EC285 iClicker Final Exam Questions

Who are these public and private organizations?

A. Private and publicly traded (i.e., on the stock exchange) companies

B. Government and Crown corporations

C. Non-Government Organizations

D. All of the above

E. None of the above

D. All of the above

What is Data?

A. 'What is data?' is incorrect

B. Data can be numbers, names, or labels.

C. The singular of data is datum

D. All of the above

E. None of the above

D. All of the above

What is an experimental unit?

A. An individual who answers a survey

B. A person on whom we experiment

C. A company, website, or another inanimate subject

D. All of the above

E. None of the above

C. A company, website, or another inanimate subject

What is a respondent?

A. An individual who answers a survey

B. A person on whom we experiment

C. A company, website, or another inanimate subject

D. All of the above

E. None of the above

A. An individual who answers a survey

What is a participant?

A. An individual who answers a survey

B. A person on whom we experiment

C. A company, website, or another inanimate subject

D. All of the above

E. None of the above

B. A person on whom we experiment

Categorical Variables

A. Are also called quantitative variables

B. Are also called qualitative variables

C. Are also called dummy variables

D. All of the above

E. None of the above

B. Are also called qualitative variables

Quantitative Variables

A. Are the same as qualitative variables

B. Can be a number such as an area code

C. Can only have 2 possible values; such as yes and no

D. All of the above

E. None of the above

E. None of the above

Identifier Variables

A. Do not have units

B. Are useful in combining data from different sources; to avoid duplication

C. Are not variables to be analyzed;

D. All of the above

E. None of the above

D. All of the above

Ordinal Variables

A. Are random numbers

B. Do not have intrinsic ordering

C. Are ordered variables

D. All of the above

E. None of the above

C. Are ordered variables

Panel Data

A. Have both cross-section and time dimensions

B. Are another word for cross-section data

C. Are data that can only have whole numbers

D. All of the above

E. None of the above

A. Have both cross-section and time dimensions

What does 'biased' mean?

a. The tendency to estimate the value of a parameter to be zero

b. The tendency to estimate the value of a parameter far away from the actual

c. The tendency to underestimate or overestimate the value of a parameter

d. All of the above

e. None of the above

c. The tendency to underestimate or overestimate the value of a parameter

What does 'randomize' mean?

a. So that it happens with a fixed probability

b. So that it happens or is chosen by chance

c. So that it happens with probability 1

d. All of the above

e. None of the above

b. So that it happens or is chosen by chance

Canada

a. Does not have a census

b. Does have a census but it is not useful

c. Does have a census that is conducted every year

d. All of the above

e. None of the above

e. None of the above

Sample statistics and population parameters

a. Will be relatively close in a representative sample

b. Are the same thing

c. Describe the sample mean and the population mean

d. All of the above

e. None of the above

a. Will be relatively close in a representative sample

Samples drawn at random

a. Lead to the same statistics

b. Generally differ

c. Lead to the same mean but different standard deviation

d. All of the above

e. None of the above

b. Generally differ

Which is not a random sample design

a. Clustered sampling

b. Stratified sampling

c. Systematic sampling

d. All of the above

e. None of the above

e. None of the above

In stratified sampling

a. The population is divided into clusters

b. Members are selected systematically

c. Members are selected at random from stratums

d. All of the above

e. None of the above

c. Members are selected at random from stratums

In cluster sampling

a. The population is divided into clusters

b. In a cluster, all members look pretty much alike

c. Members are selected at random from each cluster

d. All of the above

e. None of the above

d. All of the above

In systematic sampling

a. The systematic selection starts with a randomly selected individual

b. In the system, all members pretty much look alike

c. Systematic sampling only works with homogenous members

d. All of the above

e. None of the above

a. The systematic selection starts with a randomly selected individual

Accuracy and bias are

a. The same thing

b. Both relevant but unbiasedness is more important

c. Not relevant, only unbiasedness is

d. All of the above

e. None of the above

e. None of the above

A frequency table

a. Organizes only quantitative data

b. Organizes data in time frequency

c. Organizes data by recording counts and category names

d. All of the above

e. None of the above

c. Organizes data by recording counts and category names

A relative frequency table

a. Displays the proportions, not percentages

b. Display only percentages, not proportions

c. Can never include '0' percent

d. All of the above

e. None of the above

e. None of the above

What is the area principle?

a. Data should be displayed as squares

b. The area of a bar should correspond to the magnitude of its value

c. An area can never be '0'

d. All of the above

e. None of the above

b. The area of a bar should correspond to the magnitude of its value

Pie charts

a. Are more useful than bar charts

b. Does not have overlapping categories

c. May not add 100%

d. All of the above

e. None of the above

b. Does not have overlapping categories

Frequencies

a. You cannot combine frequencies of two categorical variables

b. The aggregate frequency of a categorical variable is 100%

c. Combining the frequency of two categorical variables gives 100%

d. All of the above

e. None of the above

e. None of the above

A contingency table

a. Shows how the values of one variable is contingent on the value of another

b. Shows the likelihood of an event

c. Shows the standard deviation

d. All of the above

e. None of the above

Shows how the values of one variable is contingent on the value of another

The marginal distribution for a variable

a. Only exists for bivariate data

b. In a contingency table is the same as its frequency distribution

c. Are for variables with negligible probabilities

d. All of the above

e. None of the above

b. In a contingency table is the same as its frequency distribution

The totals in a contingency table

a. Are always expressed in percent

b. May be expressed in percent

c. Are never expressed in percent

d. All of the above

e. None of the above

b. May be expressed in percent

A conditional distribution

a. Gives the distribution of one variable for cases that satisfy a specific condition

b. Gives the distribution of two correlated variables

c. Applies only to categorical variables

d. All of the above

e. None of the above

a. Gives the distribution of one variable for cases that satisfy a specific condition

The Simpson's Paradox

a. Refers to the phenomenon of negative probabilities

b. Results from inappropriately combining percentages of different groups

c. Refers to the fact that nobody on the Simpson's show is aging

d. All of the above

e. None of the above

b. Results from inappropriately combining percentages of different groups

For distribution, describe

a. Its shape

b. Its center

c. Its spread

d. All of the above

e. None of the above

d. All of the above

A stem-and-leaf display

a. Uses the first digit of the number as the bin

b. Uses the next digit of the number for the bar

c. Gives a similar shape as the histogram

d. All of the above

e. None of the above

d. All of the above

The peaks in a histogram are called

a. Modes

b. Apex

c. Zeniths

d. All of the above

e. None of the above

A. Modes

A histogram can

a. Have no peaks

b. Be unimodal

c. Be multimodal

d. All of the above

e. None of the above

d. All of the above

A histogram without a peak, means that the data

a. Have a unimodal distribution

b. Are uniformly distributed

c. Have no distribution

d. All of the above

e. None of the above

b. Are uniformly distributed

A distribution is symmetric

a. If it is platykurtic

b. If both halves besides the center are roughly mirror images

c. If there is no leptokurtosis

d. All of the above

e. None of the above

b. If both halves besides the center are roughly mirror images

Outliers

a. Affect statistical methods

b. Can be errors in the data

c. Can be extraordinary events

d. All of the above

e. None of the above

d. All of the above

How do you calculate the mean of a sample?

check textbook for answer

How do you calculate the variance of a sample?

check textbook for answer

How do you calculate the z score?

Check the textbook for answer

A scatterplot

a. Plots one categorical variable against another

b. Plots one quantitative variable against time

c. Plots one quantitative variable against another

d. All of the above

e. None of the above

c. Plots one quantitative variable against another

In a scatterplot, look for

a. Direction and symmetry

b. Direction and form

c. Direction and mode

d. All of the above

e. None of the above

b. Direction and form

In a scatterplot, the strength of the relationship is given

a. By the direction of the clusters

b. By the tightness of the clusters along a stream

c. By the spread of the clusters

d. All of the above

e. None of the above

b. By the tightness of the clusters along a stream

An explanatory variable is

a. A predictor variable

b. An exogenous variable

c. An independent variable

d. All of the above

e. None of the above

d. All of the above

A scatterplot is

a. A bivariate analysis

b. A multivariate analysis

c. A univariate analysis

d. All of the above

e. None of the above

a. A bivariate analysis

Correlation

a. Measures the strength of the linear association between two variables

b. Measures the strength of any association between two variables

c. Measures the slope of a line through a scatterplot

d. All of the above

e. None of the above

a. Measures the strength of the linear association between two variables

Correlation applies

a. Only to categorical variables

b. Only to quantitative variables

c. To both categorical and quantitative variables

d. All of the above

e. None of the above

b. Only to quantitative variables

Correlation

a. Is not affected by changes in the scale of either variable

b. Its sign gives the direction of the association

c. Is sensitive to outliers

d. All of the above

e. None of the above

d. All of the above

A lurking variable

a. Simulataneously affects two variables

b. Is a lagged variable

c. Is a variable that cannot be observed (like the business cycle)

d. All of the above

e. None of the above

a. Simulataneously affects two variables

Correlation

a. Is between -1 and +1

b. Has no units

c. Treats both variables symmetrically

d. All of the above

e. None of the above

d. All of the above

The following is not a linear model

a. yi = ax_i^2 + b

b. ln(yi) = aln(xi) + b

c. yi = a1xi + a2zi + b

d. All of the above

e. None of the above

a. yi = ax_i^2 + b

What is the difference between yi and ŷ

a. There is no difference

b. yi is the raw observation and ŷ is the standardized observation

c. yi is the data and ŷ is the estimate

d. All of the above

e. None of the above

c. yi is the data and ŷ is the estimate

How many residuals are there?

a. 1

b. 2

c. n - 1

d. All of the above

e. None of the above

e. None of the above

What is the difference between a residual and an error?

a. There is no difference

b. The residual is from the estimated relationship

c. The residual is ŷi - x̂ and the error is yi - xi

d. All of the above

e. None of the above

b. The residual is from the estimated relationship

Is x ever x̂?

a. Yes, when x is an explanatory variable

b. No, x is the residual

c. No, because x is an exogous variable

d. All of the above

e. None of the above

c. No, because x is an exogenous variable

In the equation b0 + b1x

a. b0 is the slope

b. b1 is the slope

c. There is no slope

d. All of the above

e. None of the above

b. b1 is the slope

ȳ and x̄

a. Are sample means

b. Are population means

c. Can be either, population or sample means

d. All of the above

e. None of the above

a. Sample means

The Quantitative Data Condition means

a. All regressions are linear

b. Linear models work better for quantitative data

c. Linear models only make sense for quantitative data

d. All of the above

e. None of the above

c. Linear models only make sense for quantitative data

The Linearity Condition means

a. The variables must have a linear association

b. Only applies to 'two variables regressions'

c. Only the dependent but not the independent variable must be linear

d. All of the above

e. None of the above

a. The variables must have a linear association

The Outlier Condition means

a. Outliers can dramatically change a regression model

b. Outliers impact sample means and standard deviations but not regression estimations

c. One outliers will not impact regression results, but more than one will

d. All of the above

e. None of the above

a. Outliers can dramatically change a regression model

What is the sample space?

a. It is the number of observations

b. It refers to the number of observations compared to the population

c. It is the collection of all possible outcomes

d. All of the above

e. None of the above

c. It is the collection of all possible outcomes

The probabilitiy of an event

a. Is a random phenomenon that generates an outcome

b. Is its long run frequency

c. It is the collection of all possible outcomes

d. All of the above

e. None of the above

b. Is its long run frequency

Independence means

a. That the outcome of one trial does not influence or change the outcome of another

b. That events do not even out in the short run

c. That all possible outcomes have the same probability

d. All of the above

e. None of the above

a. That the outcome of one trial does not influence or change the outcome of another

Empiricial probability

a. Is based on matching competing theoretical predictions

b. Is based on repeatedly observing the event's outcome

c. Is based on the Law of Averages

d. All of the above

e. None of the above

b. Is based on repeatedly observing the event's outcome

The probablitiy of the set of all possible outcomes is

a. - infinity

b. + infinity

c. 0

d. All of the above

e. None of the above

e. None of the above

The difference between joint and conditional probablities

a. Is none (they are the same)

b. Is that conditional probablities depend on marginal probabilities

c. Is that conditional probabilities depend on all events

d. All of the above

e. None of the above

b. Is that conditional probabilities depend on marginal probabilities

The general multiplication rule

a. Requires independence

b. Requires dependence

c. Does not require independence

d. All of the above

e. None of the above

c. Does not require independence

The multiplication rule applies

a. Only to disjoint events

b. Only to independent events

c. Only to linear dependent events

d. All of the above

e. None of the above

b. Only to independent events

The addition rule applies

a. Only to disjoint events

b. Only to possible events

c. Only to independent events

d. All of the above

e. None of the above

a. Only to disjoint events

Disjoint events

a. Can be but are not necessarily independent

b. Are always independent

c. Cannot be independent

d. All of the above

e. None of the above

c. Cannot be independent

What is a random variable?

a. A variable whose value is based solely on a normal distribution

b. A variable whose value is based solely on a uniform distribution

c. A variable whose value is based solely on a binomial distribution

d. All of the above

e. None of the above

e. None of the above

Random variables

a. Are discrete variables

b. Are continous variables

c. Can be discrete or continuous variables

d. All of the above

e. None of the above

c. Can be discrete or continuous variables

If we can list all the possible outcomes, the variable is called

a. An exponential random variable

b. A continuous random variable

c. A discrete random variable

d. All of the above

e. None of the above

c. A discrete random variable

In E(X) = ∑x x P(x)

a. P(x) is short for P(X = x)

b. x is an individual outcome

c. X signifies all possible outcomes

d. All of the above

e. None of the above

d. All of the above

Why is Var(X ± c) = Var(X) correct

a. It is not correct, but Var(X ± c) = Var(X) ± C

b. Because, Var(constant) = 0

c. Because, Var(constant) = 1

d. All of the above

e. None of the above

b. Because, Var(constant) = 0

Which is correct?

a. Var(aX) = a^2Var(X)

b. Var(aX) = a ± Var(X)

c. Var(aX) = Var(X)

d. All of the above

e. None of the above

a. Var(aX) = a^2Var(X)

Var(X ± Y) = Var(X) + Var(Y)

a. Applies only quantitative variables

b. Applies to all variables

c. Applies only to independent variables

d. All of the above

e. None of the above

c. Applies only to independent variables

The following is NOT a characteristic of the Bernoulli Trial

a. The probability of success, denoted p, is the same for each trial. The probability of failure is q = 1 - p

b. The trials are independent

c. There are only two possible outcomes (success and failure) for each trial

d. All of the above

e. None of the above

e. None of the above

The Binomial Distribution

a. Predicts the number of successes in a series of Bernoulli trials

b. Predicts the number of successes in a Geometric Distribution

c. Predicts the number of successes in a Normal Distribution

d. All of the above

e. None of the above

a. Predicts the number of successes in a series of Bernoulli trials

If the variable can take on any value in an interval, it is called

a. A normal random variables

b. A discreet random variable

c. A continuous random variable

d. All of the above

e. None of the above

c. A continuous random variable

True proportions

a. Are those of the underlying population

b. Are generally not observed

c. We can learn more about them through computer simulation

d. All of the above

e. None of the above

d. All of the above

The sampling distribution of proportions

a. Is the distribution of proportions over many independent samples from one population

b. May but does not have to relate to samples from one population

c. Is the same distribution as the distribution of the population

d. All of the above

e. None of the above

a. Is the distribution of proportions over many independent samples from one population

The standard deviation of the sampling distribution is

Check notebook for answer

The sampling error

a. Is the errors in the statistics due to non-random sampling

b. Is the difference between stratified and clustered sampling

c. Is the variability in the statistics from different samples of the same population

d. All of the above

e. None of the above

c. Is the variability in the statistics from different samples of the same population

The distribution for the sample proportions

a. Is usually the uniform distribution

b. Is usually the geometric distribution

c. Is usually the exponential distribution

d. All of the above

e. None of the above

e. None of the above

The 10% condition states

a. The sample size must be no larger than 10% of the population

b. At least 10% of the sample must be drawn at random

c. At least 10% of the sample must be successes or failures

d. All of the above

e. None of the above

a. The sample size must be no larger than 10% of the population

The success/failure condition states

a. That p must be success and q must be failure

b. That np and nq (n sample size, p success and q failure) are expected to be at least 10

c. That q = 1 - p

d. All of the above

e. None of the above

b. That np and nq (n sample size, p success and q failure) are expected to be at least 10

The Central Limit Theorem

a. States that the distribution of any mean becomes a normal distribution if the sample size is large

b. Is true if the underlying distribution is not normally distributed

c. Requires a larger sample size if the underlying population is skewed

d. All of the above

e. None of the above

a. States that the distribution of any mean becomes a normal distribution if the sample size is large

The random sample drawn from any population with mean = μ and variance = σ^2 the sampling distribution of ȳ is

a. ȳ ~ N(0, σ)

b. ȳ ~ N(μ, σ^2)

c. ȳ ~ N(μ, σ^2/n)

d. All of the above

e. None of the above

c. ȳ ~ N(μ, σ^2/n)

What is the standard error?

a. The sample error

b. The standard

c. The estimate of the standard deviation of p̂

d. All of the above

e. None of the above

c. The estimate of the standard deviation of p̂

What is the difference between SD(p̂) and SE(p̂)?

a. There is no difference

b. SD(p̂) is divided by n and SE(p̂) is divided by n -1

c. SE(p̂) is in terms of p̂ rather than p

d. All of the above

e. None of the above

c. SE(p̂) is in terms of p̂ rather than p

Can we be certain that p is within p̂ ± 2 x SE(p̂)?

a. Yes, because of the CLT

b. No, we can only be 95% certain

c. SE(p̂) is in terms of p̂ rather than p

d. All of the above

e. None of the above

b. No, we can only be 95% certain

p̂ is modeled as p̂ ~ N(p̂, pq/n)

a. If p̂ is from a sample

b. If the sample size is large enough

c. The sampled values are independent

d. All of the above

e. None of the above

d. All of the above

The margin of error is

ME = 2SE(p̂)

Where does the interval 40.4% and 43.6% come from?

a. It is from p̂ ± 1 x SE(p̂)

b. It is from p̂ ± 2 x SE(p̂)

c. It is from p̂ ± 3 x SE(p̂)

d. All of the above

e. None of the above

b. It is from p̂ ± 2 x SE(p̂)

How can we be certain that p is within the confidence interval?

a. If the confidence interval is between 0% and 100%

b. If the confidence interval is between -∞ and 0

c. If the confidence interval is zero

d. All of the above

e. None of the above

a. If the confidence interval is between 0% and 100%

The critical value for z* for the 95% confidence interval is

a. 1.810

b. 1.960

c. 2.132

d. All of the above

e. None of the above

b. 1.960

Data for 1000 trading day on the TSEs give the proportion of up days of 0.515

a. p = 0.515

b. p̂ = 0.515

c. q = 0.485

d. All of the above

e. None of the above

b. p̂ = 0.515

Where does the "=" belong in the hypothesis testing?

a. Always in the null hypothesis (H0)

b. Always in the alternative hypothesis (HA)

c. In either the null or in the alternative

d. All of the above

e. None of the above

a. Always in the null hypothesis (H0)

HA may also be called:

a. Ĥ0

b. H1

c. A0

d. All of the above

e. None of the above

b. H1