Package 'crashbayes'

Bayesian Estimation Supersedes the t Test (BEST)

Description

Example data from Kruschke (2013) used to compare the quantitative means of two groups using Null-Hypothesis Significance Testing and Bayesian Estimation

Usage

best

Format

best

A data frame with 89 rows and 2 columns:

group

Factor with levels 'drug' or 'placebo'

y

Observed outcome of the IQ test for an individual

Details

Outcomes from two groups of people who take an IQ test. Group 1 (N1 = 47) consumes a "smart drug" and Group 2 (N2 = 42) is a control group that consumes a placebo

The data was simulated randomly from t distributions, in order to generate some outliers.

Source

https://jkkweb.sitehost.iu.edu/BEST/

References

John K. Kruschke, Journal of Experimental Psychology: General, 2013, v.142(2), pp.573-603. (doi: 10.1037/a0029146)

---

Logistic-Normal distribution density function

Description

Probability density function of a variable whose logit is Gaussian.

Usage

dlogitnorm(x, mu, sd)

Arguments

x	Numeric vector. Evaluation value.
mu	Numeric vector. Mean of the latent Gaussian.
sd	Numeric vector. Standard deviation of the latent Gaussian.

References

https://en.wikipedia.org/wiki/Logit-normal_distribution

Examples

dlogitnorm(seq(0.1, 0.9, by = 0.1), 1, 1)

---

Confidence Interval for the residual standard deviation of a linear model

Description

Compute a Confidence Interval

Usage

sigma_ci(x, alpha)

Arguments

x	An object of class lm
alpha

Value

A data.frame with 1 line and variables parameter, point_est, ll and hh.

References

See, for instance,

Examples

sigma_ci(lm(y ~ 1, data.frame(y = rnorm(1e3, sd = 2))), alpha = 0.05)

---