Data Types and Miscellaneous
(1.2)
(1.2)
What type of data is used in Likert scales?
Ordinal
What is the ideal type of sample we desire in any statistical study, one in which all members of the population have an equal likelihood of being selected?
Simple Random Sample
Explain how to find the IQR given a list of values.
Put in order, find Q1 and Q3, then subtract Q3-Q1.
How do you calculate z score?
Your value minus the mean, then divided by the standard deviation.
True or false, to get the mean of the sample, you divide by the square root of the sample size.
False, the mean stays the same. (Standard error = SD/sqrt(n)
False, we can only represent numerical data in a histogram.
Explain how stratified random sampling works.
Split population into clusters or groups, then select a random sample from each of those clusters.
Explain the processes of calculating the standard deviation.
Find the mean, subtract the mean from each value, square each, add, divide by n-1, square root.
How do you calculate the p value once you have your z score?
You use the z chart to look up the p value, matching the decimals of the z score.
True or false: A larger sample size leads to a smaller standard error.
True.
What are the names of (a) the woman in the videos we watch and (b) the coordinator of OnRamps Statistics?
Kristin Harvey and Mike Young
When studying whether serving ice cream and number of drownings are related, a statistician realizes there is, in fact, a correlation. To imply causation, they would be failing to account for what type of variable?
Confounding variable (summer months)
How do you know when to use the mean/SD or median/IQR to represent the center and spread of the data?
Normal = mean/SD, skewed or bi-modal = median/IQR
The empirical rule says that roughly 68% of the data should be how close to the mean?
Within one standard deviation (higher or lower).
True or false: if the population data is skewed right, then the means of several samples of the same size (e.g. 40) will actually tend to be normal.
True. This is known as the Central Limit Theorem.
Explain a common error in typing code into RStudio
Wrong names of labels/variables, missing characters in the commands.
We want to survey a sample of seniors to determine which prom themes are desired this year. Explain the parameter of interest and the sampling statistic in this scenario.
Parameter of interest = choices of all seniors, sampling statistic = choices of only those seniors surveyed.
How do you calculate the mean of a frequency chart?
You multiply each value times its frequency, add up those totals, then divide by how many data points you have.
If you want the percentage of the data greater than a particular value, how do you use the z chart differently?
Using the z score, find the p value, but subtract that p value from 1.000
If you are given the standard error and sample size, how can you find the original standard deviation?
Multiply standard error by the square root of the sample size.
If you don't have a 60 in the class after the midterm, there is another way to earn eligibility to get college credit. How can you do that?
Obtain a certain score on one of these: TSI, SAT, or ACT
Explain the difference between voluntary response bias and nonresponse bias
In nonresponse bias, we care that some have not replied, we depend on seeking them out again!
How do you calculate the median, Q1, and Q3 of a frequency chart?
You count from one end to the other, identifying which bin contains the halfway point, the 25th percentile, and the 75th percentile, respectively.
If you want the 80th percentile, how do you use your z chart to find the value?
Find the closest p value near 0.800, then work backwards to find the z score...then the initial value.
If you are given the standard error and the standard deviation, how do you find the sample size?
Divide the standard deviation by the standard error, then square it.