Critical Thinking - Lecture Twenty-Four

Question 1

What are p-values?

Answer 1

P-values are the probability of getting study estimates )or a study estimate further from the null), when there is really no association, because of sampling error (chance)

Question 2

What logic do p-values use?

Answer 2

The logic of hypothesis testing

Question 3

What are the ‘two players’ involved in the association vs no association table?

Answer 3

The null hypothesis and the alternative hypothesis

Question 4

The null hypothesis (Ho)

Answer 4

Really no association in the population. Parameter equals null value

Question 5

The alternative hypothesis (Ha)

Answer 5

Really is an association in the population. Parameter does not equal null value.

Question 6

Ratio measures and difference measures of Ho

Answer 6

Ratio measures (RR, OR) = 1
Difference measures (RD) = 0

Question 7

Ratio measures and difference measures of Ha

Answer 7

Ratio measures (RR, OR) ≠ 1
Difference measures (RD) ≠ 0

Question 8

Threshold for statistical significance

Answer 8

5% (0.05)

Question 9

When p < 0.05

Answer 9

We reject Ho and accept Ha; association is ‘statistically significant’

Question 10

When p > 0.05

Answer 10

We fail to reject Ho and reject Ha; association is ‘not statistically significant’

Question 11

Fundamental concept 4

Answer 11

Probability of getting study estimate (or an estimate further from the null) when there is really no association because of sampling error (chance)

Question 12

Type-II errors

Answer 12

Incorrectly fail to reject Ho when should have (p should have been < 0.05 but got > 0.05)

Question 13

Why do type-II errors typically occur?

Answer 13

Few people in the study

Question 14

P-values and 95% confidence intervals

Answer 14

You can see whether a p-value is greater or less than 0.05 with a 95% confidence interval

Question 15

Why are p-values problematic?

Answer 15

Arbitrary threshold, only about Ho and nothing about importance

Question 16

Arbitrary threshold

Answer 16

Threshold is arbitrary and artificial

Question 17

Only about Ho

Answer 17

Just give evidence about consistency with the null hypothesis and doesn’t say anything about precision (best presented with confidence intervals)

Question 18

Nothing about importance

Answer 18

Statistical significance is not clinical significance and doesn’t say anything about whether the results are valid, useful or correct
The absence of a statistically significant association is not evidence of absence of a real association