Probability
Categorical Data
Statistical Bias
Indexing
Dimensions and Indicators
100
A shelf contains 5 novels, 3 science books, and 10 math books. You grab a book at random to read during your open block. What is the probability that you get a novel?
5/18
100
You asked your classmates their favorite movie or TV show. Is this data:
1) Categorical or numerical?
2) If categorical: Ordinal or nominal?
3) If numerical: Discrete or continuous?
Categorical, nominal
100
Is this question biased or non-biased? A pollster asks you:
"Can I count on your vote for the amazing and honest Politician McPolitics?"
Biased
100
Indexing data makes it easier to do what?
To compare datasets with very different magnitudes
100
What is the difference between a dimension and an indicator?
Dimension = Category, can't be measured
Indicator = Variable, can be measured
200
You flip a coin several times as shown below. What is the EXPERIMENTAL probability of getting tails?
HT HH TH TT TH HH TH
4/7 or about 57%
200
You asked your classmates how many songs they have on their favorite playlist. Is this data:
1) Numerical or categorical?
2) If categorical: Ordinal or nominal?
3) If numerical: Discrete or continuous?
Numerical, discrete
200
A study comes out with the title, "Billionaires like Mark Zuckerberg, Steve Jobs, and Bill Gates just needed an idea, then they dropped out of school to make it happen! You can do it too!"
What type of bias is this?
Survivorship bias
200
The population of Los Angeles starts at the indexed value of 100. Two years later, it's at an indexed value of 106. This means that the population (increased/decreased) by what percentage?
Increased by 6%
200
You're trying to rank your favorite video games for an article you're writing. You've chosen the dimension of "storyline". Would "number of cutscenes" be an indicator? Why or why not?
Yes, you can measure it
300
Your soccer team has two games to play. You have a 60% chance of winning the first game, and a 45% chance of winning the second one (based on previous games against these teams). What is the probability that you'll win both games?
27%
300
What is the purpose of k-clustering?
To separate data on a scatterplot into distinct groups
300
A study comes out with the title, "Cell phone users are very likely to have attention problems!" You read the article and it says they surveyed 15,000 cell phones users and asked if they had any type of attention disorders. What type of bias might be present here?
Selection bias OR nonresponse bias
300
The performance of a stock started at an indexed value of 100. Two weeks later, its indexed value was 68. This means that it (increased/decreased) by what percentage?
Decreased by 32%
300
You read an article with the equation:
Score = 2*WeatherIndex + IncomeIndex
Which is more important to the writer?
Weather
400
Your new playlist has 4 hip-hop songs, 8 rap songs, and 5 rock songs so far. You play the songs on shuffle. What are the chances of playing a rap song, then a rock song?
8/17*5/16 = 5/34
400
What number belongs in the empty goldenrod cell?
140
400
A popular cell provider company publishes statistics on its website, with the headline, "People love us!" The statistics are survey results from people who were given free phones to review. What type of bias might be present?
Funding bias
400
A stock starts at $50. A month later, it's at $60. What is its indexed value at that time?
120
400
You want to rank movies for an article you're writing. You've chosen "performances" as a dimension. What indicators might you use? Name at least one.
Varies!
500
What is the probability of the spinner landing on first blue, then red?
0.3*0.7 = 0.21
500
This is a relative frequency table. It is a (row/column/whole-table) frequency table.
Whole table
500
Tom likes Star Wars, so he looks up and reads articles with headlines such as "Why Star Wars is the best," and "Why everyone should love Star Wars". What kind of bias might he be experiencing?
Confirmation bias
500
Stock A started at $75 and went to $40 in a month.
Stock B started at $90 and went to $55 in a month.
Which stock performed worse? Use indexed values to find out.
A = index 53
B = index 61
So A performed worse
500
You want to rank cell phones for your YouTube channel where you review tech. What dimensions might you use? Name at least one.
Varies!