AP® Statistics Unit 1 flashcardsExploring One-Variable Data and Collecting Data
40 cards · about 10 minutes for the whole deck
Flashcard drill
Space flips the card, arrow keys move, and keys 1 to 4 rate how well you knew it.
- Position
- 1 / 40
- Due
- 40
- Mastered
- 0 / 40
This card: New
Flip the card before you rate it.
Investigative question
The question a statistical study sets out to answer. It names the population and variable, can be answered with data, and doesn't change after you see the results.
Topic 1.1: Introducing Statistics: What Can We Learn from Data?
Population
The whole group you want to learn about, with size N. It's usually too big or costly to measure everyone in it.
Topic 1.1: Introducing Statistics: What Can We Learn from Data?
Sample
The smaller group, of size n, that you actually collect data from. You use it to learn about the population.
Topic 1.1: Introducing Statistics: What Can We Learn from Data?
Observational unit
The person or thing you collect data from, like one student, one car or one day. Each row of a data set is one unit.
Topic 1.2: Variables
Categorical variable
A variable that puts each unit into a group, like eye color or zip code. Its values are labels, even when they look like numbers.
Topic 1.2: Variables
Quantitative variable
A variable whose values are counted or measured numbers, where doing math with them makes sense, like height or number of siblings.
Topic 1.2: Variables
Discrete vs. continuous
A discrete variable takes countable values with gaps between them (number of pets). A continuous one can take any value in an interval (time, weight).
Topic 1.2: Variables
Parameter
A number that describes a whole population, like μ or p. It's usually unknown, so you estimate it.
Topic 1.2: Variables
Statistic
A number that describes a sample, like x̄ or p̂. You calculate it from your data and use it to estimate a parameter.
Topic 1.2: Variables
Relative frequency
The proportion of all units that fall in a category: the category's count divided by the total. It lets you compare groups of different sizes.
Topic 1.3: Tabular Representation and Summary Statistics for One Categorical Variable
Bar chart
A graph for one categorical variable where each bar's height shows a category's count or proportion. The bars don't touch, and their order can change.
Topic 1.4: Graphical Representations for One Categorical Variable
Histogram
A graph of one quantitative variable that groups values into intervals (bins) and shows each bin's count with a bar. Changing the bin width can change how it looks.
Topic 1.5: Graphical Representations for One Quantitative Variable
Skewed right vs. skewed left
Skewed right means a long tail toward large values, which usually pulls the mean above the median. Skewed left means a long tail toward small values, with the mean usually below.
Topic 1.6: Descriptions for One Quantitative Variable Distributions
Mean (x̄)
The sum of the values divided by how many there are. It's the balance point of the data and gets pulled toward outliers and long tails.
Topic 1.7: Summary Statistics for One Quantitative Variable
Median
The middle value when the data are in order (the average of the two middle values if n is even). It's resistant: outliers and skew barely move it.
Topic 1.7: Summary Statistics for One Quantitative Variable
Standard deviation (s)
Roughly the typical distance of values from the mean. It's 0 only when all values are equal, and outliers make it bigger.
Topic 1.7: Summary Statistics for One Quantitative Variable
Interquartile range (IQR)
Q3 − Q1, the range of the middle 50% of the data. It's a resistant measure of variability.
Topic 1.7: Summary Statistics for One Quantitative Variable
1.5 × IQR outlier rule
A value is an outlier if it's more than 1.5 × IQR below Q1 or more than 1.5 × IQR above Q3.
Topic 1.7: Summary Statistics for One Quantitative Variable
Percentile
The pth percentile is the value with p% of the data at or below it. Being at the 90th percentile means you're higher than about 90% of the group.
Topic 1.7: Summary Statistics for One Quantitative Variable
Boxplot
A graph of the five-number summary (min, Q1, median, Q3, max). The box covers the middle 50% of the data, and outliers are plotted as separate points past the whiskers.
Topic 1.8: Graphical Representations of Summary Statistics for One Quantitative Variable
z-score
. It tells how many standard deviations a value is above (positive) or below (negative) the mean.
Topic 1.9: Comparisons of the Distributions for One Quantitative Variable
Census
Collecting data from every member of the population. It answers the question exactly, but it's often too slow, costly or impossible.
Topic 1.10: The Investigative Question Revisited and Data Collection
Observational study
A study that measures variables without imposing any treatment. It can show an association but can't show cause and effect.
Topic 1.10: The Investigative Question Revisited and Data Collection
Experiment
A study where researchers impose treatments on experimental units and measure the response. With random assignment, it can show cause and effect.
Topic 1.10: The Investigative Question Revisited and Data Collection
Confounding variable
A variable linked to both the explanatory and the response variable, so you can't tell which one caused the change in the response.
Topic 1.10: The Investigative Question Revisited and Data Collection
Simple random sample (SRS)
A sample chosen so that every possible group of n units has the same chance of being the sample.
Topic 1.11: Random Sampling
Stratified random sample
Split the population into groups of similar units (strata), then take an SRS from each stratum. When strata differ but units within each are alike, it gives more precise estimates.
Topic 1.11: Random Sampling
Cluster sample
Split the population into groups (clusters), randomly pick some whole clusters, and use every unit in them. It's quick and cheap.
Topic 1.11: Random Sampling
Systematic random sample
Pick a random starting point from the first k units, then take every kth unit after that.
Topic 1.11: Random Sampling
Bias
When the way you collect data makes a statistic come out too high or too low over and over. A bigger sample doesn't fix it.
Topic 1.12: Potential Problems with Sampling
Voluntary response bias
People choose themselves to respond, and those with strong (often negative) opinions are the most likely to do so.
Topic 1.12: Potential Problems with Sampling
Undercoverage
Some groups in the population have less chance, or no chance, of being chosen for the sample.
Topic 1.12: Potential Problems with Sampling
Nonresponse bias
People chosen for the sample can't be reached or refuse to answer, and they differ from the people who do respond.
Topic 1.12: Potential Problems with Sampling
Response bias
Answers are systematically off, for example because of a leading question, an interviewer's presence or people not wanting to admit something.
Topic 1.12: Potential Problems with Sampling
Random assignment
Using a chance process to decide which units get which treatment. It balances other variables across groups, which allows cause-and-effect conclusions.
Topic 1.13: Experimental Design
Placebo
A fake treatment, like a sugar pill, that looks just like the real one. It controls for the placebo effect.
Topic 1.13: Experimental Design
Double-blind
Neither the subjects nor the people who measure the response know who got which treatment, so expectations can't affect the results.
Topic 1.13: Experimental Design
Randomized block design
Group similar units into blocks first, then randomly assign treatments within each block. It removes the block variable's effect on the response.
Topic 1.13: Experimental Design
Matched pairs design
Pair up similar units, then randomly decide which one in each pair gets which treatment. Or give each unit both treatments in a random order.
Topic 1.13: Experimental Design
Replication
Using enough experimental units in each treatment group so that real differences can stand out from chance variation.
Topic 1.13: Experimental Design