Term
|
Definition
| a formula for a line that models a linear relationship between two quantitative variables |
|
|
Term
|
Definition
| the observed y mines the predicted y; denoted y - yhat |
|
|
Term
|
Definition
| a plot that show how well the regression line fits the data; complete scatter plot in a shoebox form is good, |
|
|
Term
|
Definition
| the shape in a residual plot that means there is unequal variance in the y's across all levels of x (the standard deviation doesn't stay the same) |
|
|
Term
|
Definition
| the shape in a residual plot that means the data is not linear |
|
|
Term
|
Definition
| the random variable of the sampling distribution of x bar |
|
|
Term
|
Definition
| the list of all possible outcomes of a random phenomenon |
|
|
Term
| sampling distribution of x bar |
|
Definition
| a distribution of all possible x bars from all possible samples |
|
|
Term
|
Definition
| the variability of sample results from one sample to the next; something we must measure in order to effectively do inference |
|
|
Term
|
Definition
| a two dimensional plot used to examine strength of relationship between two variables as well as direction and type of relationship |
|
|
Term
| significance level (alpha) |
|
Definition
| the risk (probability) of incorrectly rejecting a true null hypothesis. when p is low reject Ho and conclude that Ha is correct |
|
|
Term
| simple conditions for inference |
|
Definition
| SRS, population normally distributed and sigma known |
|
|
Term
|
Definition
| when percentages in a two way table reverse because a third (lurking) variable is ignored (Larry Bird and free throws) |
|
|
Term
|
Definition
| using random numbers to imitate chance behavior |
|
|
Term
|
Definition
| a measure of the average change in the response variable (Y) for every one unit increase in the explanatory variable (X) |
|
|
Term
|
Definition
| a measure of the variability of the data in a sample about x bar |
|
|
Term
| standard deviation of x bar (also called standard deviation of the sampling distribution of x bar) |
|
Definition
| a measure of the variability of the values of the statistic x bar about mu; computed as sigma over the square root of n. |
|
|
Term
|
Definition
| a number computed from sample data (without any knowledge of the value of a parameter) used to estimate the value of a parameter |
|
|
Term
|
Definition
| x bar, s, p hat: mean of a sample, standard deviation of a sample, proportion of a sample |
|
|
Term
| statistical process control |
|
Definition
| a procedure used to check a process at regular intervals to detect problems and correct them before they become serious. |
|
|
Term
| statistically significant |
|
Definition
| results of a study that differ too much from what we expected (if Ho were true) because of randomization to attribute to chance variation; the difference between the observed statistic and the claimed parameter value is too large to be due to chance. Happens when p value is lower than alpha |
|
|
Term
|
Definition
| the residuals are squared and added; denoted SSE |
|
|
Term
|
Definition
| procedure used to assess the evidence against a claim (hypothesis) about the value of a parameter |
|
|
Term
|
Definition
| a number that summarizes the data for a test of significance; usually used to obtain p value |
|
|
Term
|
Definition
| the sum of the squared deviations of the Y observations about their mean, y-bar |
|
|
Term
|
Definition
| a type of alternative hypothesis where the researcher is interested in deviations in both directions |
|
|
Term
|
Definition
| a table containing counts for two categorical variables. it has r rows and c columns. |
|
|
Term
|
Definition
| a condition where the mean of the statistic values equals the parameter that the statistic estimates |
|
|
Term
|
Definition
| the sum of squared residuals |
|
|
Term
|
Definition
| the symbol for explanatory variable |
|
|
Term
|
Definition
| a plot of sample means over time used to assess whether a process is in control |
|
|
Term
|
Definition
| the symbol for response variable |
|
|
Term
|
Definition
| the symbol for predicted y |
|
|
Term
|
Definition
| the z-value obtained from table C corresponding to a desired level of confidence; used in computing a confidence interval |
|
|
Term
|
Definition
| a measure of the number of standard deviations of a value or observation from the mean |
|
|
Term
|
Definition
| the probability that the value of the parameter mu is in the confidence interval. OR the probability that the null hypothesis is true |
|
|
