What is the .05 level of significance? | If there is a plausible likelihood (more than 5% of the time) that random sampling error produced the relationship we see in the sample, we do NOT reject the null hypothesis.
Reference page(s): 157 |

What is analysis of variance? | a technique for measuring the relationship between one nominal- or ordinal-level variable and one interval- or ratio-level variable |

What is an asymmetric measure of association? | Models the independent variable as the causal variable and the dependent variable as the effect. Reference page(s): 170 |

What is the chi-square test of significance? | a statistic used to test the statistical significance of a relationship in a cross-tabulation table Reference page(s): 164 |

What is a concordant pair? | A pair of observations that is consistent with a positive relationship. Reference page(s): 174 |

What is the confidence interval approach? | A confidence interval for a parameter is an interval of numbers within which the parameter is believed to fall. The probability that the estimator produces an interval that contains the parameter is called the confidence level. This is a number chosen to be close to 1, such as 0.95 or 0.99. Reference page(s): 159 |

What is a correlation coefficient? | a statistic that indicates the strength and direction of the relationship between two interval- or ratio-level variables. It is a standardized measure, meaning that its numerical value does not change with linear scale changes in the variables |

What is Cramer's V? | A measure of association, based on chi-square, which takes a value between 0 (no relationship) and 1 (perfect relationship). It is not a measure of predictive accuracy. Reference page(s): 172 |

What is a critical value? | value which marks the upper plausible boundary of random error and so defines H_{0}'s limitReference page(s): 167 |

What is the difference of means test? | a statistical procedure for testing the hypothesis that two population means have the same value |

What is a discordant pair? | A pair of observations that is consistent with a negative relationship. Reference page(s): 174 |

What is effect size? | the effect of a treatment or an experimental variable on a response. Most commonly the size of the effect is measured by obtaining the difference between two means or two proportions |

What is eta-squared? | a measure of association used with analysis of variance that indicates the proportion of the variance in the dependent variable that is explained by the variance in the independent variable |

What is explained variation? | that portion of the total variation in a dependent variable that is accounted for by the variation in the independent variable(s) |

What is Goodman and Kurskal's Gamma? | a measure of association between ordinal-level variables |

What is Goodman and Kurskal's Lambda? | a measure of association between one nominal- or ordinal-level variable and one nominal-level variable |

What is Kendall's Tau B or C? | a measure of association between ordinal-level variables |

What is lambda? | A measure of proportional reduction in error, designed to measure the strength of a relationship between two categorical variables, at least one of which is nominal-level. Reference page(s): 170 |

What is a matrix plot? | a graph that shows several two-variable scatterplots on one page in order to present a simultaneous view of several bivariate relationships |

What are measures of association? | statistics that summarize the relationship between two variables Reference page(s): 156 |

What is a null hypothesis? | a statement that a population parameter equals a single or specific value. Often a statement that the difference between two populations is zero Reference page(s): 156 |

What is a one-tailed test of significance? | In performing a one-tailed test of statistical significance, we do not divide .05 in two and find upper and lower confidence boundaries. Rather, we place the entire rejection region in null hypothesis territory. Reference page(s): 160 |

What is a proportional-reduction-in-error (PRE) measure? | a measure of association that indicates how much the knowledge of the value of the independent variable of a case improves prediction of the dependent variable compared to the prediction of the dependent variable based on no knowledge of the case's value on the independent variable. Examples are Goodman and Kruskal's lambda and gamma, eta-squared, and R-squared Reference page(s): 169 |

What is the P-value approach? | The researcher determines the exact probability of obtaining the observed sample difference, assuming H_{0} is correct.Reference page(s): 159 |

What is a residual? | for a given observation, the difference between its observed value on a variable and its corresponding predicted value based on some model |

What is Somer's d_{yx}? | A measure of proportional reduction in error, designed to measure the strength of the relationship between ordinal-level relationships. Reference page(s): 170 |

What is the standard error of the difference between sample means? | A procedure for testing the statistical significance of the difference between two means. It is important to recognize that each sample mean has a standard error and we must account for both sample standard errors to test the significance of their difference. Reference page(s): 158 |

What is a standardized regression coefficient? | a regression coefficient based on two standardized variables. A standardized variable is derived from a transformed raw variable and has a mean of 0 and standard deviation of 1 |

What is statistical independence? | a property of two variables in which the probability that an observation is in a particular category of one variable and a particular category of the other variable equals the simple or marginal probability of being in those categories |

What is the strength of a statistical relationship? | an indication of how consistently the values of a dependent variable are associated with the values of an independent variable |

What is a symmetric measure of association? | A measure of association that takes on the same value regardless of whether the independent variable is used to predict the dependent variable or the dependent variable is used to predict the independent variable. Reference page(s): 169 |

What is a test of statistical significance? | A test of statistical significance helps you decide whether an observed relationship between an independent variable and a dependent variable really exists in the population or whether it could have happened by chance when the sample was drawn. Reference page(s): 156 |

What is a test statistic? | tells us exactly how many standard errors separate the sample difference from 0, the difference claimed by H_{0}.Reference page(s): 160 |

What is a tied pair? | A tied pair have different values of the independent variable but the same value of the dependent variable. Reference page(s): 174 |

What is total variation? | a quantitative measure of the variation in a variable, determined by summing the squared deviation of each observation from the mean |

What is a t-ratio? | A test statistic for sample statistics. Comparable to z-scores, t-scores take into account the variability of small samples. Reference page(s): 161 |

What is a two-tailed test of statistical significance? | In finding the upper and lower limits of random sampling error, it divides the .05 rejection region in half, reporting the value above which 0.25 of the curve falls and the value below which .025 of the curve falls. Reference page(s): 159 |

What is a Type I error? | error made by rejecting a null hypothesis when it is true Reference page(s): 156 |

What is a Type II error? | error made by failing to reject a null hypothesis when it is not true Reference page(s): 156 |

What is unexplained variation? | that portion of he total variation in a dependent variable that is not accounted for by the variation in the independent variable(s) |