Questions and Answers of A Course In Statistics With R

In Problems 3–10, determine whether the underlined value is a parameter or a statistic.Following the 2018 national midterm election, 18% of the governors of the 50 United States were female.
In Problems 3–10, determine whether the underlined value is a parameter or a statistic.In a national survey on substance abuse, 13.3% of 12th graders reported using illicit drugs within the past
Stocks sometimes pay dividends to shareholders of the company. A dividend can be thought of as a share of the profit. Dividend yield is the annual dividend divided by the price of the stock. The
The following data represent the median household income (in dollars) for the 50 states and the District of Columbia in 2017.With the first class having a lower class limit of 40,000 and a class
The table shows the tax, in dollars, on a pack of cigarettes in each of the 50 states and Washington, DC, as of January 2015.With a first class having a lower class limit of 0 and a class width of
The following pie chart displays the position played by the most valuable player (MVP) in the National League of Major League Baseball from 1931 through 2018. Explain how the graphic is misleading.
Between 1980 and 2016, the percent of adults in the United States who were overweight more than doubled from 15% to 40%.(a) Construct a graphic that is not misleading to depict this situation.(b)
The average per gallon price for regular unleaded gasoline in the United States rose from $1.46 in 2001 to $2.77 in 2018.(a) Construct a graphic that is not misleading to depict this situation.(b)
The U.S. Census Bureau uses money income thresholds to define poverty. For example, in 2018 the poverty threshold for a family of four with two children was $25,100. The bar graph represents the
Find the stationary distribution for the Ehrenfest Markov Chain.Data from in stationary distributionIf we have an ergodic Markov Chain, we know that each state will be visited infinitely often.
Suppose that you have a new observation xnew. Find details with ?predict. glm and use them for prediction purposes for any xnew of your choice with chdglm.
The R code tosscoin(times=3) returns an object of the data. frame class. However, a probabilist is familiar if the sample space is neatly written out as Ω = {H, T} or Ω = {HH, HT, TH, TT}. Use the
For small χ values and χ around 0, write a program to obtain the expectation of a normal RV, which incorporates the expectation of an RV for an arbitrary RV, as given in Equation 5.16.Data from in
Let Xn follow a Poisson distribution Pois(χ∕n). Verify if the Feller condition holds for this sequence. If the Feller condition is satisfied, verify for the Liapounov’s condition.
If the rate of exponential distribution for Xn is nχ, verify the Lindeberg and Feller condition for the sequence under consideration.
Using the dpois function, find the minimum value of χ, such that P(X > 10) ≥ 0.2.
For different values of χ, obtain a plot of the curved normal family.
Italicize the y-axis label in the expression part in Example 7.3.1.Data from in Example 7.3.1Suppose X ∼ b(100, p), and we have four statistics/estimators, see Table 7.2, for estimation of p. To
For the galton dataset from UsingR package, what will be the conclusion of the MP test that the height of the child is H ∶ χ = 68 against K ∶ χ = 75, given that variance is known to be 1.7873.
If the variance is unknown in the previous example, carry out the likelihood-ratio test, see LRNormalMean_UV, and draw the conclusion at the χ = 0.05 level of significance.
Compare the Behrens-Fisher test results with the Mann-Whitney nonparametric test for the Youden-Beale data.
Using self-defined functions for DFFITS and DFBETAS, as given in Equations 12.66 and 12.65, say my_dffits and my_dfbetas, compute the values for an ailm fitted object and compare the results with the
The VIF given in Equation 12.67 for a covariate requires computation of R2, as obtained in the regression model when the covariate is an output and other covariates are input variables for it. Thus,
Identify if the multicollinearity problems exist for the fitted ailm object using (i) VIF method, and (ii) eigen system analysis.
Carry out the diagnostic tests for the olson_crd fitted model in Example 13.3.4. Repeat a similar exercise for the ANOVA model fitted in Example 13.3.2.Data from in Example 13.3.4We need to determine
The function granova.2w may be applied on the girdernew dataset with a slight modification. Create a new data frame girdernew2 <- girdernew[,c(3,1,2)]. Note that an additional R package rgl will
Perform the diagnostic tests on the BIBD model in Example 13.4.4.In Example 13.4.4For a chemical reaction experiment, the blocks arise due to the Batch number, Catalyst of different types from the
The Mahalanobis distance D2 given in Equation 14.7 is easily obtained in R using the mahalanobis function. Using this function, obtain the distance of the observations from the entire dataset for the
Using the HotellingsT2 function from the ICSNP package, test whether average sepal and petal length and width for setosa species equals [5.936 2.770 4.260 1.326] in the iris dataset.
Using the HotellingsT2 function from the ICSNP package, test whether average sepal and petal length and width for setosa species equals that of versicolor in the iris dataset.
Test whether the Sepal and Petal characteristics are independent of each other in the iris dataset.
Find the PCs for the stack loss dataset, which explain 85% of the variation in the original dataset.
For the US crime data of Example 13.4.2, carry out the PCA for the covariates and then perform the regression analysis on the PC scores. Investigate if the multicollinearity problem persists in the
Check out for the example of the factanal function. Are factors present in the iris dataset? Develop the complete analysis for the problem.
Perform the χ2 tests for the datasets in the first problem here.
Obtain the 90% confidence intervals for the logistic regression model chdglm, as discussed in Example 17.5.1. Also, carry out the deviance test to find if the overall fitted model chdglm is a
The likelihood function for the logistic regression model is given in Equation 17.8. It may be tempting to write a function, say lik_Logistic, which is proportional to the likelihood function.
Write a program to obtain the minimum between two corresponding elements of two vectors. As an example, for the two vectors A=(1,2,3,4) and B=(4,3,2,1), your program should return the minimum as
Using the options, fix the number of digits of the output during a session to four digits.
Find the details about complex numbers and perform the basic arithmetic related to complex numbers. What do you expect when you perform mean, median, and sd on an array of complex numbers? Check the
For a gamma integral, it is well known that Γ(n) = (n − 1)!, where n is an integer. Verify the same for your choice of integers. Note that you are required to use gamma for the left-hand side and
For a number x, can you always say that round(floor(x)) == floor (ro und(x)). Also, test which of these relationships hold true: floor (ceil ing(x)) == ceiling(floor(x)), floor(sign(x)) ==
By using the is.na function to substitute the missing observations of a vector, you may select a numeric vector of your choice with missing values, with 0. Attempt to replace the missing values of a
Consider the factor vector explevels <- gl(3, 2), and now change the third and fourth elements to 1 with explevels[3:4]<-1. Now, 2 is an extra factor level which is not present as a factor for
For a numeric vector, do you expect min(x) == -max (-x) ?
The Stirling function stirling is given as an approximation of n!. The R function factorial is also an approximation for the factorial operation. This means that prod(1:n) will not always be the same
In Subsection 2.4.1, we computed the norm of a vector x as sqrt (sum(x ̂ 2)). With some extra effort, it is indeed possible to obtain the same using the R function norm. Explore the options type and
Create the matrix A <- matrix(1:16,nrow=4) in R. Using the functions upper. tri, lower. tri, and diag, obtain the identity matrix.
For the matrix A<- matrix(c(1:12),nrow=2), find the determinant using the det function.
Check whether ginv and solve result in the same inverse matrix for a non-singular square matrix? In the case of a singular matrix, say matrix(rep(1,4),nrow=2), what will be the generalized inverse?
For the data. frame some in Example 3.2.2, what will be your expectation of the R code summary(some)? Validate the expectation by running the code too.Data from in Example 3.2.2In this example, we
By considering the dataset rootstock imported in Section 3.3, export the data back to the working directory using the write. dta function from the foreign package.Data from in Section 3.3Datasets may
Run edit(newsome1) as required in Section 3.4, and comment on how this function is different from the View function.Data from in Section 3.4R objects are of varying nature and we may be interested in
For any directory in your computer, use the function list. files to obtain the contents, inclusive of files and maybe other directories. Recollect that the default list. files () function returns the
The attach function, when applied on a data. frame object, loads the variables in the R session. How do you undo this operation? If the attach function is repeated more than once, what will be the
Suppose that the option header=FALSE is an error when an object is imported. Write appropriate codes which bring up the right variable names and deletes the wrong observations too. For example,
Using the aggregate function, as in Example 3.5.1, obtain the frequency instead of sum. Also, extend the list variables in the example to include both GPP and Grade, and hence obtain the sum of Sat
Using the ifelse conditional function, create a new as. Date type of function, which can read date objects available in a vector in two different forms.
Find the time difference between two time objects in units of hours, days, etc.
Let x be a numeric vector. Create a new function, say depth, which will have a serial number as an argument, between 1:length(x), and its output should return the depth of the datum.
The part B of Figure 4.4, see Example 4.5, clearly shows the presence of outliers for the number of dead insects for insecticides C and D. Identify the outlying data points. Remove the outlying
The number of intervals for the five histograms in Figure 4.5 can be seen as 11, 6, 11, 6, and 10. How do you obtain these numbers through R?Data from in Figure 4.5 5 5 0 -3 Histogram of Sample
Create a function which generates a histogram with the intervals according to the percentiles of the data vector.
Explore the different choices of breaks given in Formulas 4.5 – 4.7 for the different histogram examples.
Using the R function pareto.chart from the qcc package, obtain the Pareto chart for the causes and frequencies, as in Example 4.10, and compare the results with Figure 4.9.Data from in Figure
Create an R function, say trimean, for computing trimean, as given in Equation 4.8. Apply the new function for datasets of your choices considered in the chapter.Data from in Equation 4.8 TM Q₁
Fit resistant line models for the six pairs of data discussed in Example 4.17. Validate the correlations as implied by the scatter plots in Figure 4.12.Data from in Figure 4.12
For the datasets available in the files rocket_propellant.csv and toluca_company.dat, build the resistant line models. In the former file, the input variable is Age_of_Propellant, while in the latter
Consider the three sets from Ω = LETTERS: A = {“U”, “X”, “M”, “J”, “B”, “D”}, B = {“N”, “J”, “H”, “C”, “G”, “X”}, and C = {“H”, “V”, “N”,
The sample space of a die rolling becomes very large, depending on number of times we roll the die, and also on the number of sides of the die. Write a R program using the rolldie function from the
Find out more details about the Roulette game and make a preliminary finding about it in the function roulette.
Run the codes names(table(rowSums(S_Die))) and table (rowSums(S_Die)) from Example 5.2.7 and verify that you have completely understood the examples code. Now, roll four die and answer the
For the thirteenth of a month problem, start with an arbitrary year, say 1857, and then run the program up to year 2256. Do you expect that the 13th will more likely be a Friday than any other day?
In Example 5.3.3, the digits are drawn to solve a replacement problem. Obtain the probability of obtaining at least two even numbers in a draw of five using the leading digits of e.Data from in
What is the number of people whose birthday you need to ask so that the probability of finding a birthday mate is at least half? Write a brief R program to obtain the size as the probability varies
Construct a program which can conclude if the collection of sets over a finite probability space is a field.
Extend the program in the previous problem to verify if probabilities defined over an arbitrary collection of finite sets satisfies the requirement of being a probability measure.
Explore if the addrv function from the prob package can be used to handle more than two variables.
Extend the R function Expectation_NNRV_Unif for computing the expectation of a uniform RV over the interval [−a, a], a ∈ R.
Evaluate the R program of de Moivre-Laplace CLT for different values of p.
Using the normal approximation, CLT result, for the triangular distribution for various values of a, b, and c, create an R program for evaluating P(−c∕2 < X̄ < c∕2).
For the uniform and beta distribution, write R programs to obtain mean and variance using Equation 5.16.Data from in Equation 5.16 EX = EX+ - EX-,
For a fixed p value in a negative binomial RV, see Equation 6.20, obtain a plot of the mean and variance for different r values and comment.Data from in Equation 6.20 (x+r-¹) p'(1 − p)*, x = 0, 1,
Using the choose function, create a new function for the pmf of hypergeometric distribution.
Using the integrate and dt (for density of t-distribution), verify the mean and variance of the t RV.
Reconstruct Part A of Figure 6.9 using the curve function instead of the plot function. What are the apparent advantages of using the curve function, if any?Data from in Figure 6.9
Suppose X follows a negative binomial distribution with parameters as defined in Equation 6.20. Assume that for obtaining r = 6 failures, x is noted as 10. Obtain the likelihood function plot and
In a directory on a particular folder of a hard disk drive, there are N = 50 files. Suppose that in a random selection of n = 12 files, 9 are observed to be e-books. Under the assumption of a
The t-test used on the galton dataset is t.test(galton$child,mu= mean(galton$parent)). However, there is a “pairing” between the height of the child and the parent. Is the test
For the swiss $Bottforg data vector, obtain the empirical cdf and estimate the statistical functionals of skewness and kurtosis.
For the parent height in the galton set, obtain the histogram smoothing and the kernel smoothing estimates and draw the right inference.
The nerve dataset, as discussed in Section 8.2, deals with the cumulative distribution function. Estimate the density function of the nerve data using histogram smoothing, and uniform, Epanechnikov,
For a beta prior Be(a, b) on the probability of success in a Bernoulli trial, find the probability of sunrise. For a large n, obtain the plot of the probability for various a and b values.
Under a symmetric Dirichlet prior, with symmetric parameter c, the probability of a birthday match, see Diaconis and Holmes (2002) is given by Write an R program to compute the probability of a
The TPM of a gamblers walk consists of infinite states. Restricting the matrix over [−n, n] states, that is considering only the corresponding rows and columns and not the restricted gamblers walk,
Using the msteptpm function, obtain P10 for testtpm, testtpm2, and testtpm3 TPM’s.
Using the p.as.plot function from Convergence Concepts, study the convergence in probability and almost sure convergence limit theorems.
Elaborate on the details of the R program in Example 11.6.1.Data from in Example 11.6.1The prior probability prior_weights is extended over a prior grid as required in this approach. A very
Simulate 1000 observations from the standard normal distribution using AR_Normal function and then obtain the histogram with the option freq=FALSE (why?). Add the normal curve, try curve with
Using the accept-reject algorithm, generate observations from the binomial distribution as target distribution and the uniform distribution as proposal distribution. Reverse the roles and carry out

Showing 1 - 100 of 120