hypothesis testing

Question 1

what is a null hypothesis ?

Answer 1

it is a statement that claims that there is no association between two variables

Question 2

are hypothesis made on populations or samples ?

Answer 2

a hypothesis can only be made on a population parameter

Question 3

what are the errors associated with the judgement over the null hypothesis ?

Answer 3

probability of a type 1 error
probability of a type 2 error
power of the study

Question 4

what is a type 1 error ?

Answer 4

the probability of rejecting the true null hypothesis

Question 5

what is a type 2 error ?

Answer 5

the probability of accepting a false null hypothesis

Question 6

what is the power of the study ?

Answer 6

probability of not making a type 2 error

Question 7

how is the power calculated ?

Answer 7

1-B (type 2 error )

Question 8

what are the types of variables ?

Answer 8

quantitative and qualitative

Question 9

what are the types of quantitative variables ?

Answer 9

discrete

continuous

Question 10

what are the types of qualitative variables ?

Answer 10

nominal
ordinal
binary

Question 11

if we have two qualitative variables what type of statistical study is used ?

Answer 11

chi-squared test

Question 12

if we have a qualitative variable and a quantitative variable what type of statistical test is used ?

Answer 12

only 2 groups : independent t test

more than 2 groups : anova

Question 13

if we have 2 quantitative variables what type of statistical test is used ?

Answer 13

Pearson coloration and we can get an r value

Question 14

if we have a study that includes pre and post treatment what is the statistical test of choice ?

Answer 14

with quantitative variables: paired sample t test

with qualitative variables : McNemmars test

Question 15

what are the disadvantages of using a t test ?

Answer 15

can only be used to compare 2 variables cannot make comparisons among more than 2 groups

Question 16

how can we draw a conclusion based on a Pearson coloration ?

Answer 16

1. p=0 the population correlation coefficient is 0, there is no association
2. p is not equal to 0 , the population correlation coefficient is not 0 a nonzero correlation could exist

Question 17

what does a small p value indicate ?

Answer 17

indicates strong evidence against the null hypothesis , so you reject the null hypothesis

Question 18

what does a large p value indicate ?

Answer 18

indicates weak evidence against the null hypothesis , so you accept null hypothesis

Question 19

quantative vs qualitative in 2 groups only ?

Answer 19

independant t test

Question 20

2 qualitatives ?

Answer 20

chi square test

Question 21

2 yes and nos ?

Answer 21

chi square test