MK 4200 - exam 3

To conduct a "Paired t-test" in excel, you can use "t-test: two sample assuming unequal variance" in data analysis add-ins. T | F

False

Close-ended questions are relatively more difficult to code in general compared to open-ended questions. T | F

False

In cross tabulations, variables can be either nominal (categorical) or continuous. T | F

False

In dummy coding, for the M levels of the nominal variable considered, you create M+1 dummy variables. T | F

False

In simple tabulations, the sample is divided to understand how the variable of interest (DV) varies across different groups of another variable (IV). T | F

False

Correlation might be used to make predictions

false

You conduct the following hypothesis test at significant level 0.05. Ho: mean () = 5000 Ha: mean () > 5000 and you find that the one tailed p-value is 0.07 and two tailed p-value is 0.14. What is the probabilities of wrongly rejecting the null hypothesis when it is, in fact, true. a. 5% b. 7% c. 14% d. 95% e. 86%

b. 7%

Categorical IVs might be used directly in a regression model, but the continuous IVs might be dummy coded.

false

Correlation is the statistical measure that indicates the extent to which two (continuous/numerical) variables move together.

true

Data editing corresponds to identifying problems in the data. T | F

true

Descriptive statistics used to summarize the variables of interest in the data. T | F

true

Dummy coding is the only way to use nominal (categorical) variables in regression models. T | F

true

In coding close-ended questions, we generally assign numerical values to the response categories. T | F

true

Null hypothesis refers to cases such as something is not present, there is no effect, no impact, no relationship, or there is no difference between different groups. T | F

true

Omissions, ambiguities, interviewer errors and inconsistencies are the commonly observed problems in the data. T | F

true

Regression generates a function linking the DV to the IV(s).

true

Simple tabulations can be used to document frequencies and percentages of a nominal (categorical) variable. T | F

true