Number of Predictors

Tables are often very helpful for summarizing the models in a study. Here, we can see three

models and the impact of each of the predictors (main effect of individual variables [e.g., Dog]

plus interaction effects [e.g., Dog x Social Support]) on the different outcomes. We want to look

at the most complex model, which means the model with the most predictors.

Model 1: Dog vs. No Pet.

Model 2: Cat vs. No Pet.

Model 3: Dog + Cat vs. No Pet.

Do they differ in the number of predictors? If so, use the largest number of predictors to

substitute for k in the Rule of Thumb.

Table 2. Models of companion pet groups with sociodemographics and social support.

Functional

Pain

Subjective

Success

Ability

SE

Dog vs. No Pet

Gender

Age

Race

Education

Income

Live Alone

Dog

Social Support

Dog x Social Support

Cat vs. No Pet

Gender

Age

Race

Education

Income

Live Alone

Cat

Social Support

Catx Social Support

Dog + Cat vs. No Pet

Gender

Chronic

Illness

B

SE

0.38 0.04

0.06*** 0.00

0.23*** 0.06

-0.08*** 0.01

-0.17 0.02

-0.07** 0.06

-0.32*** 0.06

-0.08

0.01

0.08

0.02

0.38*** 0.05

0.06*** 0.00

0.26*** 0.07

0.00 0.01

-0.18 0.02

-0.14" 0.06

0.32 0.04

-0.07*** 0.01

-0.06 0.06

0.38*** 0.06

0.06*** 0.00

0.29*** 0.07

-0.02*** 0.01

-0.16*** 0.02

-0.05** 0.06

-0.12" 0.34

-0.18"* 0.03

0.02 0.08

B

-1.91***

0.21

-0.05*** 0.01

-0.55*** 0.30

0.18***

0.05

1.25*** 0.09

0.46*** 0.06

SE

1.99* 1.18

0.14

0.27

1.16

-0.54*

-2.18***

0.21

-0.05*** 0.02

-0.70*** 0.30

0.11*** 0.06

0.09

1.35***

0.50***

0.04

1.11

0.72

1.14*** 0.14

-0.23 0.26

-2.07*** 0.22

-0.05*** 0.02

-1.00*** 0.31

0.14*** 0.06

1.26*** 0.09

Age

Race

Education

Income

Live Alone

Dog+Cat

Social Support

Dog+Cat x

Social Support

Note: n = 5,502; p<0.10, *p<0.05, **p<0.01, ***p<0.001.

0.46" 0.26

2.10* 0.92

1.16*** 0.14

-0.52* 0.04

B

SE

0.56*** 0.09

-0.02

0.06

-0.17 0.10

-0.08*** 0.02

-0.39*** 0.04

-0.23* 0.10

-0.23* 0.19

-0.36** 0.06

0.09

0.11

0.56*** 0.09

-0.01

0.01

0.02* 0.13

-0.06*** 0.02

-0.42*** 0.04

0.10

-0.27*

0.42 0.46

-0.35*** 0.06

-0.09 0.11

0.54 0.09

-0.02 0.01

0.12 0.13

-0.07*** 0.02

-0.39*** 0.04

-0.25 0.11

-1.22* 0.65

-0.36* 0.06

0.34** 0.05

B

0.24 0.14

0.07*** 0.01

0.98**

0.20

0.02***

0.82

0.35**

0.00

0.06

0.11

0.56*

0.21

1.67*** 0.10

-0.14

0.06

0.13

0.08***

0.80

0.15

0.01

0.21

0.00*** 0.04

0.84*** 0.06

0.33*** 0.17

-1.19 0.51

1.66*** 0.10

0.25 0.18

0.09

0.07**

0.74

0.00

0.81***

0.07

0.14

0.41**

1.25

1.68***

0.61

0.10

-0.34** 0.13

0.16

0.01

0.22

0.04/nItem 4 (17 pts.)

Use the Pruchno et al. (2018) study to answer the following questions. Be sure to be

thorough in your explanations.

A. What type of research design do the authors of the study use (experimental,

quasi-experimental, correlational, or descriptive)? How do you know? Explain. (2 pts.)

B. What is the target population in the Pruchno et al. (2018) study? Explain how you

arrived at your answer using the information about the ORANJ BOWL panel. (2 pts.)

C. Do the researchers use a probability or a non-probability sampling method? Explain your

answer and identify the sampling method used in your explanation. (2 pts.)

D. Is the sample representative of the target population? Explain. (3 pts.)

E. Is the sample a sufficient size, or is it underpowered or overpowered? Explain how you

know, including a comparison to an estimated sample size. (4 pts.)

Hint: This article is complex in terms of the analyses to be conducted. We will focus on

the main analyses, the GLMS (general linear regression models). It is okay if you are

unfamiliar with linear regression. Use the "Rule of Thumb" formula for regressions. See

below for a tip on the number of predictors. Be sure to state your estimate for the sample

size of the study! In other words, your response must include the following: (1) the rule of

thumb equation you used with the correct number of predictors inserted, (2) the

estimated minimum sample size, and (3) your decision about whether the sample size is

too large, adequate, or too small, based on comparison of estimate with actual sample

size.

F. Is the sample biased? Explain how you came to your conclusion. (4 pts)/nModule 3: Homework Assignment

30 pts.

Respond to the prompt(s) for each item below using complete sentences and clear writing. You

may single-space your work. A cover page or page numbers are not required. Cite and

reference only where indicated unless you utilize outside sources in a response.

Return to the assignment page when you are ready to submit your assignment.

**You will need to download the article below from the assignment page and use it for Item 4.

Pruchno et al. (2018)

Collaboration on this assignment is NOT allowed. Your work must be your own.

Item 1 (3 pts.)

Dr. Smith is conducting a study to examine the effects of work overload on stress. He

advertises his study in two large office buildings of more than 800 employees each. Two

hundred fifty-four people volunteer to participate, and Dr. Smith randomly selects 200 of these

volunteers for his sample. Is there a possibility that Dr. Smith's sample is biased? Explain in

detail (also be specific in terms of the type of bias).

Item 2 (5 pts.)

Dana and Dan are both conducting a study to examine the relationship between number of

pregnancies and level of cognitive decline in women over the age of 60. Dana randomly selects

a sample of 50 women over the age of 60 who are patients of a large neurology clinic and then

administers the Mini-Cog to assess their level of cognitive impairment. She also records the

number of pregnancies for each woman. Dan, on the other hand, randomly selects the health

records for 50 women over the age of 60 who have been patients of the large neurology clinic

within the past 10 years. The health records contain information about the women's cognitive

impairment level and number of pregnancies.

Who has the better approach for obtaining the sample? Explain in detail. Response must be

thorough and use specific terminology.

Item 3 (5 pts.)

A. What are at least two problems associated with a sample size that is too small? (2 pts.)

B. Why does increasing the sample size typically improve a study? (2 pts.)

C. What is the main problem associated with a sample size that is too large? (1 pt.)