-
Notifications
You must be signed in to change notification settings - Fork 5
/
exercises.Rmd
223 lines (143 loc) · 5.86 KB
/
exercises.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
---
title: "R Notebook"
output: html_notebook
---
# Exercises
```{r, eval=FALSE}
suppressMessages(require(Hmisc, quietly = TRUE, warn.conflicts = FALSE))
# open this file
Hmisc::getRs("exercises.Rmd", "couthcommander", "rworkshop")
# open the solutions
Hmisc::getRs("answers.Rmd", "couthcommander", "rworkshop")
```
## Challenge 1
The first time you install a package within a new R session, you must select the CRAN mirror. Usually the best choice is the repository that is geographically closest to you. Once selected subsequent package installations will use this same server.
What command allows you to select a new CRAN mirror?
```{r, eval=FALSE}
```
How do you manually specify the default repository?
```{r, eval=FALSE}
```
## Challenge 2
```{r}
gender <- c('M','M','F','M','F','F','M','F','M')
age <- c(34, 64, 38, 63, 40, 73, 27, 51, 47)
smoker <- c('no','yes','no','no','yes','no','no','no','yes')
exercise <- factor(c('moderate','frequent','some','some','moderate','none',
'none','moderate','moderate'),
levels=c('none','some','moderate','frequent'), ordered=TRUE
)
los <- c(4,8,1,10,6,3,9,4,8)
x <- data.frame(gender, age, smoker, exercise, los)
```
1. Create a linear model using `x`, estimating the association between `los` and all remaining variables
```{r}
```
2. Create a new model, this time predicting `los` by `gender`; show the model summary
```{r}
```
3. What is the estimate for the intercept? What is the estimate for gender?
```{r}
```
4. Re-calculate the standard errors, by taking the square root of the diagonal of the variance-covariance matrix of the summary of the linear model
```{r}
```
5. Predict `los` with the following new data set
```{r}
newdat <- data.frame(gender=c('F','M','F'))
```
6. Sum the square of the residuals of the model. Compare this to passing the model to the `deviance` function.
```{r}
```
7. Create a subset of `x` by taking all records where `gender` is 'M' and assigning it to the variable `men`. Do the same for the variable `women`.
```{r}
```
8. Call the `t.test` function, where the first argument is los for women and the second argument is los for men. Add the argument var.equal and set it to TRUE. Does this match the p-value computed in the model summary?
```{r}
```
## Challenge 3
```{r}
require(splines)
x <- seq(0, 3.5*pi, length=50)
dat <- data.frame(x = x, y = 4 * sin(x) + rnorm(length(x)))
```
1. Create a scatterplot of `dat`.
```{r}
```
2. `f <- lm(y ~ ns(x,1), data = dat)` will create a linear model where `y` is predicted with a natural cubic spline of `x`; in this case it uses a spline with one degree of freedom. Create five models, increasing the degrees of freedom from 1 to 5.
```{r}
```
3. Generate predicted values for the five models with the given data set.
```{r}
newdat <- data.frame(x=seq(x[1]*0.9, x[50]*1.1, length=50))
```
```{r}
```
4. Recreate the scatterplot of `dat`, but add lines for the predicted values (try it with base, ggplot, and plotly).
```{r, base}
```
```{r, ggplot}
```
```{r, plotly}
```
## Challenge 4
1. Retrieve the `titanic3` data set.
```{r}
```
2. Describe the data.
```{r}
```
3. `naclus` can be used to examine missing data. Use it on the dataset and plot the results.
```{r}
```
4. Describe `age`, `sex`, `pclass`, and `embarked` with the `summaryM` function while stratifying on `survived`. Show the output as a table and plot.
```{r}
```
5. Use a logistic regression model (`lrm`) with the formula `survived ~ rcs(age,5)*sex+pclass`. `rcs(age,5)` indicates that age will be represented by a restricted cubic spline with five knots. Save the fit object as `f` and print it.
```{r}
```
6. Obtain predictions for a data.frame that contains variables for `age`, `sex`, and `pclass`. Provide your own values for three or four observations. Pass the predicted values to `plogis` to perform a logistic transformation.
```{r}
```
7. Plot the `nomogram` of the fit object. Add `fun=plogis` as an argument to `nomogram`.
```{r}
```
8. Use `ggplot` and `Predict` to plot the predictors `age`, `sex`, and `pclass`. Include `fun=plogis` as an argument to `Predict`.
```{r}
```
## Challenge 5
The CDC has many available data sets. Take a look at the demographics data file for the [NHANES National Youth Fitness Survey](https://wwwn.cdc.gov/nchs/nhanes/search/nnyfsdata.aspx?Component=Demographics). This is an XPT file, or SAS export file. The code book can be viewed [here](https://wwwn.cdc.gov/Nchs/Nnyfs/Y_DEMO.htm).
1. Download, then import this dataset.
```{r}
```
2. Keep only the following variables: `RIAGENDR, RIDAGEYR, INDHHIN2, DMDHHSIZ`. Describe the data.
```{r}
```
3. Turn `RIAGENDR` into a factor variable with the proper value labels.
```{r}
```
4. Modify `INDHHIN2` by collapsing:
* 1,2,3,4,13 into 1
* 5,6,7,8 into 2
* 9,10,14 into 3
* 15 into 4
* 12,77,99 into NA
Then turn it into an ordered factor variable with the labels `$0-$19999, $20000-$54999, $55000-$99999, $100000+`.
```{r}
```
5. Show the `table` of gender against age, and household income against size.
```{r}
```
## Challenge 6
Suppose you have a sample of N=100 from the Gamma distribution with shape=2 and scale=1. Calculate the 75th percentile with a basic bootstrapped 95% confidence interval for the upper quartile (75th percentile).
```{r}
```
Did the CI work?
```{r}
```
## Challenge 7
[https://fivethirtyeight.com/features/can-you-solve-these-colorful-puzzles/](Puzzler)
You play a game with four balls: One ball is red, one is blue, one is green and one is yellow. They are placed in a box. You draw a ball out of the box at random and note its color. Without replacing the first ball, you draw a second ball and then paint it to match the color of the first. Replace both balls, and repeat the process. The game ends when all four balls have become the same color. What is the expected number of turns to finish the game?
Simulate the answer.
```{r}
```