A | B |

LINEAR | regression which assumes a proportionate relation between two variables |

INTERCEPT | the point on the Y axis where the regression line intersects |

SLOPE | the "rise over the run" of the regression line |

COEFFICIENT OF DETERMINATION | the percent of variance which one variable can predict in another; r squared |

COVARIANCE | it is good for this to be negative in our investment portfolios (r * SDx * SDy) |

CORRELATION | the Pearson coefficient is a measure of |

POSITIVE | a direct association between two variables; when one increases, the other increases; when one decreases, the other decreases |

NEGATIVE | an inverse association between two variables; when one increases, the other decreases |

STRONG | a correlation coefficient close to negative one |

WEAK | a correlation coefficient close to zero |

SCATTER PLOT | graph of bivariate relationship between two variables |

INDEPENDENT | variable which is a cause (or selected for the X axis) |

DEPENDENT | variable which is the outcome to be predicted |

Y AXIS | verticle representation of the outcome (criterion) variable |

X AXIS | horizontal representation of the predictor variable |

CURVILINEAR | when two variables have an association which is direct over a certain range, and inverse over another range |

SPURIOUS | when two collateral effects are correlated |

PEARSON | the type of coefficient used for correlations between two variables that are ratio scales and normally distributed |

ZERO | when there is absolutely no association between variables, the correlation is |