Exam 10: Distributions and Associations

In a box-and-whiskers plot of an interval variable, what do the lower and upper lines of the box represent?

For the research study in question 1, create a report giving measures and charts (where applicable) for a bivariate and a three-way association between the variables in the study.

Design a research study on a topic of your choice. Make sure the outcome is a continuous variable, and that there are at least three independent variables with one of them being categorical. Construct a table with the variables in columns, and each observation or case for those variables, in rows. Have between seven to 10 rows in the table. Insert artificial values in each cell corresponding to the variable value for each row. This will be your data used in the study. If you have or find any public data on the topic of your choice, you could use it as your data source. You could also use survey data collected by the Center for Disease Control (CDC) on smoking habits among youth. You could access this data at HYPERLINK "https://www.cdc.gov/tobacco/data_statistics/surveys/nyts/index.htm" https://www.cdc.gov/tobacco/data_statistics/surveys/nyts/index.htm. Now, create a report showing central tendency, variability, and shape of any two of your variables in the study. Explain any calculations you make to arrive at your report results.

Statistical methods refer to techniques used to describe, organize, and, interpret data.

What is a bivariate association? Explain, with an example, the measure(s) used to show this type of an association.

The correlation coefficient between two variables was found to be 0.37. What is the coefficient of determination between the two variables? What does this measure represent?

Which of the following statements are true regarding the term "interquantile range"?

The shape of a distribution has a skewness value of -12.5. What can you say about the magnitude of the mean relative to the median of this distribution?

What are the plausible limits on values of the coefficient of determination measure? How are these different from limits of the correlation coefficient measure?

What are the plausible limits to the results from an ANOVA test?

What does the z-score represent for a number in a roughly normal distribution?

Which of the following correctly characterize the plausibility of Z-scores of a distribution calculated using the sample mean and deviation?

The sum of the squared deviations from the mean of 20 values is 1750. What is the standard deviation of these values?

Why is a numeric association between 2 variables, not necessarily indicative of a cause-effect relationship between the variables? Explain with an example.

Which of the following is considered the best way to present data (in charts) of a nominal variable?

What is the median value of the following set of numbers: 2, 5, 17, 1, 11, 18?

What are the plausible values possible for the standard deviation of any distribution?

The values of a numeric variable were as follows: 148, 120, 91, 178, 202, 115, and, missing. The mean value of the variable is 142.33.

The frequency distribution of a continuous variable with many unique values should be presented in a chart, rather than in a table.

Which measure of central tendency is preferred to describe a distribution that is significantly skewed?