BUSN 302: Data Heads Part 1 & 2

Choosing a specific technology to solve a problem, instead of finding the correct one based on the problem.

How many questions should a Data Head ask?

T or F: Arbitrarily picking and choosing which data points are outliers are the best way for any dataset.

Zip codes, Yes/No, True/False, and party affiliations are an example of what kind of categorical data?

T or F:  Underestimating variation causes people to overestimate their confidence in small data.

The number of cars you have is an example of what kind of numerical data? (Ex: 0, 1, 2, 3 cars)

Write the Probability of rolling a 1 on a six-sided die (D)

The weather is an example of what kind of numerical data? (Ex: 65 degrees F, 66  degrees F)

Single parameter of a population, such as its mean

According to Chapter 4, what is not a question for arguing with data?

Gives a range of plausible values for where the true percentage may lie and considered a inferential statistic.

Polling of information to similar crowds but having a percentage of the answers change is:

T or F: Utilizing a histogram can help depict whether an object is correlated or not

Asking a politicians approval rating from their political party is an example of:

Probability is measured by which two numbers? "___ to ___"

T or F: The chance of any two events happening together cannot be greater than either event happening by itself.

Correlation is a measurement of what kind of trend(s)?

T or F: You can start with the technology to be used when solving data problems.

T or F: Exploratory Data Analysis happens only once in a project.

Define: Sample results that is collected on some population that have a lower or higher probability than others.

T or F: The higher the power of a test, the lower rate of probability of a false negative. 

+/-% in the range of confidence

T or F: Experimental data is always the most cost effective and ethical way to collect data.

Data representing the underemployed is not considered in the unemployment rate is an example of:

P(A | B) x P(B) = P(B | A) x P(A) is referred to as:

Which is not an example of unstructured data?

The following image is a depiction of what kind of graph?

T or F: The larger the dataset, the more reliable it is

Definition:  H₀ - The Status Quo

The following image is a depiction of what kind of graph?

T or F: In probability, the following is always true: P(A | B) = P(B | A)

What data event was mentioned in the introduction where analysts were wrong?

The following image is a depiction of what kind of graph?

"4/5 dentists prefer this toothpaste" means what % of dentists prefer this toothpaste?

What is encoded information?

Most common number in the dataset

Conditional Probability, using the term "given" is symbolized how?

What is the intersection of observations and features?

Which is not a question you should ask to challenge the statistics?

The preferred type of data collection should always be:

Two events happening at the same time which are independent, using the term "and", is symbolized how?

T or F: With independent events, your chances for an event do not increase or decrease based on past performance.

The following image is a depiction of what kind of graph?

T or F: You need data to make informed decisions

Which is not a question a Data Head should ask?

T or F: If you increase the false positives in a probability, you can decrease the amount of false negatives.

What are the two types of statistical variations? Measurement Variation and ______?

If events are independent, you ______ their probabilities.

To reject the null hypothesis and say the result is statistically significant, which must be true?

According to the book, What is NOT an example of why a Data Head would question a statistical statement?

What is the not a reason why data projects fail?

According to the text, why do data problems occur? 

What is the process of iteration, discovery, and data scrutiny?

T or F: Observational data is collected under conditions with treatment groups and time-tested to maintain integrity 

Sum of all numbers divided by count of all numbers

The Pearson correlation coefficient ranges from what number to what number? "__ to __"

T or F: Datapoints that differ significantly from other datapoints are called variations.

Statistics is broken down into two categories: Descriptive Statistics & ____________ Statistics

You grab marbles and use that information to tell you what else is in the bag. You have just used:

T or F: Finding correlated values can help reduce the redundancies in your data.

What did you have to make a prediction on in the introduction of the book?

You open the bag and see all the marbles then blindly grab a handful and guess what's in your hand. You have just used:

Surveys of 1-10 given to customers, but any < 8 was considered negative. The graph is what thinking statistically term?

Definition: Hₐ - New knowledge

Choosing the specific display method, instead of finding the correct one based on the problem.

Midpoint of data range in sorted order

Survey Ratings (1-10) is an example of what kind of categorical data?

Given the below graph, what is the probability of your computer having a virus, given a positive test?  [ P(V|+) ]

What was the root cause of the Challenger explosion?