model_slides.utf8

class: center, middle, inverse, title-slide

# <div class="line-block">Getting Started in R<br />
an introduction to data analysis and visualisation</div>
## Modeling Data
### Réka Solymosi, Sam Langton & Emily Buehler
### 4 July 2019

---

class: inverse, center, middle

# Modeling Data

---
## Making inferences from data

---
## Univariate

### Summary of one variable

---
## Univariate

For all variables in dataframe

```r
summary(gapminder)
```

```
##         country        continent        year         lifeExp     
##  Afghanistan:  12   Africa  :624   Min.   :1952   Min.   :23.60  
##  Albania    :  12   Americas:300   1st Qu.:1966   1st Qu.:48.20  
##  Algeria    :  12   Asia    :396   Median :1980   Median :60.71  
##  Angola     :  12   Europe  :360   Mean   :1980   Mean   :59.47  
##  Argentina  :  12   Oceania : 24   3rd Qu.:1993   3rd Qu.:70.85  
##  Australia  :  12                  Max.   :2007   Max.   :82.60  
##  (Other)    :1632                                                
##       pop              gdpPercap       
##  Min.   :6.001e+04   Min.   :   241.2  
##  1st Qu.:2.794e+06   1st Qu.:  1202.1  
##  Median :7.024e+06   Median :  3531.8  
##  Mean   :2.960e+07   Mean   :  7215.3  
##  3rd Qu.:1.959e+07   3rd Qu.:  9325.5  
##  Max.   :1.319e+09   Max.   :113523.1  
## 
```

---
## Univariate

For all variables in dataframe with skimr

```r
library(skimr)
```

---

```r
gapminder %>%  skim()
```

```
## Skim summary statistics
##  n obs: 1704 
##  n variables: 6 
## 
## -- Variable type:factor --------------------------------------------------------------
##   variable missing complete    n n_unique
##  continent       0     1704 1704        5
##    country       0     1704 1704      142
##                              top_counts ordered
##  Afr: 624, Asi: 396, Eur: 360, Ame: 300   FALSE
##      Afg: 12, Alb: 12, Alg: 12, Ang: 12   FALSE
## 
## -- Variable type:integer -------------------------------------------------------------
##  variable missing complete    n    mean       sd    p0        p25     p50
##       pop       0     1704 1704 3e+07    1.1e+08 60011 2793664    7e+06  
##      year       0     1704 1704  1979.5 17.27     1952    1965.75  1979.5
##       p75       p100     hist
##  2e+07       1.3e+09 <U+2587><U+2581><U+2581><U+2581><U+2581><U+2581><U+2581><U+2581>
##   1993.25 2007       <U+2587><U+2583><U+2587><U+2583><U+2583><U+2587><U+2583><U+2587>
## 
## -- Variable type:numeric -------------------------------------------------------------
##   variable missing complete    n    mean      sd     p0     p25     p50
##  gdpPercap       0     1704 1704 7215.33 9857.45 241.17 1202.06 3531.85
##    lifeExp       0     1704 1704   59.47   12.92  23.6    48.2    60.71
##      p75      p100     hist
##  9325.46 113523.13 <U+2587><U+2581><U+2581><U+2581><U+2581><U+2581><U+2581><U+2581>
##    70.85     82.6  <U+2581><U+2582><U+2585><U+2585><U+2585><U+2585><U+2587><U+2583>
```

---
## Bivariate stats

### making comparisons

---
## Numeric - numeric

```r
cor(var1, var2, method = "pearson") # kendall, spearman
```

```r
cor.test(var1, var2, method = "pearson") # kendall, spearman
```

---
## Categorical - categorical

### Cross tabs

```r
chisq.test(table(var1, var2))
```

```r
fisher.test(table(var1, var2))
```

---
## Categorical - categorical

### Odds ratio

```r
library(vcd)

oddsratio(table(var1, var2)) 
```

---
## Categorical - numeric

```r
# t-test
t.test(var1 ~ var2)

# anova
aov(var1 ~ var2, data=mydataframe)
```

---
## Multivariable

```r
fit_1 <- glm(dependent_var ~ independent_var_1 + independent_var_2, data = mydata)
summary(fit_1)
```

---
## Multivariable

```r
fit_2 <- glm(lifeExp ~ continent + gdpPercap, data = gapminder)
summary(fit_2)
```

```
## 
## Call:
## glm(formula = lifeExp ~ continent + gdpPercap, data = gapminder)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -49.241   -4.479    0.347    5.105   25.138  
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)       4.789e+01  3.398e-01  140.93   <2e-16 ***
## continentAmericas 1.359e+01  6.008e-01   22.62   <2e-16 ***
## continentAsia     8.658e+00  5.555e-01   15.59   <2e-16 ***
## continentEurope   1.757e+01  6.257e-01   28.08   <2e-16 ***
## continentOceania  1.815e+01  1.787e+00   10.15   <2e-16 ***
## gdpPercap         4.453e-04  2.350e-05   18.95   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for gaussian family taken to be 70.39368)
## 
##     Null deviance: 284148  on 1703  degrees of freedom
## Residual deviance: 119528  on 1698  degrees of freedom
## AIC: 12093
## 
## Number of Fisher Scoring iterations: 2
```

---
## Multivariable

```r
library(car)
residualPlots(fit_2)
```

```
##           Test stat Pr(>|Test stat|)    
## continent                               
## gdpPercap     19809        < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
```

---
## Multivariable

```r
marginalModelPlots(fit_2)
```

---
## Multivariable

```r
library(effects)
plot(allEffects(fit_2))
```

---
## Multivariable

```r
library(sjPlot)
plot_model(fit_2, show.values = TRUE)
```

---

## Multivariable

```r
p1 <- plot_model(fit_2)
```

```r
ggplot(p1$data) + theme_minimal() +
  geom_vline(xintercept = 1, linetype = "dashed") +
  geom_errorbarh(aes(xmin = conf.low, xmax = conf.high, y = term), height = 0.2) +
  geom_point(aes(y = term, x = estimate), size = 3, col = "red") +
  labs(y = " ", x = "Estimate") + xlim(0,23) +
  scale_y_discrete(labels = c("GDP","Oceania","Europe","Asia","America"))
```

---

## Multivariable