想请各位对研究设计比较有心得的高手 帮我看看下面这四个题目 非常感谢大家!:) 1. Which of the following is not a condition for the confounding effects of regression artifacts? a. Subjects chosen for this treatment on extremely high or low scores on a pretest. b. An unreliable test is used for both the pretest and posttest. c. A t-test finds no significant differences between the group's pretest and posttest scores. d. All of the above are essential conditions for the presence of regression artifacts. e. None of the above are essential conditions for the presence of regression artifacts. 2. Which of the following is not true of random sampling? a. It is the basis for all inferential statistics. b. It is the basis of hypothesis testing. c. It ensures representativeness. d. It us bias-free. 3. Which of the following is not a specific purpose of random assignment of subjects to treatment and control group in a true experiment? a. To randomly distribute individual differences among treatment and control groups b. To increase the internal validity. c. To control for the effects of history. d. To control for the possible interaction of selection and maturation. 4. When the interrater reliability is quite low, what's the likely effect of these errors of measurement in the dependent variable on the variance in the dependent variable? a. Since one eater scored test lower than another, the variance will be increased and biased in a negative direction. b. Since one eater scored test higher than another, the variance will be increased and biased in a positive direction. c. The errors of measurement will add to the total variance, but not in any systematic direction. d. None of the above. 麻烦大家解答了 非常感谢^^ -- http://www.wretch.cc/album/littlemi --

※ 发信站: 批踢踢实业坊(ptt.cc) ◆ From: 173.19.200.123 ※ 编辑: mimichelle 来自: 173.19.200.123 (12/13 13:22)