Chi-Square
Hierarchical Regression (Moderation)
Data Transformation
Standard Multiple Regression
100

To conduct a Chi-Square test, there MUST be a minimum of _________ in each category. 

5 cases for the expected frequency 

100

You are interested in examining if the relationship between exercise and depression can be strengthen by sleep pattern. You gather data from 36 patients and analyze if depressive symptoms score can be predicted by those two behaviors as well as by the interaction of those two behaviors. 

What is your outcome variable?

Depressive Symptoms score

100

Please name the four common data transformations. 

Sorting/Filtering Cases

Dummy Coding

Reversing Scoring

Computing a new variable

100

Standard multiple regression allows you to find ___________________________ for the predicted outcome. 

the best set of predictors / a set of predictors / multiple predictors 
200

Name the TYPE of Chi-Square Test that compares observed cases (N) to expected cases (N)

One Variable Chi-Square Test

200

What does the italicized portion of the hierarchical regression equation below represent: 

       Y^ = a (constant) + bX1 +bX2 + bX1X2 + e

Regression coefficient for the interaction term

200

This function allows you to exclude cases from your analysis without deleting them from the active dataset. What type of data transformation is this? 


Filtering/Sorting Cases

200

Please list the assumptions of a standard multiple regression.

•Linear relationships 

•Homoscedasticity 

•Independence of Error Terms 

•Normality of error terms 

300

The (1)_________________ statistic tells you whether it is a significant difference, while the (2)__________________ table allows you to see the proportions for each level of X at various levels of Y.  

(1) Pearson Chi-Square

(2) Crosstabs

300

You are interested in examining if the relationship between exercise and depression can be strengthen by sleep pattern. You gather data from 36 patients and analyze if depressive symptoms score can be predicted by those two behaviors as well as by the interaction of those two behaviors. 

What are your predictor variables? Which one would be considered the moderator?

Predictors: Sleep Pattern & Exercise

Moderator: Sleep Pattern

300

This function allows you convert categorical and scale variables into a simpler numeric form for regression. 

What type of data transformation is this? 

Please provide a scheme for the data transformation on the following variable: "Annual Income" ranges from $20k - $100k

Dummy Coding 

Example Scheme (can be any split):

0 = $20k - $49k

1 = $50k - $100k

300

Please describe a scenario in which a researcher interested in predicting anxiety would run a standard multiple regression. Identify the number of predictors you should have AND the name the most appropriate predictors you can think of for anxiety. 

Needs to list at least two concepts/variables like: 

Stress Level & Diet 


400

Please use your group's white board to write out the symbolic notation for results using the following values: 

Your two variables are X and Y.

X2 = 12.47

df = 3

N = 1003

p= 0.03

HINT: X2(...

 χ2 (3, N = 1003) = 12.47, p=.03.

400

In a hierarchical regression equation, what is the name of the value that represents the predicted outcome value when all other variables are "0"? 




CONSTANT

400

You are presented with two statements relating to the current state of a dataset and the expected. Please name the data transformation you would conduct to meet the expected.

  • Current State of Variable: Gender variable includes three levels: male, female, and non-binary app users
  • Expected State of Variable: Gender variable should only include female app users

Sorting/Filtering Cases

400

Please write the regression equation for a standard multiple regression that includes a set of three (3) predictors. 

Y^= A + βX+ βX+ βX3

500

Name ANY five (5) variables that would be appropriate in conducting a Chi-Square test. 

Any categorical variable, such as: 

Gender, Ethnicity, SES, Marital Status, Education level, Left-handed vs. right-handed, Neurotypical vs. ADHD...

500

You are being shown a Model Summary and Coefficients Table from SPSS. 

Using the table, please fill in the appropriate values and terms below:

The first predictor: _______________ was NOT significantly associated with How Far you think you will go in school as the outcome (b= ___, t=___, p= __). 

The second predictor: _____________ was NOT significantly associated with How Far you think you will go in school as the outcome (b= __, t= __, p=___). 

The results showed that the interaction term (b=__, t= ___ p= __) was also NOT significant in predicting How Far you think you will go in school as the outcome.  

The first predictor: Enjoy caring for children was NOT significantly associated with How Far you think you will go in school as the outcome (b= -.146, t= -1.645, p= .100). 

The second predictor: Mother fulfilling was NOT significantly associated with How Far you think you will go in school as the outcome (b= -.062, t= -.498, p= .619). 

The results showed that the interaction term (b= .039, t= 1.253 p=.210) was also NOT significant in predicting How Far you think you will go in school as the outcome.  

500

You are presented with two statements relating to the current state of a dataset and the expected. Please name the data transformation you would conduct to meet the expected.

  • Current: Five nominal items are a part of a satisfaction measure.
  • Expected: One scale variable that stands as a “total score” which includes all items on the satisfaction measure

Computing a new variable

500

You are being shown a Model Summary and Coefficients Table from SPSS. 

Using the table, please fill in the appropriate values and terms below:

A multiple regression was run to predict [insert dependent variable] from [insert predictor IV1], [insert predictor IV2], and [insert predictor IV3]. 

All variables significantly/did not significantly predict [insert dependent variable], F(#, #) = ##.##, p = #.##, R2 = .##.

 

A multiple regression was run to predict [Self Esteem] from [Household Income], [Close to Mom], and [Close to Dad]. 

All variables significantly predict [Self Esteem], F(3, 613) = 10.804, p < .001, R2 = .050.