Spot The Study Design
Below are several real results sections taken from APA published manuscripts. Based on the excerpts, I want you to do a few things for each study. FIRST, identify the study design (tell me if it is correlational or experimental). SECOND, if it is experimental, identify the independent variable. THIRD, if it is experimental, identify the dependent variables. FOURTH, tell me what statistical test the author ran and tell me how you know they ran that specific test (that is, what features of the results excerpt points to it being statistical test ABC rather than statistical test XYZ). FINALLY, piece together the null and alternative hypotheses for each study excerpt.
Note #1: In published research, authors might refer to tables for means, so you may not see them in the excerpts below!
Note #2: Sometimes the author specifically mentioned the test they ran in the excerpt. Since I think you can spot it without being blatantly told what test they ran, I simple deleted that info (hence the ________ in some of the paragraphs). Hope you don’t mind!
Note #3: I might have included the same kind of study design more than once (and omitted some of the study designs we covered this semester). You are forewarned!
____________________________________________________________________________
Study One Results Section:
To measure amount of violent video game play, participants were asked to name their three favorite video games, to indicate how often they play each video game (on a scale from 1 = sometimes to 7 = very often), and to rate how violent the content of each video game was (on a scale from 1=not at all to 7=very). As in previous research (e.g., Anderson & Dill, 2000; Greitemeyer, 2014), for each video game, the frequency of game play was multiplied by violent content. These three violent video game exposure scores were then summed to provide a measure of the amount of violent video game play.
The expanded version of the Comprehensive Assessment of Sadistic Tendencies (Buckels & Paulhus, 2014) was used to assess everyday sadism, which contains 18 items. A sample item is: “I was purposely mean to some people in high school.” To measure narcissism, psychopathy, and Machiavellianism, we used the Dirty Dozen, with four items per subscale (Jonason & Webster, 2010). Sample items are: “I tend to want others to pay attention to me” (narcissism), “I have used deceit or lied to getmy way“ (Machiavellianism), and “I tend to be cynical“(psychopathy). Both sadistic tendencies and the Dark Triad items were assessed on a scale from 1 (strongly disagree) to 5 (strongly agree). To measure trait aggression, participants responded to the short version of the Buss and Perry aggression questionnaire (Bryant & Smith, 2001),which contains 12 items (e.g., “I have threatened people I know.”) These items were assessed on a scale from 1 (very unlike me) to 5 (very like me). To measure the Big 5, a brief version was employed (Gosling, Rentfrow, & Swann, 2003). There are two items per scale. Some scale reliabilities were relatively poor, which is a typical psychometric cost of using short measures (Gosling et al., 2003). The Big 5 items were assessed on a scale from 1 (disagree strongly) to 7 (strongly agree.
All measures are shown in Table 1. In support of our central hypothesis, violent video game play was positively associated with everyday sadism at both times of measurement. In addition, amount of violent video game play was consistently positively associated with trait aggression and the Dark Triad and was negatively associated with agreeableness.
1. What kind of study design is this (experimental or correlational)?
2. If experimental, what is the independent variable?
3. If experimental, what is the dependent variable?
4. What kind of statistical test did the author run, and how do you know the used this test?
5. What do you think the null and alternative hypotheses are in this study? You might have to guess, but make them educated guesses!
_____________________________________________________________________________
Study Two Results Section
Researchers examined the effect of perceived control on health complaints of geriatric patients in a long-term care facility. Thirty patients were randomly selected to participate in the study. Half were given a plant to care for and half were given a plant, but the care for the plant was turned over to the staff. The number of health complaints was recorded for each patient over a seven day period. Researchers found that those geriatric patients who directly cared for the plants reported fewer health complaints (M = 16.60, SD = 7.79) than those given plants cared for by the long-term care facility staff (M = 27.07, SD = 7.74), t(28) = 3.69, p < .001
1. What kind of study design is this (experimental or correlational)?
2. If experimental, what is the independent variable?
3. If experimental, what is the dependent variable?
4. What kind of statistical test did the author run, and how do you know the used this test?
5. What do you think the null and alternative hypotheses are in this study? You might have to guess, but make it aneducated guesses!
______________________________________________________________________________
Study Three Results Section
The current study examined the clinical efficacy of a new antidepressant. Depressed patients were randomly assigned to one of three groups: a placebo group, a group that received a low dose of the drug, and a group that received a moderate dose of the drug. After four weeks of treatment, the patients completed the Beck Depression Inventory. The higher the score, the more depressed the patient. There was a significant difference, F(2, 223) = 3.56, p < .05. Follow-up Tukey post-hoc tests showed that participants showed significantly less depression as measured by the Beck Depression Inventory in both the low-dose drug condition (M = 5.66, SD = 1.22) and the moderate-dose condition (M = 6.12, SD = 1.18) than the placebo condition (M = 8.87, SD = 1.65). However, the low-dose and moderate-dose conditions did not differ from each other.
1. What kind of study design is this (experimental or correlational)?
2. If experimental, what is the independent variable?
3. If experimental, what is the dependent variable?
4. What kind of statistical test did the author run, and how do you know the used this test?
5. What do you think the null and alternative hypotheses are in this study? You might have to guess, but make it aneducated guesses!
______________________________________________________________________________
Study Four Results Section:
A study wanted to examine the effect of a new Federal Drug Administration (FDA) e-cigarette warning label on college students’ perceived advantages and risks of e-cigarette use, as well as students’ intentions to use e-cigarettes. Using college students at a Midwestern university, the study measured 338 student attitudes toward e-cigarettes both prior to and after exposing them to the warning label proposed by the FDA. Findings showed that college students’ perceived advantages of e-cigarette use were positively related to their intentions to use e-cigarettes, t(337) = 4.67, p < .01. However, their perceived risks were negatively associated with their intentions, t(337) = -8.56, p < .001. Participants also expressed less intention to use e-cigarettes after reading the new label, t(337) = 4.56, p < .05. The warning label proposed by the FDA is thus effective, though it has room for improvement to make a greater impact on e-cigarette use intention.
1. What kind of study design is this (experimental or correlational)?
2. If experimental, what is the independent variable(s)?
3. If experimental, what is the dependent variable(s)?
4. What kind of statistical test did the author run, and how do you know the used this test?
5. What do you think the null and alternative hypotheses are in this study? You might have to guess, but make it aneducated guesses!
______________________________________________________________________________
Study Five Results Section
This study makes an original and rigorous contribution to the psychology of sport injury literature by examining the efficacy of emotional disclosure to promote sport-injury-related growth (SIRG). Participants (N = 45) were assigned to one of three groups (i.e., written disclosure [WD, where participants were asked to write about their deepest thoughts and feelings regarding their recent sporting injury], verbal disclosure [VD, where participants were asked to talk about their deepest thoughts and feelings regarding their recent sporting injury into an audio-tape recorder], or control [C, where participants were asked to write facts about their daily events). The VD group (M= 40.17, SD = 26.15) experienced SIRG to a much greater extent than the WD group (M = 44.47, SD = 19.71) and the C group (M= 42.67, SD = 21.49), F(2, 43) = 7.86, p < .05. There was no significant difference between the WD and control groups.Practical implications are considered at intrapersonal, interpersonal, institutional, and cultural levels.
1. What kind of study design is this (experimental or correlational)?
2. If experimental, what is the independent variable?
3. If experimental, what is the dependent variable?
4. What kind of statistical test did the author run, and how do you know the used this test?
5. What do you think the null and alternative hypotheses are in this study? You might have to guess, but make it aneducated guesses!
