Chapter 9, Problem 1.6C

Suppose a clinical psychologist sets out to see whether sexual orientation is related to relationship longevity. He decides to measure relationship satisfaction in a group of homosexual couples and a group of heterosexual couples. He chooses the Marital Satisfaction Inventory because it refers to “partner” and “relationship” rather than “spouse” and “marriage,” which makes it useful for research with both traditional and nontraditional couples. Higher scores on the Marital Satisfaction Inventory indicate greater relationship satisfaction. The psychologist administers the Marital Satisfaction Inventory to 53 couples—23 are homosexual couples and 30 are heterosexual couples. He wants to calculate the correlation between a couple’s relationship satisfaction and sexual orientation. Which of the following types of correlations would be most appropriate for the psychologist to use? A point-biserial correlation   A Spearman correlation   A phi-correlation   A Pearson…

According to Stuart (2010), which of the following statements about observational study designs for causal inference are typically true? Choose all that apply. Including propensity score estimates as a predictor in a regression model on outcomes can help resolve imbalance between treatment and control groups for covariates used in the propensity score model Standard diagnostic tools for binary prediction or classification models (e.g. logistic regression or classification trees) are similarly used in evaluating propensity score estimates When conditional ignorability holds given the observed covariates, then the treatment assignment will also be ignorable conditioned on the propensity scores Overfitting in propensity score estimation can achieve more efficient estimates of treatment effects than using propensity score estimates that are closer to the true propensities Unlike full matching, subclassification, and weighting methods, nearest neighbor matching does not necessarily use all…

A sample of twenty automobiles was taken, and the miles per gallon (MPG), horsepower, and total weight were recorded. Develop a linear regression model to predict MPG using horsepower as the only indepen- dent variable. Develop another model with weight as the independent variable. Which of these two models is better? Explain. MPG 44 44 40 37 37 34 35 32 30 28 26 26 25 22 20 21 18 18 16 16 4 HORSEPOWER 67 50 62 69 66 63 90 99 63 91 94 88 124 97 114 102 114 142 153 139 WEIGHT 1,844 1,998 1,752 1,980 1,797 2,199 2,404 2,611 3,236 2,606 2,580 2,507 2,922 2,434 3,248 2,812 3,382 3,197 4,380 4,036