Predictive Business Analytics Exam 1
Over many trials, the 99% confidence interval will NOT include the true population parameter what percent of the time?
1% of the time
If y=b+mX and sCov(X,Y)=96, sVar(X)=12, sVar(Y)=21, sMean(X)=4, sMean(Y)=2; what is the y-intercept?
2 - (8*4) = -30
Suppose a sample of five analytics students' heights were: 62 inches, 72 inches, 58 inches, and 48 inches. What is the sample mean of the height of the students?
60 inches
If y=b+mX and sCov(X,Y)=96, sVar(X)=12, sVar(Y)=21, sMean(X)=4, sMean(Y)=2; what is the slope m?
96/12 = 8
A hypothesis in a predictive analytics setting is ____________.
A proposed idea based on limited evidence that leads to further investigation
When making a claim via inductive reasoning, which of the following is true concerning the degree of support?
An objective degree of support has a statistical foundation, generally constructed via deductive reasoning.
In making an active prediction it is advantageous for the relationship being predicted to be of what sort?
Causal
In grouping customers into separate types according to their spending, internet browsing, payment method, and age a firm is engaging in what sort of analysis?
Cluster analysis
Of the following, which is not an element in the scientific method?
Collect Market Data
A random variable that takes on a countably infinite number of values is known as what type of random variable?
Continuous
The process of forming conclusions, judgments, or inferences from facts or premises is:
reasoning
If you are trying to prove that A causes B, why does it make sense to have your null hypothesis be "A does not cause B"?
Data cannot confirm a hypothesis and it is easier to make strong inductive arguments when rejecting a hypothesis
Suppose a colleague claims that if the price elasticity of demand for the company's good is inelastic, then raising the price of the good will lead to higher sales. This is example of what type of reasoning?
Deductive reasoning
Suppose we are proving the statement that if two integers are even, then their sum is even. We execute the proof by first showing that if integer A and B are even, then they can be defined as A = 2k and B = 2m. We then note that their sum must be A + B = 2(k + m), which must be even. This is an example of what type of proof?
Direct proof
The effect of the treatment on the treated (ETT) is the average treatment effect for the group given the treatment is which of the following?
ETT + Selection Bias
When does the difference in the mean outcomes across the treated and untreated groups yield an unbiased estimate of the average treatment effect?
ETT = ATE
If you were building a hypothesis test to determine whether or not the price elasticity of demand for your product is -3.0, which of the following would be a natural null hypothesis?
Ho: mu = -3.0
Reasoning that goes from the specific (e.g., a data sample) to the general (e.g. the population) is known as:
Inductive reasoning
Taking samples of registered voters and asking them to disclose their preferences leading up to elections in order to assess the view of all registered voters on a particular candidate is an example of what sort of reasoning?
Inductive reasoning
The greatest impediment to using nonexperimental data to measure treatment effects is that __________.
Lack of random assignment of the treatment
If the residual for a point is -6, which of the following is true?
Negative value means prediction was too high (6 high)
Most data available to business are ______________ data.
Non experimental Data
A hypothesis to be tested using a data sample is known as _____.
Null Hypothesis
Suppose you want to answer the following question: "How will Sales of version 2.0 of our product change when we release version 3.0 of our product?" What type of data analysis is crucial toward answering this question?
Passive prediction
If the residual for a point is 4, which of the following is true?
Positive value means prediction was too low (4 low)
Which of the following are empirically testable conclusions?
Price markups should be lower in markets with more firms.
Which is not a primary component in deductive reasoning?
Sample of observations
Suppose you collect monthly sales figures for each store location in your company as well as the wages paid to employees for each store, and that you have a complete history for the last ten years for each store. Provided this information is in table format, the information you've gathered is an example of what type of data?
Structured data
For the same sample, the 90% confidence interval will have what relation to the 95% confidence interval?
The 95% confidence interval will be wider and more accurate
If you are intending to refute conclusions drawn via clear deductive reasoning, what must you disagree with?
The assumptions or the methods of proof
The treatment effect is ______________.
The change in the outcome resulting from variation in the treatment
If Profit is the Y variable, and Price is the X variable, and m is positive, which of the following is the correct interpretation of the equation?
The higher the prices, the larger the profit (Positive Correlation)
If Profit is the Y variable, and Price is the X variable, and m is negative, which of the following is the correct interpretation of the equation?
The higher the prices, the lower the profit (Negative correlation)
Which of the following are you assuming is true to calculate the p-value of a test statistic?
The null hypothesis is true (not certain)
Suppose there is a promotion using a sign to entice customers to purchase a candy bar. The promotion sign is in place 50% of the four-hour blocks over two weeks. The sign was up for all hours just before lunch and dinner times. The number of purchases when the sign was up was twice as high as times when the sign was not up. Why would the effect of treatment on the treated not equal the average treatment effect?
The sign was not up for all hours and therefore the treatment would not equal the average (Complete bullshit btw)
Suppose there are 100 subjects receiving a cholesterol drug and 100 who do not. The average level change was -48 for those given the drug, and -6 for the rest. What is a reason why this difference exists?
The treatment effect
In a broad sense, the role of a confidence interval for the population mean is meant to accurately portray what?
The uncertainty involved with observing a sample and not the entire population.
Which of the following statements best summarizes the use of business analytics?
The use of data analysis to aid in business decision making
The form of the potential outcome framework paradigm (the simple treatment framework) is which of the following?
Treatment effect = outcome Ti - outcome NTi
Why is it that inductive reasoning does not involve a proof?
We cannot prove the general from the specific
Which of the following is not an element of the scientific method?
Write down scientific method
Which question below is NOT an example of one plausibly used in the scientific method?
Write down scientific method
The scientific method includes of the following except which one?
Write down scientific method - 1. Ask a question, 2. Do research, 3. Formulate a hypothesis, 4. Conduct experiment, 5. Analysis data, 6. Communicate findings
At what X-value would the line defined by Y = 20 + 10X cross the x-axis?
X = -2
Suppose your model follows the standard form of the simple regression equation, Y = b + mX, with Y = 4 + (-2)X, at what X-value would the line defined by that equation cross the x-axis?
X = 2
Suppose that your equation is Y = -28 + 7X. What value of Y is where the line defined by that equation crosses the y-axis
Y = -28
In the standard form of the simple regression equation, Y = b + mX, at what point would the line defined by that equation cross the y-axis?
Y = b
Suppose you've assumed the following two data-generating processes: (1) Yi = f (Hi, Ji) and (2) Ji = g (Xi, Zi). What do these assumptions imply?
Z has an indirect causal effect on Y.
In the deductive reasoning behind the claim that "If firms sell homogenous products, then prices should fall to marginal costs" the role of "firms sell homogenous products" is:
an assumption
Reasoning that goes from the general to the specific or "top-down" logic is known as:
deductive reasoning
Measures of the central tendencies of variables such as the mean, median, and mode are examples of _________________.
descriptive statistics
Measures of the spread of variables such as the variance and range are examples of _______________
descriptive statistics
Quantitative measures meant to summarize and interpret properties of a dataset are instances of ________
descriptive statistics
As long as your sample is large enough, you don't have to worry about using the sample standard deviation in place of the unknown population standard deviation in constructing a confidence interval because ________.
for a large sample, the t-distribution is similar to the standard normal distribution
As the size of a random sample gets larger, what does the distribution of the sample mean begin to resemble?
normal distribution
The probability of attaining a test statistic at least as extreme as the one that was observed is known as the _____.
p-value
By showing your colleague that the conclusions of your analysis regarding the optimal pricing strategy for the firm would be the same under a variety of different assumptions regarding the price response of competitors is an example of:
robustness
The primary distinction between a subjective degree of support and an objective degree of support is the use of a(n):
statistical foundation
Degrees of support based off opinion and ultimately lacking any statistical foundation are often termed:
subjective degree of support
If Profit is the Y variable, and Price is the X variable, m is -10 and b is -20, at what point is the breakeven reached?
x = -2
If you have a model that follows the standard form of the simple regression equation, Y = b + mX, with Y = -16 + 4X, at what X-value would the line defined by that equation cross the x-axis?
x = 4
