AP Statistics Vocabulary

When only either the researchers or the subjects know which treatments were assigned to groups.

A family of distributions that always take on positive values and are skewed right.

The distribution of many samples.

Making conclusions about a larger population based on sample data.

A non-symmetric distribution that has a distinct tail.

The distribution of a random variable of continuing trials until a certain number of successes.

The four evenly sized sections of a set of ordered data.

The sum of the values of the observations divided by the number of observations.

Occurs when we fail to reject the Null hypothesis when it was actually false.

The response value a Least Squares Regression Line would expect for a given explanatory value.

A diagram used to display the sample space of a chance process involving a sequence of outcomes

When knowing the value of one variable helps to predict the value of another.

The distribution of total values for categorical variables on a one-way or two-way table.

A graph that shows bars that have ranges for counts of a continuous variable.

When a group of the population does not get accurate representation in a sample.

When the effects of two different variables on a response variable cannot be told apart.

A variable that takes on an infinite number of values.

When randomly selected individuals cannot be contacted or refuse to participate.

When it is not possible for two event to occur simultaneously.

The occurrence of one event or the other, or both.

The distribution of a random variable with the number of trials set in advance.

A fixed value used as a cutoff on what probability is or is not statistically significant.

A variable of description rather than value.

A number from a sample used to estimate some characteristic of a population.

When the design of a study would consistently give an over or underestimate of the true value.

Explains how well the regression line fits the data, from 0 (weak) to 1 (strong).

The claim that we do not believe to be true that we are trying to find evidence against.

A sampling distribution of at least 30 will be approx normal even if the population is not.

The typical or common distance observations are away from the mean.

The maximum minus the minimum.

An accurate statistic used to approximate the parameter of a population.

A Normal distribution with mean 0 and standard deviation of 1.

The fraction of the variation that can be explained by the least-squares regression line (r²).

A graph that shows the relationship between two quantitative variables using dots.

A sample selected by taking individuals that were easy to reach.

The middle number (resistant to outliers).

An event that rarely would have happened just by chance.

The number of standard deviations to be added/subtracted from the test statistic (z* or t*)

A study where researchers deliberately impose treatment on the individuals.

When neither the researchers nor the subjects know which treatments were assigned to groups.

The individual terms that are added together to form the test statistic for categorical data.

The range from Q1 to Q3.

A group of experimental units that are similar and so are treated as one experimental unit.

The number of individuals of a sample found in each category in response to a survey.

A variable of value rather than description.

The probability that the statistic would have taken on a value given the Null hypothesis true.

When the right and left sides of a distribution are mirror images of each other.

The # of standard deviations an observation falls from the center of a Normal distribution.

A sample obtained by putting individuals into like-groups and randomly choosing some from each.

Occurs when we reject the Null hypothesis when it was actually true.

Minumum, Q1, Median, Q3, and Maximum values of a data set.

A graph of the five-number summary.

The proportion of a chance process will approach a single value as you do more trials.

The distribution of just one sample.

The proportion of observations that are lower than a particular observation.

The standard deviation of a significance test or confidence interval.

An inactive (fake) treatment for which some subjects may actually respond.

The most common number.

__% of all such samples would produce a range of values that would capture the true value.

The smallest collection of individuals to which a treatment is to be applied.

A number that describes some characteristic of a population.

A smaller group of individuals whose information is used to infer about a larger group.

The probability that a test will reject the Null when the Alternative is true.

A model that describes the overall pattern of a distribution.

An imitation of a chance behavior that uses a model that accurately represents the situation.

The difference between an observed value and its predicted/expected value.

The occurrence of two events at the same time.

A study that attempts to survey every individual of the population.

The probability that an event will occur given that another event has already occurred.

The exact counts of a variable.

A sample selected by taking individuals that select themselves.

A sample by putting individuals into population-like groups and randomly choosing one group.

The variable that may predict the changes in another variable.

The set of all possible outcomes of a chance process.

The amount of counts of a variable out of all counts, often expressed as a percent.

A procedure using a sample statistic to make a decision about the validity of a claim.

Individuals are monitored for measures of variables of interest but not influenced in response.

The (inaccurate) use of a regression line to estimate outside the range of the given data.

A class of density curves that are symmetric, single-peaked, and bell-shaped.

The probability that an event does NOT happen.

When a distribution is even across the full range of values of the variable.

A sample where each individual was randomly chosen from the population.

Decisions based through a process of chance.

In experiments, when all variables except for the explanatory variable must be kept the same.

A sample where each individual was randomly chosen and randomly assigned to a treatment.

The entire group of individuals which we are interested in knowing something about.

The science of data.

A number between 0 and 1 that describes the proportion of an outcome in a chance process.

A family of distributions like the Normal curve expect with more variability in the samples.

The claim that we actually believe to be true that we are trying to find evidence for.

An outcome of a chance process is more likely to occur if it has not occurred for a long time.

The total value to be added/subtracted from the test statistic to find the interval max/min.

A variable that takes on a finite number of values (usually no decimals).

Explains the linear relationship between two quantitative variables, from -1 to 1.

A range of plausible values for a parameter, based on a statistic.

An individual that falls well outside the pattern of data.

The number of individuals that would be found in each category if the Null hypothesis is true.

A graph of quantitative data with two clear peaks.

When randomly selected individuals in a sample do not provide accurate information.

A common form of blocking in comparing two different treatments, often on the same sample.