Exercise 1

Use the table1 package to replicate the table below. Use the examples provided in the following vignette. What do you notice from the table? Which species of penguin is the heaviest? Which one has the largest flippers? Which have the largest bill depth? How are the different species distributed across the three islands?

## Rows: 344
## Columns: 8
## $ species           <fct> Adelie, Adelie, Adelie, Adelie, Adelie, Adelie, Adel…
## $ island            <fct> Torgersen, Torgersen, Torgersen, Torgersen, Torgerse…
## $ bill_length_mm    <dbl> 39.1, 39.5, 40.3, NA, 36.7, 39.3, 38.9, 39.2, 34.1, …
## $ bill_depth_mm     <dbl> 18.7, 17.4, 18.0, NA, 19.3, 20.6, 17.8, 19.6, 18.1, …
## $ flipper_length_mm <int> 181, 186, 195, NA, 193, 190, 181, 195, 193, 190, 186…
## $ body_mass_g       <int> 3750, 3800, 3250, NA, 3450, 3650, 3625, 4675, 3475, …
## $ sex               <fct> male, female, female, NA, female, male, female, male…
## $ year              <int> 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007…
Adelie
(N=152)
Chinstrap
(N=68)
Gentoo
(N=124)
factor(sex)
female 73 (48.0%) 34 (50.0%) 58 (46.8%)
male 73 (48.0%) 34 (50.0%) 61 (49.2%)
Missing 6 (3.9%) 0 (0%) 5 (4.0%)
factor(island)
Biscoe 44 (28.9%) 0 (0%) 124 (100%)
Dream 56 (36.8%) 68 (100%) 0 (0%)
Torgersen 52 (34.2%) 0 (0%) 0 (0%)
body_mass_g
Mean (SD) 3700 (459) 3730 (384) 5080 (504)
Median [Min, Max] 3700 [2850, 4780] 3700 [2700, 4800] 5000 [3950, 6300]
Missing 1 (0.7%) 0 (0%) 1 (0.8%)
flipper_length_mm
Mean (SD) 190 (6.54) 196 (7.13) 217 (6.48)
Median [Min, Max] 190 [172, 210] 196 [178, 212] 216 [203, 231]
Missing 1 (0.7%) 0 (0%) 1 (0.8%)
bill_length_mm
Mean (SD) 38.8 (2.66) 48.8 (3.34) 47.5 (3.08)
Median [Min, Max] 38.8 [32.1, 46.0] 49.6 [40.9, 58.0] 47.3 [40.9, 59.6]
Missing 1 (0.7%) 0 (0%) 1 (0.8%)
bill_depth_mm
Mean (SD) 18.3 (1.22) 18.4 (1.14) 15.0 (0.981)
Median [Min, Max] 18.4 [15.5, 21.5] 18.5 [16.4, 20.8] 15.0 [13.1, 17.3]
Missing 1 (0.7%) 0 (0%) 1 (0.8%)

Answer: As the table shows, the Adelie penguins are distributed across all three islands, while the Chinstrap and Gentoo penguins can only be found on Dream and Biscoe, respectively. The heaviest penguins are the Gentoo species, and they also have the longest flippers. However, the Adelie and Chinstrap penguins have a larger bill depth. While the mean is higer for the Chinstrap penguins, the deepest bill belongs to an Adelie specimen.

Exercise 2

  1. Replicate the scatter plot below, coloring the points according to the species. What can you tell about the relationship between bill depth and penguin weight? Comment on the intercepts and the slopes. Do different species have similar intercepts? Slopes? Does the outcome variable appear normally distributed? Why does this matter?

Answer: There seems to be a positive relationship between bill depth and penguin weight. The Adelie and chinstrap species seemingly have similar values in both, while the Gentoo have a higher weight, but flatter beaks. However the increase in weight per mm bill depth is higher in the Gentoo, leading to a steeper slope. Both the predictor and outcome variable seem normally distributed from the data summary above (mean and median are almost identical with a reasonably small)

Exercise 3

Now replicate the plot below, describing the relationship between flipper length and body mass, and coloring the data according to the associated species. Facet the plot by island (search online if necessary). Finally, tell a story about the relationship between flipper length and weight in these three penguin species, and the distribution of penguins across the three islands.

Answer: Flipper length also seems to be related to Weight positively and linearly. While you can see the species have different distributions and occur on different islands, the relationship seems to be consistent both within the Adelie apecies across islands and between the species.

Exercise 4

Replicate the scatter plot below, adding vertical and horizontal lines to indicate the mean of the predictor and of the outcome variable. Show that the linear regression line passes at the intersection of the two means.

Answer: Why is it piiiiiiiiink?

Exercise 5

Use the lm function in R to fit a simple linear regression with one predictor. Write up your findings using the template below. Fill in the gaps in the template with the result of your model.

## 
## Call:
## lm(formula = body_mass_g ~ flipper_length_mm, data = penguins)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1058.80  -259.27   -26.88   247.33  1288.69 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)       -5780.831    305.815  -18.90   <2e-16 ***
## flipper_length_mm    49.686      1.518   32.72   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 394.3 on 340 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.759,  Adjusted R-squared:  0.7583 
## F-statistic:  1071 on 1 and 340 DF,  p-value: < 2.2e-16
## # A tibble: 2 × 7
##   term              estimate std.error statistic   p.value conf.low conf.high
##   <chr>                <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
## 1 (Intercept)        -5781.     306.       -18.9 5.59e- 55  -6382.    -5179. 
## 2 flipper_length_mm     49.7      1.52      32.7 4.37e-107     46.7      52.7
## # A tibble: 1 × 12
##   r.squared adj.r.squared sigma statistic   p.value    df logLik   AIC   BIC
##       <dbl>         <dbl> <dbl>     <dbl>     <dbl> <dbl>  <dbl> <dbl> <dbl>
## 1     0.759         0.758  394.     1071. 4.37e-107     1 -2528. 5063. 5074.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>

Answer: Linear regression was used to test the association between weight (body_mass_g) and flipper length (flipper_length_mm) using data from n = 344 Penguins. 75.9% of the variation in weight was explained by the model (R2= 0.758). There was a significant positive association between weight and flipper length (B = 49.7; 95% CI = [46.7,52.7]; p < .001). On average, for every 1-mm difference in flipper length, penguins differ in mean weight by 49.7 grams.

Exercise 6

Use the lm function in R to fit predict the body mass using a different explanatory variable. Write up your findings using a similar template like the one used above. Which model is better, in your view? This one or the model in the previous question? Justify your answer.

## 
## Call:
## lm(formula = body_mass_g ~ bill_length_mm, data = penguins)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1762.08  -446.98    32.59   462.31  1636.86 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     362.307    283.345   1.279    0.202    
## bill_length_mm   87.415      6.402  13.654   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 645.4 on 340 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.3542, Adjusted R-squared:  0.3523 
## F-statistic: 186.4 on 1 and 340 DF,  p-value: < 2.2e-16
## # A tibble: 2 × 7
##   term           estimate std.error statistic  p.value conf.low conf.high
##   <chr>             <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
## 1 (Intercept)       362.     283.        1.28 2.02e- 1   -195.       920.
## 2 bill_length_mm     87.4      6.40     13.7  3.81e-34     74.8      100.
## # A tibble: 1 × 12
##   r.squared adj.r.squared sigma statistic  p.value    df logLik   AIC   BIC
##       <dbl>         <dbl> <dbl>     <dbl>    <dbl> <dbl>  <dbl> <dbl> <dbl>
## 1     0.354         0.352  645.      186. 3.81e-34     1 -2697. 5400. 5411.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>
## 
## Call:
## lm(formula = body_mass_g ~ bill_depth_mm, data = penguins)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1607.38  -510.10   -66.96   462.43  1819.28 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    7488.65     335.22   22.34   <2e-16 ***
## bill_depth_mm  -191.64      19.42   -9.87   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 708.1 on 340 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.2227, Adjusted R-squared:  0.2204 
## F-statistic: 97.41 on 1 and 340 DF,  p-value: < 2.2e-16
## # A tibble: 2 × 7
##   term          estimate std.error statistic  p.value conf.low conf.high
##   <chr>            <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
## 1 (Intercept)      7489.     335.      22.3  1.13e-68    6829.     8148.
## 2 bill_depth_mm    -192.      19.4     -9.87 2.28e-20    -230.     -153.
## # A tibble: 1 × 12
##   r.squared adj.r.squared sigma statistic  p.value    df logLik   AIC   BIC
##       <dbl>         <dbl> <dbl>     <dbl>    <dbl> <dbl>  <dbl> <dbl> <dbl>
## 1     0.223         0.220  708.      97.4 2.28e-20     1 -2729. 5463. 5475.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>
## 
## Call:
## lm(formula = body_mass_g ~ year, data = penguins)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1500.5  -648.4  -192.0   549.5  2140.9 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)
## (Intercept) -78977.94  106777.95  -0.740    0.460
## year            41.42      53.18   0.779    0.437
## 
## Residual standard error: 802.4 on 340 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.001782,   Adjusted R-squared:  -0.001154 
## F-statistic: 0.6068 on 1 and 340 DF,  p-value: 0.4365
## # A tibble: 2 × 7
##   term        estimate std.error statistic p.value  conf.low conf.high
##   <chr>          <dbl>     <dbl>     <dbl>   <dbl>     <dbl>     <dbl>
## 1 (Intercept) -78978.   106778.     -0.740   0.460 -289006.    131051.
## 2 year            41.4      53.2     0.779   0.437     -63.2      146.
## # A tibble: 1 × 12
##   r.squared adj.r.squared sigma statistic p.value    df logLik   AIC   BIC
##       <dbl>         <dbl> <dbl>     <dbl>   <dbl> <dbl>  <dbl> <dbl> <dbl>
## 1   0.00178      -0.00115  802.     0.607   0.437     1 -2771. 5549. 5560.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>

Answer: After exploring the other numerical variables, flipper length seems to be the best predictor of weight. The respective explained variations are lower for bill length(R2=0.352;p=), bill depth(R2=0.22;) however both of them are significantly associated (p<0.001). Interestingly, the relationships are of different valence. For every millimeter of bill length, the weight increases by 87.4 grams, while for every millimeter of depth it decreases by 192 grams.

Exercise 7

We now want to fit a model with parallel slopes, one slope for each of the three species of penguins. Run the regression as you have done above, but this time, add the species variable as a predictor in your model. (1) Write the equation for the linear model (you will need to replace the coefficients in the formula b0,b1,b2 with their estimates). (2) Write up your findings in a similar manner to the template shown in the previous question. (3) Write a separate model for each of the three species. (4) Use the augment(M2) to see the list of residuals and show that the mean of the residuals is almost zero and its standard deviation is the residual standard error.

## 
## Call:
## lm(formula = body_mass_g ~ flipper_length_mm + species, data = penguins)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -927.70 -254.82  -23.92  241.16 1191.68 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)       -4031.477    584.151  -6.901 2.55e-11 ***
## flipper_length_mm    40.705      3.071  13.255  < 2e-16 ***
## speciesChinstrap   -206.510     57.731  -3.577 0.000398 ***
## speciesGentoo       266.810     95.264   2.801 0.005392 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 375.5 on 338 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.7826, Adjusted R-squared:  0.7807 
## F-statistic: 405.7 on 3 and 338 DF,  p-value: < 2.2e-16
## # A tibble: 4 × 7
##   term              estimate std.error statistic  p.value conf.low conf.high
##   <chr>                <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
## 1 (Intercept)        -4031.     584.       -6.90 2.55e-11  -5181.    -2882. 
## 2 flipper_length_mm     40.7      3.07     13.3  1.40e-32     34.7      46.7
## 3 speciesChinstrap    -207.      57.7      -3.58 3.98e- 4   -320.      -93.0
## 4 speciesGentoo        267.      95.3       2.80 5.39e- 3     79.4     454.
## # A tibble: 1 × 12
##   r.squared adj.r.squared sigma statistic   p.value    df logLik   AIC   BIC
##       <dbl>         <dbl> <dbl>     <dbl>     <dbl> <dbl>  <dbl> <dbl> <dbl>
## 1     0.783         0.781  376.      406. 1.25e-111     3 -2511. 5032. 5051.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>
## # A tibble: 342 × 10
##    .rownames body_mass_g flipper_length_mm species .fitted .resid    .hat .sigma
##    <chr>           <int>             <int> <fct>     <dbl>  <dbl>   <dbl>  <dbl>
##  1 1                3750               181 Adelie    3336.  414.  0.0120    375.
##  2 2                3800               186 Adelie    3540.  260.  0.00767   376.
##  3 3                3250               195 Adelie    3906. -656.  0.00833   374.
##  4 5                3450               193 Adelie    3825. -375.  0.00724   376.
##  5 6                3650               190 Adelie    3703.  -52.5 0.00662   376.
##  6 7                3625               181 Adelie    3336.  289.  0.0120    376.
##  7 8                4675               195 Adelie    3906.  769.  0.00833   374.
##  8 9                3475               193 Adelie    3825. -350.  0.00724   376.
##  9 10               4250               190 Adelie    3703.  547.  0.00662   375.
## 10 11               3300               186 Adelie    3540. -240.  0.00767   376.
## # ℹ 332 more rows
## # ℹ 2 more variables: .cooksd <dbl>, .std.resid <dbl>
## [1] -1.618022e-14
## [1] 373.8795

Answer: Adding the species improved the accounted variance of the model (R2 = 0.781). The new model takes the Adelie penguins as a baseline and adds 267 grams for a Gentoo or subtracts 207 grams for a Chinstrap penguin. Then the weight increases by 40.7 grams per millimeter flipper length.

Exercise 8

Reproduce the parallel slopes image below using the coefficients from the second model M2.

Answer:

Exercise 9

Search online for an explanation of the various plots (for example, this is a good resource, but you may find others). Create a plot for each of the four diagnostic tests, and describe in words what is the purpose of each diagnostic plot. Then interpret the plot: what can we learn from it?

Answer: Firstly, the residuals vs fitted plot shows if there are patterns in our residuals that do not seem to fit a linear model. While there is a slight bend in our data I do not believe it to be large enough to justify a quadratic model. Secondly, there is the QQ plot, which graphically displays if the residuals are normally distributed. This seems to be the case for our model as all the dots follow the line without systematic deviations. Thirdly, we observe the scale location plot to assess homoscedasticity. In our data the residuals seem to be normally distributed along the values, though there is a hole in the center between 4000-4500 grams, likely resembling the different species. Lastly we see a plot of cooks distance, which shows influential values. The observations 40,170, and 315 stand out and we should investigate if these are measurement errors.

Exercise 10

Run the type 3 Anova, discuss and interpret the output you see and link it to the results of the fitted model summary(M5)

## 
## Call:
## lm(formula = body_mass_g ~ flipper_length_mm + species, data = penguins)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -927.70 -254.82  -23.92  241.16 1191.68 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)       -4031.477    584.151  -6.901 2.55e-11 ***
## flipper_length_mm    40.705      3.071  13.255  < 2e-16 ***
## speciesChinstrap   -206.510     57.731  -3.577 0.000398 ***
## speciesGentoo       266.810     95.264   2.801 0.005392 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 375.5 on 338 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.7826, Adjusted R-squared:  0.7807 
## F-statistic: 405.7 on 3 and 338 DF,  p-value: < 2.2e-16
##                    Df    Sum Sq   Mean Sq F value   Pr(>F)    
## flipper_length_mm   1 166452902 166452902 1180.29  < 2e-16 ***
## species             2   5187807   2593904   18.39 2.62e-08 ***
## Residuals         338  47666988    141027                     
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 2 observations deleted due to missingness

Answer: The Anova indicates that for both flipper length and species the difference between the groups is significantly larger than the variation within groups. This supports our previous results from the linear regression.

Exercise 11

Now repeat exercises 6 - 10 but this time analyze the association between the bill depth and the body mass: body_mass_g ~ bill_depth_mm + species

## 
## Call:
## lm(formula = body_mass_g ~ bill_depth_mm + species, data = penguins)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -867.73 -255.61  -27.41  242.41 1190.86 
## 
## Coefficients:
##                  Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      -1007.28     323.56  -3.113  0.00201 ** 
## bill_depth_mm      256.61      17.56  14.611  < 2e-16 ***
## speciesChinstrap    13.38      52.95   0.253  0.80069    
## speciesGentoo     2238.67      73.68  30.383  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 362.4 on 338 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.7975, Adjusted R-squared:  0.7957 
## F-statistic: 443.8 on 3 and 338 DF,  p-value: < 2.2e-16
## # A tibble: 4 × 7
##   term             estimate std.error statistic  p.value conf.low conf.high
##   <chr>               <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
## 1 (Intercept)       -1007.      324.     -3.11  2.01e- 3  -1644.      -371.
## 2 bill_depth_mm       257.       17.6    14.6   8.10e-38    222.       291.
## 3 speciesChinstrap     13.4      52.9     0.253 8.01e- 1    -90.8      118.
## 4 speciesGentoo      2239.       73.7    30.4   1.16e-98   2094.      2384.
## # A tibble: 1 × 12
##   r.squared adj.r.squared sigma statistic   p.value    df logLik   AIC   BIC
##       <dbl>         <dbl> <dbl>     <dbl>     <dbl> <dbl>  <dbl> <dbl> <dbl>
## 1     0.798         0.796  362.      444. 7.72e-117     3 -2499. 5007. 5026.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>
## # A tibble: 342 × 10
##    .rownames body_mass_g bill_depth_mm species .fitted .resid    .hat .sigma
##    <chr>           <int>         <dbl> <fct>     <dbl>  <dbl>   <dbl>  <dbl>
##  1 1                3750          18.7 Adelie    3791.  -41.4 0.00692   363.
##  2 2                3800          17.4 Adelie    3458.  342.  0.00873   362.
##  3 3                3250          18   Adelie    3612. -362.  0.00690   362.
##  4 5                3450          19.3 Adelie    3945. -495.  0.00876   362.
##  5 6                3650          20.6 Adelie    4279. -629.  0.0185    361.
##  6 7                3625          17.8 Adelie    3560.   64.5 0.00732   363.
##  7 8                4675          19.6 Adelie    4022.  653.  0.0103    361.
##  8 9                3475          18.1 Adelie    3637. -162.  0.00677   363.
##  9 10               4250          20.2 Adelie    4176.   73.7 0.0147    363.
## 10 11               3300          17.1 Adelie    3381.  -80.8 0.0103    363.
## # ℹ 332 more rows
## # ℹ 2 more variables: .cooksd <dbl>, .std.resid <dbl>
## [1] -1.03489e-14
## [1] 360.8383

## 
## Call:
## lm(formula = body_mass_g ~ bill_depth_mm + species, data = penguins)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -867.73 -255.61  -27.41  242.41 1190.86 
## 
## Coefficients:
##                  Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      -1007.28     323.56  -3.113  0.00201 ** 
## bill_depth_mm      256.61      17.56  14.611  < 2e-16 ***
## speciesChinstrap    13.38      52.95   0.253  0.80069    
## speciesGentoo     2238.67      73.68  30.383  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 362.4 on 338 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.7975, Adjusted R-squared:  0.7957 
## F-statistic: 443.8 on 3 and 338 DF,  p-value: < 2.2e-16
##                Df    Sum Sq  Mean Sq F value Pr(>F)    
## bill_depth_mm   1  48840779 48840779   371.8 <2e-16 ***
## species         2 126067249 63033624   479.9 <2e-16 ***
## Residuals     338  44399670   131360                   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 2 observations deleted due to missingness

Answer: Here there seems to be a much bigger difference between the species. The Gentoo species runs entirely seperately from the other two. Thus it might be a better model to combine Adelie and Chinstrap penguins while excluding Gentoo. The 4 assessment plots also indicate this difference showing even clearer bimodal distributions of the residuals, likely violating homoscedasticity. Lastly, observation 170 is an outlier in both models and likely represents a measurement error.