In: Statistics and Probability
Scenario. Bank X provides home loan service to their
retail customers and charge a interest rate for their service. Due
to market fluctuations, Bank X only offers floating interest rate
(FIR) for their home loan customers. A friend of you who works as a
banker at Bank X told you that the average yearly FIR in the last
thirty years follows a Normal distribution with mean 3.2% (i.e., μ
= 0.032) and standard deviation 0.04 (i.e., σ = 0.04). In addition,
a sample of size 10 (drawn from N(0.032, 0.0016)) is available to
you which has been summaried in the table below
-0.021 0.029 -0.009 -0.002 0.002 -0.006 0.006 -0.064 0.023 0.031
Table 1: A sample of FIR
Your friend seek help from you to use your knowledge from TSTA602
to assist Bank X to do the following data analysis. Please write a
report to answer all the following questions.
(a). calculate (mannually) the sample mean, and sample
standard de- viation for the sample in Table 1.
(b). if we draw samples of sizes 10 many times and form a
distribution of sample mean, state the distribution of the sample
mean and provide the reason for your conclusion; calculate the mean
of the sample means and its standard deviation.
(c). based on (b), find the probability that the sample
mean is smaller than 0.02. Please keep two decimal places in the
calculation of standardization.
(d). if the sample mean from (a) is your observed value,
calculate the 95% confidence interval for the sample mean.
(e). An outlier is a data point outside the interval [Q1
− 1.5IQR, Q3 + 1.5IQR], where Q1 and Q3 are first and third
quartile respectively, and IQR
1
is the interquartile range. Explain whether there is
any outlier appears in the sample in Table 1? You can calculate Q1
and Q3, and IQR using R (in Rstudio).
(f). Use R (in Rstudio) to generate 1,000,000 samples of
size 10 from N(0.032, 0.0016) (please set the seed equals to 602),
compute the sample mean for each of these samples, draw a histgram
(set the frequency parameter to FALSE) for these sample means and
add a density curve to the histgram. Please provide the histgram
with the density curve here and attach your R code as appendix.
Note : Allowed to solve only 4 questions in one
post.
a. Mean and standard deviation of the sample
b. The distribution of the mean will be normal.
The mean of the sample mean = 0.032
the standard deviation =
The reason for this is the central limit theroem which states that If we repeatedly take a large number of the sample of size n, then the distribution of the sample means will be normally distributed and the mean of the this distributed will be equal to the population mean. As the sample size increase, the sampling distributed tends more to the normal distribution, irrespective of the shape of the population distribution.
c. Probability of less than 0.02
d. 95% confidence interval