StatisticsBackground-Examples.qmd

---
title: "Solved examples for Statistics Background talks"
author: "Alex Sanchez"
output:
  html_document:
    code_folding: show
    toc: yes
    toc_float: 
      toc_collapsed: yes
    toc_depth: 3
    theme: cosmo
    highlight: textmate
    number_sections: yes
editor: 
  markdown: 
    wrap: 72
self_contained: true
---

```{r include=FALSE}
require(knitr)
opts_chunk$set(
concordance=FALSE, echo=TRUE,  warning=FALSE, error=FALSE, message=FALSE)
```

# Data Exploration

Start loading toy dataset

```{r}
toyDataSet <- read.csv("datasets/toyDataSet.txt", sep="", row.names = 1)

```

Compute mean and sd rowwise and columnwise

```{r}
rowM<- apply (toyDataSet,1,mean)
rowSd <- apply (toyDataSet,1,sd)
toyDataSet2 <- data.frame(toyDataSet,means=rowM, SDs = rowSd)
colM<- apply (toyDataSet2,2,mean)
colSd <- apply (toyDataSet2,2,sd)
toyDataSet2 <- rbind(toyDataSet2,means=colM, SDs = colSd)
# install.packages("xlsx")
# WriteXLS::WriteXLS(toyDataSet, "toyDataset.xls")
kableExtra::kable(toyDataSet)
```

- With few variables, numerical summaries are useful, but warning with small sample size!

```{r}
#install(skimr)
library(skimr)
skim(t(toyDataSet))
```