Quantitative research (analyzing bivariate)

Question 1

What is bivariate analysis?

Answer 1

test the relationship between variables. Is there a link that exists or not between the variables?

Question 2

What are the types of differences between responses?

Answer 2

1. mathematical: numbers are different
2. statistical: statistically significant = difference is large enough to be unlikely to have occurred because of chance or sampling error
3. managerial: difference is important if results or numbers are sufficiently different

Question 3

What are the steps of the bivariate analysis process?

Answer 3

1. start form the research problem
2. identify the questions you cant to analyze and identify the variables related to each question
3. decide to conduct bivariate analysis
4. identify the measurement scales for each variable related to the question
5. choose the analysis technique (cross-tabulations, comparisons of means, correlation)
6. conduct the statistical test (chi-square, T-tes, F-test)

Question 4

What are the 4 analysis techniques for bivariate analysis?

Answer 4

1. cross tabulations -> comparing frequencies between variables
2. comparison of means & ANOVA -> comparing averages
3. correlation -> strength of a linear relationship
4. regression -> dependency between variables

Question 5

When should you use a chi-square test?

Answer 5

cross tabulation

Question 6

When should you use a T-tes

Answer 6

comparison of means

Question 7

when should you use an F-test

Answer 7

correlation or regression

Question 8

what should be the value of p to reject H0

Answer 8

<=0.05 or 0.025 (T-tes)

Question 9

If p = 0.07, can you reject H0?

Answer 9

No

Question 10

What are the steps to perform a statistical test?

Answer 10

1. determine the appropriate analysis and test to perform
2. identify H0 et Ha
3. calculate the statistic and p-value to test Ho
4. decision (reject or no)
5. calculate the strenght and direction of the relationship (if applicable)
6. interpret the result

Question 11

What should be the null hypothesis for cross tabulations?

Answer 11

there is no difference to X variable when Y is this or that

Question 12

What should be the null hypothesis for a comparision of means?

Answer 12

the means are the same for both variables

Question 13

When should you use anova instead of T-test?

Answer 13

when you have a metric varibale + a non metric one with >2 categories

Question 14

What should be the null hypothesis for correlation testing?

Answer 14

there is no relationship between the 2 variables

Question 15

What should be the null hypothesis of linear regression?

Answer 15

X has no impact on Y