Hypothesis Testing

Question 1

designed to detect significant differences: differences that did not occur by random chance; significance testing

Answer 1

Hypothesis testing

Question 2

“The difference is caused by random chance”
The H0 always states there is “no significant difference” (statistically significant correlation)
No difference in correlation relationship

Answer 2

Null Hypothesis - H0

Question 3

“The difference is real”
(H1) always contradicts the H0
There is a difference in correlation relationship

Answer 3

Alternative/Research Hypothesis - H1

Question 4

SPSS Rows (Y)

Answer 4

dependent variables

Question 5

SPSS columns (X)

Answer 5

independent variables

Question 6

rows/columns on the ends (totals)

Answer 6

marginal frequencies

Question 7

Combined table with two independent variables (one is a control)

Answer 7

trivariate table

Question 8

Process by which we determine whether our hypothesized relationship exists beyond a “reasonable doubt.”(usually p ≤.05 or p ≤.01 or p ≤.001 is “reasonable”)

Meaning: There is a 5% or 1% chance or .1% chance (p=probability) that we are making the wrong decision

(Anything above .05 is not statistically sigificant)

Answer 8

Hypothesis testing

Question 9

Hypothesis testing process involves …

Answer 9

trying to reject or fail to reject the null hypothesis in favor or support of the research hypothesis

(We NEVER prove or reject the research hypothesis)

Question 10

Criteria for rejecting null hypothesis

Answer 10

Is there a relationship between the two variables?

If yes, is the relationship statistically significant at a given level of p (≤.05)?

Use a TEST STATISTIC like Chi-Square and the p-value related to the probability of making an error in our conclusion (pattern = random, not real)