The questions listed below are designed for
discussion and preparation before the midterm.
When reviewing these questions:
Illustrate your points with specific examples
Be as complete as you can with your definitions
In other words, be as specific as you can
and do not leave anything up to the reader.
Why do we make distinctions between samples and populations in statistics?
Discuss the differences between the descriptive and the inferential approaches to statistics. Is one "better" than the other? Are they competitive or complementary? Illustrate the kind of situation in which each approach is appropriate.
Discuss the use of exploratory data analysis. Illustrate with an example.
What is statistical visualization? Why do we use it?
Discuss histograms, frequency plots, boxplots, normal-probability plots, quantile plots and quantile-quantile plots. What are the strengths and weekness of each. What do we use each for?
Discuss the phrases "Being a Statistician is not having to be certain"; "Uncertainty - Something you can always count on", and "Statisics: Stability from variability."
What is the point of constructing frequency distribution tables and graphs?
What are the properties of a random sample?
Know the differences between each type of measurement scale (nominal, ordinal, interval, ratio). Illustrate each type with an example. What measures of central tendency and variation are appropriate for each type?
Know how to make a frequency distribution table (with f, cumf, % and cum%). Be able to describe its contents.
What is the relation between the median, percentiles, and the box plot?
What is skew? Kurtosis? Define and illustrate each with an example.
Compare and contrast the type of information you get with relative frequencies versus cumulative frequencies.
Why to statisticians care about the distribution of their data?
Is it enough to know general descriptive information about a distribution (i.e., the range, skewness, mean, etc.)? Why or why not?
What are outliers? What impact do they have on how you describe your data?
What are some of the special qualities of the mean?
What is variability? Discuss measures of variability. What are their strengths and weaknesses?
What are the sum of squares?
Why do we standardized data?
What does a Z-score tell you (i.e., how do you interpret one)? How do you convert a raw score to a Z-score?
What is the normal distribution? What is the standard-normal distribution? What is the unit-normal distribution?
How do you use the normal distribution table to find the percentage of the population that is expected to fall between two points or beyond one point in the distribution?
What are some of the benefits of using the normal distribution as a model for data at the population level?