Inferential Statistics: Uncertainty

Question 1

Inferential statistics?

Answer 1

Using sample data to make an inferences or conclusions on a population

Question 2

Hypothesis testing?

Answer 2

Making decisions based on experimental data. Forming statistical method of assessing between two possible realities

Question 3

Which hypothesis do you use for biomedical reserach?

Answer 3

Null hypothesis

Question 4

What are the two possibilities of null hypothesis?

Answer 4

The data are either consistent with the null hypothesis of no effect.
Or
the data are not consistent with the null hypothesis of no effect

Question 5

The p-value?

Answer 5

P-value is the level of marginal significance within a statistical hypothesis test, representing the probability of the occurrence of a given event.

The p-value is the probability that the null hypothesis is true. (1 – the p-value) is the probability that the alternative hypothesis is true. A low p-value shows that the results are replicable. A low p-value shows that the effect is large or that the result is of major theoretical, clinical or practical importance

Question 6

Null-hypothesis?

Answer 6

(in a statistical test) the hypothesis that there is no significant difference between specified populations, any observed difference being due to sampling or experimental error.

Question 7

Why is it called the null-hypothesis?

Answer 7

A scientific hypothesis is a statement of what theresearcher expects to find upon conducting a study. A statistical hypothesis, however, is a statement of what the statisticianexpects NOT to find. For this reason it is called a NULL hypothesis.

Question 8

p=1

Answer 8

There was no effect. Same outcome for groups

Question 9

p<1

Answer 9

There was no effect. Different outcome to exposure for groups.

Question 10

p<0.05

Answer 10

Null hypothesis is not true. Making decisions based on the p-value

Question 11

p=0.01

Answer 11

Evidence against the null hypothesis than p=1

Question 12

What does a decrease in p value mean?

Answer 12

Decrease in p-value and that increases evidence false, since accumulating against the null hypothesis

NO true effect. Null hypothesis can be

Question 13

What strongly influences the p-value?

Answer 13

Strongly influenced by sample size

Question 14

P-value and effect size?

Answer 14

P-value is not measure of effect size

Question 15

P-value and the importance of the finding

Answer 15

P-value is not a measure of the importance of the finding

Question 16

P-value and the null hypothesis

Answer 16

P-value is not the probability that the null hypothesis true. We do assume that the the null hypothesis is true.

Question 17

P-value in the alternative hypothesis ?

Answer 17

P-value is not the probability that the alternative hypothesis is true

Question 18

General Linear Model?

Answer 18

The term “general” linear model (GLM) usually refers to conventional linear regression models for a continuous response variable given continuous and/or categorical predictors. It includes multiple linear regression, as well as ANOVA and ANCOVA (with fixed effects only).

Question 19

General Linear model includes what?

Answer 19

One dependent/response variable
(measured on an numeric scale)

One or more independent/explanatory variables
(measured on categorical or numeric scale)

Question 20

Numeric Variable vs Numeric Variable Features?

Answer 20

1. Linear Regression
2. Describes the relationship between X & Y variables
3. Null hypothesis is that the regression coefficient is zero

Question 21

What does it mean when the regression coefficient is zero?

Answer 21

A value of zero indicates that there is no relationship between the two variables.

Question 22

Numeric Variable vs Categorical variable Features?

Answer 22

1. Special case=two categories
2. Special case=three or more categories
3. Null hypothesis is that the difference between groups is zero

Question 23

T-test?

Answer 23

A t test is a statistical test that is used to compare the means of two groups. It is often used in hypothesis testing to determine whether a process or treatment actually has an effect on the population of interest, or whether two groups are different from one another.

Question 24

Paired t-test?

Answer 24

Person is exposed to two intervention treatments

Question 25

Unpaired t-test?

Answer 25

One person in the group is offer one intervention/2 intervention

Question 26

When do we the t-test?

Answer 26

When we have two categories

Question 27

When do we the ANOVA?

Answer 27

When we have three or more categories.

Also consists of repeated measures of the same intervention on the same person

Question 28

What is probability threshold?

Answer 28

The decision for converting a predicted probability or scoring into a class label is governed by a parameter referred to as the “decision threshold,” “discrimination threshold,” or simply the “threshold.”

Question 29

Two categorical variables null hypothesis?

Answer 29

Null hypothesis is that there is no relationship between the rows and
columns in a contingency table (they are independent)