Quantitative Methods for LEL

.title[
# Quantitative Methods for LEL
]
.subtitle[
## Week 3
]
.author[
### Dr Stefano Coretta
]
.institute[
### University of Edinburgh
]
.date[
### 2023/10/03
]

---

---

## Data visualisation

---

## Good data visualisation

.bg-washed-blue.b--dark-blue.ba.bw2.br3.shadow-5.ph4.mt2[
Alberto Cairo has identified four common features of good data visualisation ([Spiegelhalter 2019](https://www.penguin.co.uk/books/294857/the-art-of-statistics-by-spiegelhalter-david/9780241258767):64-66):

1. It contains **reliable information**.

2. The design has been chosen so that relevant **patterns become noticeable**.

3. It is presented in an **attractive** manner, but appearance should not get in the way of **honesty, clarity and depth**.

4. When appropriate, it is organized in a way that **enables some exploration**.
]

---

---

## Endangerment status

```r
glot_status
```

```
## # A tibble: 8,345 × 18
##    ID        Language_ID Parameter_ID Value Code_ID Comment Source codeReference status Name  Macroarea
##    <chr>     <chr>       <chr>        <chr> <chr>   <chr>   <chr>  <lgl>         <fct>  <chr> <chr>    
##  1 kolp1236… kolp1236    aes          3     aes-sh… Kol (1… hh:he… NA            shift… Kol … Papunesia
##  2 tana1288… tana1288    aes          3     aes-sh… Tanahm… hh:he… NA            shift… Tana… Papunesia
##  3 touo1238… touo1238    aes          3     aes-sh… Touo (… hh:he… NA            shift… Touo  Papunesia
##  4 bert1248… bert1248    aes          3     aes-sh… Fadash… hh:he… NA            shift… Berta Africa   
##  5 sius1254… sius1254    aes          6     aes-ex… Siusla… hh:he… NA            extin… Sius… North Am…
##  6 cent2045… cent2045    aes          6     aes-ex… Jalaa … <NA>   NA            extin… Jalaa Africa   
##  7 else1239… else1239    aes          3     aes-sh… Elseng… hh:he… NA            shift… Else… Papunesia
##  8 taia1239… taia1239    aes          4     aes-mo… Taiap … hh:he… NA            morib… Taiap Papunesia
##  9 pyuu1245… pyuu1245    aes          3     aes-sh… Pyu (4… hh:he… NA            shift… Pyu   Papunesia
## 10 mato1253… mato1253    aes          6     aes-ex… Arára … hh:he… NA            extin… Mato… South Am…
## # ℹ 8,335 more rows
## # ℹ 7 more variables: Latitude <dbl>, Longitude <dbl>, Glottocode <chr>, ISO639P3code <chr>,
## #   Countries <chr>, Family_ID <chr>, Language_ID.y <chr>
```

---

## Bar chart

???

Bar charts are great for counts (of anything).

The *x*-axis includes the level of status, while the *y*-axis shows the number of languages per status level.

---

## Stacked bar chart

---

???

In this plot I separated endangered vs non-endangered languages.
Within the endangered languages I further show the counts of different status levels.

---

???

Here, the *x*-axis corresponds to the language macro-areas in the data.
Within each bar, the counts for each of the status levels is given.

---

## Stacked proportion (filled) bar chart

???

So far we have seen raw counts.
What about proportions?

You can show proportions by using a "filled" bar chart.
Each bar is stretched so that covers the entire range from 0 to 1.

Note that proportions are between 0 and 1, while percentages are between 0 and 100%.

By default, `geom_bar()` adds a *y* label "counts" so you have to manually change the label to "proportions".

---

## Dot matrix chart

---

## Mosaic plot

---

## Formant values

```r
formants
```

```
## # A tibble: 24,012 × 22
##    speaker file     word   time    f3    f0 language gender glottocode  item ipa   c1    c1_phonation
##    <chr>   <chr>    <chr> <dbl> <dbl> <dbl> <chr>    <chr>  <chr>      <dbl> <chr> <chr> <chr>       
##  1 it01    it01-001 pugu  0.111 2280.  137. Italian  m      ital1282      20 pugu  p     voiceless   
##  2 it01    it01-001 pugu  0.111 2280.  137. Italian  m      ital1282      20 pugu  p     voiceless   
##  3 it01    it01-001 pugu  0.222 2124.  134. Italian  m      ital1282      20 pugu  p     voiceless   
##  4 it01    it01-001 pugu  0.222 2124.  134. Italian  m      ital1282      20 pugu  p     voiceless   
##  5 it01    it01-001 pugu  0.333 2314.  134. Italian  m      ital1282      20 pugu  p     voiceless   
##  6 it01    it01-001 pugu  0.333 2314.  134. Italian  m      ital1282      20 pugu  p     voiceless   
##  7 it01    it01-001 pugu  0.444 2374.  135. Italian  m      ital1282      20 pugu  p     voiceless   
##  8 it01    it01-001 pugu  0.444 2374.  135. Italian  m      ital1282      20 pugu  p     voiceless   
##  9 it01    it01-001 pugu  0.556 2307.  137. Italian  m      ital1282      20 pugu  p     voiceless   
## 10 it01    it01-001 pugu  0.556 2307.  137. Italian  m      ital1282      20 pugu  p     voiceless   
## # ℹ 24,002 more rows
## # ℹ 9 more variables: vowel <chr>, anteropost <chr>, height <chr>, c2 <chr>, c2_phonation <chr>,
## #   c2_place <chr>, formant <chr>, value <dbl>, id <chr>
```

---

## Line plot

---

---

---

---

## Infant gestures

```r
gestures
```

```
## # A tibble: 1,620 × 11
##    dyad  background months task  gesture count_raw count ct_raw    ct pro_rata    id
##    <chr> <chr>       <dbl> <chr> <chr>       <dbl> <dbl>  <dbl> <dbl> <chr>    <dbl>
##  1 b01   Bengali        10 five  reach           5     5      1     1 no           3
##  2 b01   Bengali        10 five  point           0     0      0     0 no           2
##  3 b01   Bengali        10 five  ho_gv           0     0      0     0 no           1
##  4 b01   Bengali        10 tp1   reach           0     0      0     0 no           6
##  5 b01   Bengali        10 tp1   point           0     0      0     0 no           5
##  6 b01   Bengali        10 tp1   ho_gv           0     0      0     0 no           4
##  7 b01   Bengali        10 tp2   reach           0     0      0     0 no           9
##  8 b01   Bengali        10 tp2   point           0     0      0     0 no           8
##  9 b01   Bengali        10 tp2   ho_gv           0     0      0     0 no           7
## 10 b01   Bengali        11 five  reach           7     8      3     3 yes          3
## # ℹ 1,610 more rows
```

---

## More line plots

---

---

---

---

## Connected dots plot

---

---

---

## Phonetics of politeness

```r
polite
```

```
## # A tibble: 224 × 27
##    subject gender birthplace musicstudent months_ger scenario task  attitude total_duration
##    <chr>   <chr>  <chr>      <chr>             <dbl>    <dbl> <chr> <chr>             <dbl>
##  1 F1      F      seoul_area yes                  18        6 not   inf               55.2 
##  2 F1      F      seoul_area yes                  18        6 not   pol               28.5 
##  3 F1      F      seoul_area yes                  18        7 not   inf               60.3 
##  4 F1      F      seoul_area yes                  18        7 not   pol               40.8 
##  5 F1      F      seoul_area yes                  18        1 dct   pol               18.4 
##  6 F1      F      seoul_area yes                  18        1 dct   inf               13.6 
##  7 F1      F      seoul_area yes                  18        2 dct   pol                5.22
##  8 F1      F      seoul_area yes                  18        2 dct   inf                4.25
##  9 F1      F      seoul_area yes                  18        3 dct   pol                6.79
## 10 F1      F      seoul_area yes                  18        3 dct   inf                4.13
## # ℹ 214 more rows
## # ℹ 18 more variables: articulation_rate <dbl>, f0mn <dbl>, f0sd <dbl>, f0range <dbl>, inmn <dbl>,
## #   insd <dbl>, inrange <dbl>, shimmer <dbl>, jitter <dbl>, HNRmn <dbl>, H1H2 <dbl>,
## #   breath_count <dbl>, filler_count <dbl>, hiss_count <dbl>, nasal_count <dbl>, sil_count <dbl>,
## #   ya_count <dbl>, yey_count <dbl>
```

---

## Strip chart

---

---

---

## Density plot

---

---

---

---

---

## Violin plot

---

---

---

---

---

## Scatter plot

---

---

---

---

---

---

---

## DO'S AND DON'TS

---

## DO

---

???

Bar charts should be used for discrete numeric variables, not for continuous variables.

---

???

If you want to show proportions, instead of raw counts, use proportion bar charts (aka filled bar chart).

---

???

To show proportions from multiple subjects/items, use strip charts.

---

## DON'T

???

Never ever ever use bar charts with error bars to show mean proportions. They are misleading:

- The bars do not indicate a discrete numeric values: mean proportions are continuous variables.
- Error bars mask the true variability of the data: show raw proportions instead.

For more see: https://www.data-to-viz.com/caveat/error_bar.html, https://stats.stackexchange.com/questions/349422/does-it-make-sense-to-add-error-bars-in-a-bar-chart-of-frequencies/367889#367889

---

## DO

???

For continuous variables, like acoustic measures or reaction times, use violins with overlaid strip charts. You can include very narrow box plots, but remember that box plots mask variability in the raw data.

---

## DON'T

???

Can you see what difference it makes to use box plots only?

---

## Summary

.bg-washed-blue.b--dark-blue.ba.bw2.br3.shadow-5.ph4.mt2[
- Carefully think about which type of variable you are working with: **continuous or discrete**?

- The type of variable allows you to select appropriate types of plots. Your **go-to plots** are:

- Bar charts (and variants).
  - Strip charts.
  - Line plots.
  - Density plots.
  - Violin plots.

- Be mindful of the **DOs and DON'Ts** of plotting.
]