# gsbBayesUpdate: Bayesian Update In gsbDesign: Group Sequential Bayes Design

## Description

Bayesian update from prior and data to posterior for normally distributed data with known sigma.

## Usage

 `1` ```gsbBayesUpdate(alpha, beta, meanData, precisionData, with.alpha = TRUE) ```

## Arguments

 `alpha` `vector` of prior means. `beta` `vector` of prior precisions. `meanData` `vector` of means from data. `precisionData` `vector` of precisions from data. `with.alpha` `logical`. If `with.alpha = TRUE`, `alpha`, `beta`, `meanData` and `precisionData` has to be specified and the posterior means, posterior precisions and weights are returned. Else only `beta` and `precisionData` has to be specified and the posterior precisions and weights are returned.

## Value

 `alpha` posterior means. Only if `with.alpha = TRUE`. `beta` posterior precisions. `weight` weights of the priors relative to the whole information after updating.

## Note

This function is used in the function `gsb()`.

## Author(s)

Florian Gerber <[email protected]>, Thomas Gsponer

`gsb`

## Examples

 ```1 2 3 4 5 6``` ```## One dimensional case, with.alpha = FALSE gsbBayesUpdate(beta=10,precisionData=20, with.alpha=FALSE) ## Two dimensional case, with.alpha = TRUE gsbBayesUpdate(alpha=c(5,6),beta=c(10,11),meanData=c(10,11), precisionData=c(20,21),with.alpha=TRUE) ```

### Example output

```Loading required package: gsDesign
Loading required package: xtable
Loading required package: ggplot2
Loading required package: lattice
Loading required package: grid
\$beta
[1] 30

\$weight
[1] 0.3333333

\$alpha
[1] 8.333333 9.281250

\$beta
[1] 30 32

\$weight
[1] 0.3333333 0.3437500
```

gsbDesign documentation built on Jan. 11, 2020, 9:28 a.m.