4.4 Heights of adults. Researchers studying anthropometry collected body girth measurements and skeletal diameter measurements, as well as age, weight, height and gender, for 507 physically active individuals. The histogram below shows the sample distribution of heights in centimeters.
Point estimate for average height = 147.12, Median = 170.3
Point estimate for st. dev. = 9.4
IQR = 177.8 - 163.8
IQR
## [1] 14
Mean = 171.7
SD = 9.4
Mean - 2* SD
## [1] 152.9
Mean + 2* SD
## [1] 190.5
# 180 cm not considered unusually tall, 155 cm not considered unusually tall either. They are both within 2 SD of the mean
Point estimates based on samples approximate the population so the mean and st dev. of a new sample may be different.
We use SE:
SE = 9.4 / 507^.5
SE
## [1] 0.4174687
4.14 Thanksgiving spending, Part I.
False. The point estimate is always in the confidence interval. Inference is made on the population parameter.
We can be lenient with the skew given the size of the sample.
False, the confidence interval does not make inferences on sample means.
True
True
False, we would need to use a sample 9 time larger.
# True
(89.11-80.31) / 2
## [1] 4.4
4.24 Gifted children, Part I.
Sample observations are independent since it is a random sample and number of children, 36, is very likely to be less than 10 percent of the population.
The sample is greater than 30.
The population distribution is not strongly skewed.
Conditions seem to be satisfied for inference.
H0: mean = 32
HA: mean < 32
mean <- 30.69
sd <- 4.31
n <- 36
se <- sd/sqrt(n)
Z_score <- (mean-32)/se
pvalue <- pnorm(Z_score)
pvalue
## [1] 0.0341013
P-value of 0.034 is smaller than the significance level of 0.10. We reject the null hypothesis since there is sufficient evidence to reject H0 in favor of HA.
low <- 30.69 - (qnorm(0.95) * (4.31 / sqrt(36)))
up <- 30.69 + (qnorm(0.95) * (4.31 / sqrt(36)))
c(low, up)
## [1] 29.50845 31.87155
While the hypothesis test rejected the null hypothesis, the average of 32 months is also not within the confidence interval. So results from the hypothesis test and the confidence interval agree.
4.26 Gifted children, Part II.
H0 = 100 IQ HA ≠ 100 α = 0.10
Z_score <- (118.2 - 100) / (6.5 / sqrt(36))
Z_score
## [1] 16.8
p_value <- 2 * (pnorm(Z_score, 0, 1, lower.tail = FALSE))
p_value
## [1] 2.44044e-63
low <- 118.2 - (qnorm(0.95) * (6.5 / sqrt(36)))
up <- 118.2 + (qnorm(0.95) * (6.5 / sqrt(36)))
c(low,up)
## [1] 116.4181 119.9819
Yes they do. The p-value is much lower than the significance level of 0.10. The confidence interval does not include the average IQ of 100 for the population.
4.34 Define the term “sampling distribution” of the mean, and describe how the shape, center, and spread of the sampling distribution of the mean change as sample size increases.
The distribution of sample means, called the sampling distributio The sampling distribution is the distribution of sample means. As the sample size increases, the shape of the distribution becomes more normal, the center is closer to the true mean, and the spread of the samples are smaller and vice versa.
4.40 CFLBs. A manufacturer of compact fluorescent light bulbs advertises that the distribution of the lifespans of these light bulbs is nearly normal with a mean of 9,000 hours and a standard deviation of 1,000 hours.
1 - pnorm(q = 10500, mean = 9000, sd = 1000)
## [1] 0.0668072
The sample will approximate normal distribution since the population has normal distribution.
se <- 1000/sqrt(15)
se
## [1] 258.1989
N(9000, 258.1989)
pnorm(10500, 9000, 1000/sqrt(15), lower.tail = FALSE)
## [1] 3.133452e-09
sd<-1000
mean<-9000
se <- sd / sqrt(15)
norm <- seq(mean - (4 * sd), mean + (4 * sd), length=15)
random<- seq(mean - (4 * se), mean + (4 * se), length=15)
norm2 <- dnorm(norm, mean, sd)
random2 <- dnorm(random, mean, se)
plot(norm, norm2, type="l",col="red",
xlab="Lightbulb Population vs Sampling",
main="Distribution", ylim=c(0,0.0020))
lines(random, random2, col="blue")
The parameters are based on the population so We can’t estimate (a) without a normal distribution. We can’t estimate (c) either because the sample size is less than 30.
4.48 Same observation, di↵erent sample size. Suppose you conduct a hypothesis test based on a sample where the sample size is n = 50, and arrive at a p-value of 0.08. You then refer back to your notes and discover that you made a careless mistake, the sample size should have been n = 500. Will your p-value increase, decrease, or stay the same? Explain.
The p-value depends on the z-value. Since the denominator of the z-value calculation is the standard error, an increase in sample size would result in a decrease in the standard error and an increase the z-value determined. That would result in a decrease in p-value.