Comms 351 Study Guide

In a dataset containing information on patients at a hospital, which of the following would be best represented as an "observation" or 'row' in a standard row/column dataset?

• Patient ID

• Age

• Gender

• Weight

In a dataset containing information on patients at a hospital, which of the following would be best represented as an "observation" or 'row' in a standard row/column dataset?

• Patient ID

• Age

• Gender

• Weight

Patient ID

Which of the following platforms would be the best platform to use to collect data about earned media coverage (i.e. news articles, blogs, etc. about a person or organization)? 

• Google Analytics

• Meltwater

• Tableau

• Python

Meltwater

Which of the following is the most clear example of continuous numeric data?

• Shoe size

• Speed

• Family size

• Month

Speed

Which of the following provides the best example of nominal categorical data?

• Age groups

• Height

• Number of members in a family

• Ethnicity

• A Likert Scale

Ethnicity

Is the following statement True or False: Discrete Numeric Data and Ordinal Categorical Data are terms that describe the same thing, because they both describe a limited number of items that have a logical ordering to them.

False

Which of the following measures of Central Tendency in a dataset is the same as the numerical average?

• Mean

• Median

• Mode

• Kurtosis

Mean

Which of the following measures of Central Tendency is most easily affected by outliers?

• Median

• Mean

• Mode

• Standard deviation

Mean

A right-skewed data distribution representing the age of college students will have outliers that are:

• Very old compared to the average college student’s age

• Very young compared to the average college student’s age

• Clustered around the average age of college students

Very old compared to the average college student’s age

In a data distribution representing the height of male BYU students, it was found that the average height of a student was five feet eleven inches. The number of inches by which the typical male BYU student is either taller or shorter than this average is best by:

• A normal distribution

• Kurtosis

• Skew

• Standard Deviation

Standard Deviation

A data distribution with a skew of .7 would be considered:

• Right skewed

• Left skewed

• Normal

• Leptokurtic

Normal

If one was rolling a pair of six sided dice, the probability of one die landing on ‘1’ and the other die landing on ‘2’ may be calculated

• The multiplication rule

• The addition rule

• Bayes conditional probability formula

• Factorial probability

The multiplication rule

The relationship between two categorical variables may be best determined using:

• A t-test

• Neural Networks

• Linear Regression

• A Chi-Square test

A Chi-Square test

The relationship between two continuous numerical variables would be best analyzed using:

• Analysis of Variance

• Logistic Regression

• Linear Regression

• Chi Square Test for Homogeneity

Linear regression

True or False: All KPIs are metrics, but not all metric are KPIs

True

Analysis of Variance (ANOVA) accounts for not just averages/means, but also the distributions of the data from which the averages are derived

• True

• False

True

Your organization publishes a newsletter that provides updates for key audience members, and is considered a premier channel for engaging with important stakeholders. You set a goal to get 500 people to subscribe to your newsletter. Which of the following elements is missing in order for this to be considered a good KPI (choose the best answer):

• Simple

• Measurable

• Aligned

• Timely

Timely

Which of the following types of chart best visualizes a relationship between two continuous variables?

• Histogram

• Scatterplot

• Bar Chart

• Pie Chart

Scatterplot

Which of the following charts is the best choice for showing the distribution of a single numerical variable?

• Bar chart

• Scatterplot

• Histogram

• Radar Chart

Histogram

Which of the following charts is the best choice for showing the difference in the average weight of two different subspecies of baboon?

• Histogram

• Scatterplot

• Pie chart

• Column chart

Column chart

Which of the following charts allows you to visualize the effect of multiple variables on an observation?

• Histogram

• Heat map

• Radar Chart

• Boxplot

Radar chart

For a scatterplot that displays the potential relationship between two variables, that relationship - if it exists - will nearly always be visible to the naked eye

• True

• False

True

Which of the following statistical techniques would be used to compare the average test scores of students in three different high schools to determine if there is a statistically significant difference between them?

• Linear Regression

• T-test

• Analysis of Variance (ANOVA)

• Chi-Square

Analysis of Variance (ANOVA)

Which of the following tests would you use to compare the means of two samples when each observation in one sample can be paired with an observation in the other sample?

• Paired Sample T-test

• One-way ANOVA

• Linear regression

• Chi Square

Paired Sample T-test

Which of the following is not an assumption of ANOVA:

• The dependent (response) variable is approximately normally distributed for each group

• The expected count of the dependent variable must be at least 5

• The observations in each group (category) are independent of each other and the observations within groups were obtained by a random sample

• The variances for each group should be roughly equal

The expected count of the dependent variable must be at least 5

In our experiment based on ANOVA, we set the significance level at 5 percent. The statistical test shows an F statistic of 5.639 and p-value of .006. Which of the following should be our course of action:

• Accept the alternative hypothesis because the F statistic is greater than the F critical value

• Reject the alternative hypothesis because the p-value is too small.

• Fail to reject the null hypothesis because the p-value is lower than the significance level.

• Reject the null hypothesis because the p-value is lower than our significance level.

Reject the null hypothesis because the p-value is lower than our significance level.

You wish to determine whether a preference exists among BYU students between hot dogs and hamburgers. You survey a random sample of 100 BYU students and ask them to select whether they prefer hot dogs, hamburgers, or neither. To analyze the survey results, which of the following statistical tests would you leverage?

• One Way ANOVA

• Chi Square Test of Association

• Logistic regression

• Chi Square Goodness of Fit

Chi Square Goodness of Fit

You want to test whether income is influenced by age, shoe size, and right-handed/left-handedness. Which of the following statistical techniques makes the most sense?

• Multiple Linear Regression

• Logistic Regression

• MANOVA

• Linear Regression

Multiple Linear Regression

Which of the following is a predictive machine learning approach?

• Chi Square Test for Homogeneity

• T-test

• Simple Linear Regression

• Normalization

Simple Linear Regression