seed(123) A <- factor(sample(c("Male", "Female"), 100, replace = TRUE)) B <- factor(sample(c("Location1", "Location2", "Location3"), 100, replace = TRUE)) pairwise.chisq.test(A, B, "holm")set.seed(123) A <- factor(sample(c("Male", "Female"), 100, replace = TRUE)) B <- factor(sample(c("Location1", "Location2", "Location3"), 100, replace = TRUE)) pairwise.chisq.test(A, B, "holm")
This is the dataset of the PF8 example.
data(pf8)data(pf8)
A data frame with 731 observations in 16 variables.
Matrix of Pflegeberufe by Isfort et al. 2018
data(Pflegeberufe)data(Pflegeberufe)
A matrix with 9 cols (years) and 5 rows (nursing profession).
Isfort et al. 2018 (Pflegethermometer)
returns sensitivity specifity, negativ-predictive-value, postitiv-predictive-value
sens.spec(rp, rn, fp, fn)sens.spec(rp, rn, fp, fn)
rp |
number of true-positive (richtig-positiv) |
rn |
number of true-negative (richtig-negativ) |
fp |
number of false-positive (falsch-positiv) |
fn |
number of false-negative (falsch-negativ) |
a data.frame with sens, spec, ppw, npw
sens.spec(40, 17, 85, 4)sens.spec(40, 17, 85, 4)
z-Transformation by given numbers, with z = (x - mu) / sd
ztrans(x, mu = 0, sd = 1)ztrans(x, mu = 0, sd = 1)
x |
a value to transform |
mu |
the given mu |
sd |
the given standard deviation |
the z-transformed value
ztrans(120,mu=118,sd=20)ztrans(120,mu=118,sd=20)