10-Hierarchical-models.Rmd

# (PART) 等級線性迴歸模型 analysis of hierarchical and other dependent data {-}


# 相互依賴數據及簡單的應對方案 {#Hierarchical}

> To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of.
>
> ~ Sir Ronald Aylmer Fisher


```{block2, note-thankslinda, type='rmdnote'}
The Analysis of Hierarchical and Other Dependent Data lectures were orgainised and taught by Professor [Linda Sharples](https://www.lshtm.ac.uk/aboutus/people/sharples.linda), and Dr. [Edmund Njeru Njagi](https://www.lshtm.ac.uk/aboutus/people/njagi.edmund-njeru).
```


```{r Hier-Session01, child = ('10-Hierarchical/Session01.Rmd')}
```


## Practical Hierarchical 01

```{r Hier-Practical01, child = ('10-Hierarchical/Practical01.Rmd')}
```


# 隨機截距模型 random intercept model {#random-intercept}

```{r Hier-Session02, child = ('10-Hierarchical/Session02.Rmd')}
```




## Practical Hierarchical 02

```{r Hier-Practical02, child = ('10-Hierarchical/Practical02.Rmd')}
```




# 隨機截距模型中加入共變量 random intercept model with covariates {#random-inter-cov}


```{r Hier-Session03, child = ('10-Hierarchical/Session03.Rmd')}
```


## Practical Hierarchical 03

```{r Hier-Practical03, child = ('10-Hierarchical/Practical03.Rmd')}
```



# 隨機回歸系數模型  random coefficient model {#random-coefficient}


```{r Hier-Session04, child = ('10-Hierarchical/Session04.Rmd')}
```


## Practical Hierarchical 04

```{r Hier-Practical04, child = ('10-Hierarchical/Practical04.Rmd')}
```




# 縱向研究數據 longitudinal data 1 {#longitudinal1}
 
 
```{r Hier-Session05, child = ('10-Hierarchical/Session05.Rmd')}
```




## Practical 05-Hier



```{r Hier-Practical05, child = ('10-Hierarchical/Practical05.Rmd')}
```



# 縱向研究數據 longitudinal data 2 {#longitudinal2}

```{r Hier-Session06, child = ('10-Hierarchical/Session06.Rmd')}
```




## Practical 06-Hier


```{r Hier-Practical06, child = ('10-Hierarchical/Practical06.Rmd')}
```

# 縱向研究數據 longitudinal data 3 {#longitudinal3}


```{r Hier-Session07, child = ('10-Hierarchical/Session07.Rmd')}
```

## Practical 07-Hier


```{r Hier-Practical07, child = ('10-Hierarchical/Practical07.Rmd')}
```

# 廣義估計方程式 Generalized Estimating Equation
 

```{r Hier-Session08, child = ('10-Hierarchical/Session08.Rmd')}
``` 
 

## Practical 08-Hier


```{r Hier-Practical08, child = ('10-Hierarchical/Practical08.Rmd')}
``` 
 
# 聚類分析 Cluster analysis/unsupervised learning  {#cluster-ana}


```{r Hier-Session09, child = ('10-Hierarchical/Session09.Rmd')}
``` 
 




# 主成分分析 Principal Component Analysis  {#PCA}

> A big computer, a complex algorithm and a long time does not equal science.
> ~ Robert Gentleman


```{block2, note-text, type='rmdnote'}
PCA lecture was taught by Professor [Luigi Palla](https://scholar.google.co.uk/citations?hl=en&user=p-cHaf0AAAAJ&view_op=list_works&sortby=pubdate).
```


```{r Hier-Session11, child = ('10-Hierarchical/Session11.Rmd')}
```



## Cluster analysis/PCA practical 


```{r Hier-Practical11, child = ('10-Hierarchical/Practical11.Rmd')}
``` 


# 缺失數據 Missing data 1 


```{r Hier-Session10, child = ('10-Hierarchical/Session10.Rmd')}
```

## Practical 10-Hier

```{r Hier-Practical10, child = ('10-Hierarchical/Practical10.Rmd')}
```


# 缺失數據 Missing data 2

# Further issues