Question 1

Setup

metro_area <- c("Atlanta", "Boston", "Chicago", "Dallas", "Denver", "Detroit", "LasVegas", "LosAngeles", "MiamiFt.Lauderdale", "MinneapolisStPaul", "NewYork", "Phoenix", "Portland", "SanDiego", "SanFrancisco", "Seattle", "Tampa", "WashingtonDC")
price_change <- c(1.2, -3.4, -0.9, 0.8, -0.7, -9.7, -6.1, -4.8, -6.4, -3.4, -3.8, -7.3, 3.8, -7.8, -4.1, 6.9, -8.8, -7.2)
loan_payments_overdue <- c(4.55, 3.31, 2.99, 4.26, 3.56, 4.71, 4.9, 3.05, 5.63, 3.01, 3.29, 3.26, 1.93, 3.45, 2.29, 1.65, 4.6, 3.14)

data <- data.frame(metro_area, price_change, loan_payments_overdue)

Question 1A

model <- lm(price_change ~ loan_payments_overdue, data)
r_squared <- summary(model)$r.squared
adj_r_squared <- summary(model)$adj.r.squared
r_squared
## [1] 0.2791527
adj_r_squared
## [1] 0.2340997
#An R-squared value of 0.2340997 means that about 23.41% of the variability in the percentage change in average home prices (Y) from July 2006 to July 2007 can be explained by the percentage of mortgage loans 30 days or more overdue (x) in the model. To me, this low R-Squared value indicates a weak relationship.

Question 1B

cov_matrix <- vcov(model)

se_beta0 <- sqrt(cov_matrix[1, 1])
se_beta1 <- sqrt(cov_matrix[2, 2])
se_beta0
## [1] 3.324019
se_beta1
## [1] 0.9033113
cov_matrix
##                       (Intercept) loan_payments_overdue
## (Intercept)             11.049104            -2.8821922
## loan_payments_overdue   -2.882192             0.8159714
# The covarience indicates that when loan payments overdue increases, the Intercept tends to decrease.

Question 1C

X <- cbind(1, data$x)

validity_check <- t(X) %*% (model$residuals)

Question 1D

conf_interval <- confint(model)[2, ]
conf_interval
##      2.5 %     97.5 % 
## -4.1634543 -0.3335853

Question 1E

predicted_value <- predict(model, newdata = data.frame(x = 4))
## Warning: 'newdata' had 1 row but variables found have 18 rows
conf_interval_predict <- predict(model, newdata = data.frame(x = 4), interval = "confidence")
## Warning: 'newdata' had 1 row but variables found have 18 rows
predicted_value
##          1          2          3          4          5          6          7 
## -5.7162712 -2.9281067 -2.2085804 -5.0642005 -3.4902367 -6.0760344 -6.5032532 
##          8          9         10         11         12         13         14 
## -2.3434916 -8.1446726 -2.2535508 -2.8831363 -2.8156807  0.1748506 -3.2428995 
##         15         16         17         18 
## -0.6346165  0.8044361 -5.8286972 -2.5458584
conf_interval_predict
##           fit        lwr         upr
## 1  -5.7162712  -8.491488 -2.94105466
## 2  -2.9281067  -4.949096 -0.90711737
## 3  -2.2085804  -4.440490  0.02332940
## 4  -5.0642005  -7.481961 -2.64644037
## 5  -3.4902367  -5.466633 -1.51384038
## 6  -6.0760344  -9.074366 -3.07770248
## 7  -6.5032532  -9.784038 -3.22246870
## 8  -2.3434916  -4.524323 -0.16266040
## 9  -8.1446726 -12.621330 -3.66801522
## 10 -2.2535508  -4.467903 -0.03919862
## 11 -2.8831363  -4.912535 -0.85373738
## 12 -2.8156807  -4.858976 -0.77238591
## 13  0.1748506  -3.474377  3.82407801
## 14 -3.2428995  -5.224844 -1.26095515
## 15 -0.6346165  -3.726845  2.45761233
## 16  0.8044361  -3.305859  4.91473096
## 17 -5.8286972  -8.671972 -2.98542254
## 18 -2.5458584  -4.659489 -0.43222788

Question 2

Setup

library(faraway)
data(sat)
View(sat)

Question 2A

model <- lm(total ~ expend + ratio + salary, data = sat)
summary(model)
## 
## Call:
## lm(formula = total ~ expend + ratio + salary, data = sat)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -140.911  -46.740   -7.535   47.966  123.329 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 1069.234    110.925   9.639 1.29e-12 ***
## expend        16.469     22.050   0.747   0.4589    
## ratio          6.330      6.542   0.968   0.3383    
## salary        -8.823      4.697  -1.878   0.0667 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 68.65 on 46 degrees of freedom
## Multiple R-squared:  0.2096, Adjusted R-squared:  0.1581 
## F-statistic: 4.066 on 3 and 46 DF,  p-value: 0.01209

Question 2B

t_test_salary <- summary(model)$coefficients["salary", "t value"]
p_value_salary <- summary(model)$coefficients["salary", "Pr(>|t|)"]
p_value_salary
## [1] 0.06666771
t_test_salary
## [1] -1.878437
cat("T-test for βsalary: t =", t_test_salary, "p-value =", p_value_salary, "\n")
## T-test for βsalary: t = -1.878437 p-value = 0.06666771

Question 2C

f_test <- summary(model)$fstatistic
p_value_f_test <- pf(f_test[1], f_test[2], f_test[3], lower.tail = FALSE)
f_test
##     value     numdf     dendf 
##  4.066203  3.000000 46.000000
p_value_f_test
##      value 
## 0.01208607
#Yes it appears that the salary, ratio and expend impacts SAT scores based on the p-value of .012

Question 2D

model_takers <- lm(total ~ expend + ratio + salary + takers, data = sat)
anova_result <- anova(model, model_takers)
cat("F-test comparing the two models:\n")
## F-test comparing the two models:
print(anova_result)
## Analysis of Variance Table
## 
## Model 1: total ~ expend + ratio + salary
## Model 2: total ~ expend + ratio + salary + takers
##   Res.Df    RSS Df Sum of Sq      F    Pr(>F)    
## 1     46 216812                                  
## 2     45  48124  1    168688 157.74 2.607e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
t_test_takers <- summary(model_takers)$coefficients["takers", "t value"]
p_value_takers <- summary(model_takers)$coefficients["takers", "Pr(>|t|)"]

cat("T-test for βtakers: t =", t_test_takers, "p-value =", p_value_takers, "\n")
## T-test for βtakers: t = -12.55937 p-value = 2.606559e-16

Question 3

setup

data(prostate)

Question 3A

original_model <- lm(lpsa ~ ., data = prostate)
original_model <- lm(lpsa ~ ., data = prostate)
summary(original_model)
## 
## Call:
## lm(formula = lpsa ~ ., data = prostate)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.7331 -0.3713 -0.0170  0.4141  1.6381 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  0.669337   1.296387   0.516  0.60693    
## lcavol       0.587022   0.087920   6.677 2.11e-09 ***
## lweight      0.454467   0.170012   2.673  0.00896 ** 
## age         -0.019637   0.011173  -1.758  0.08229 .  
## lbph         0.107054   0.058449   1.832  0.07040 .  
## svi          0.766157   0.244309   3.136  0.00233 ** 
## lcp         -0.105474   0.091013  -1.159  0.24964    
## gleason      0.045142   0.157465   0.287  0.77503    
## pgg45        0.004525   0.004421   1.024  0.30886    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.7084 on 88 degrees of freedom
## Multiple R-squared:  0.6548, Adjusted R-squared:  0.6234 
## F-statistic: 20.86 on 8 and 88 DF,  p-value: < 2.2e-16
significant_predictors <- subset(summary(original_model)$coefficients, 'Pr(>|t|)' <= 0.05)
selected_predictors <- rownames(significant_predictors)

Question 3B

set.seed(123)
perm_test_stat <- function(data) {
  perm_model <- lm(lpsa ~ age, data = data)
  return(summary(perm_model)$coef[2, 3])
}

Question 4

Setup

library(faraway)
data(fat)

Question 4A

full_model <- lm(brozek ~ ., data = fat)
summary(full_model)
## 
## Call:
## lm(formula = brozek ~ ., data = fat)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1.11191 -0.04847  0.00277  0.04625  1.47542 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 12.1524013  4.1718589   2.913  0.00393 ** 
## siri         0.8884085  0.0111341  79.792  < 2e-16 ***
## density     -9.8456305  3.7471770  -2.627  0.00917 ** 
## age         -0.0005268  0.0012935  -0.407  0.68421    
## weight       0.0084855  0.0036200   2.344  0.01991 *  
## height      -0.0005459  0.0044439  -0.123  0.90234    
## adipos      -0.0153248  0.0124778  -1.228  0.22062    
## free        -0.0097388  0.0044270  -2.200  0.02880 *  
## neck         0.0005002  0.0094279   0.053  0.95773    
## chest        0.0021454  0.0043013   0.499  0.61840    
## abdom        0.0014464  0.0044217   0.327  0.74388    
## hip         -0.0044514  0.0058941  -0.755  0.45087    
## thigh        0.0156926  0.0059507   2.637  0.00892 ** 
## knee        -0.0252126  0.0098531  -2.559  0.01113 *  
## ankle        0.0027790  0.0089580   0.310  0.75667    
## biceps      -0.0147134  0.0069201  -2.126  0.03454 *  
## forearm      0.0149983  0.0080832   1.855  0.06478 .  
## wrist        0.0326518  0.0218000   1.498  0.13554    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.1706 on 234 degrees of freedom
## Multiple R-squared:  0.9995, Adjusted R-squared:  0.9995 
## F-statistic: 3.046e+04 on 17 and 234 DF,  p-value: < 2.2e-16

Question 4B

smaller_model <- lm(brozek ~ age + weight + height + abdom, data = fat)
summary(smaller_model)
## 
## Call:
## lm(formula = brozek ~ age + weight + height + abdom, data = fat)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -11.5105  -2.9346   0.0087   2.8942   9.4179 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -32.769636   6.541902  -5.009 1.04e-06 ***
## age          -0.007051   0.024342  -0.290    0.772    
## weight       -0.123722   0.025046  -4.940 1.44e-06 ***
## height       -0.116694   0.082727  -1.411    0.160    
## abdom         0.889704   0.067267  13.226  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.126 on 247 degrees of freedom
## Multiple R-squared:  0.7211, Adjusted R-squared:  0.7166 
## F-statistic: 159.7 on 4 and 247 DF,  p-value: < 2.2e-16
# Compare the full model to the smaller model using an F-test
anova_result <- anova(smaller_model, full_model)
cat("F-test comparing the two models:\n")
## F-test comparing the two models:
anova_result
## Analysis of Variance Table
## 
## Model 1: brozek ~ age + weight + height + abdom
## Model 2: brozek ~ siri + density + age + weight + height + adipos + free + 
##     neck + chest + abdom + hip + thigh + knee + ankle + biceps + 
##     forearm + wrist
##   Res.Df    RSS Df Sum of Sq     F    Pr(>F)    
## 1    247 4205.0                                 
## 2    234    6.8 13    4198.2 11096 < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1