Week 6

Question 1

Null hypothesis

Answer 1

Null hypothesis is a hypothesis against the research question, claiming that there is no difference in the result and the only difference observed are just noise or error

Question 2

P values & Null Hypothesis

Answer 2

P value < 0.05, reject hypothesis
P value > 0.05, accept hypothesis

Question 3

H0 hypothesis

Answer 3

H0 is a hypothesis against the research question, claiming there is no difference in result and differences observed is just noise
Eg (There is no effect of toothbrushing on the exam score)

Question 4

Ha hypothesis

Answer 4

The opposite of the null hypothesis, claiming there is a difference in the result
Eg (There is an effect of toothbrushing on the exam score)

Question 5

Type 1 error

Answer 5

Reject the null hypothesis when it is true (false-positive)

Question 6

Type 2 error

Answer 6

Not to reject the null hypothesis when it is false (false-negative)

Question 7

Chi-sqaure goodness-of-fit test

Answer 7

Proportions with more than two levels
One group
Nominal or Ordinal Variables
Eg (Dice rolling)

Question 8

Chi-square test of association

Answer 8

Comparing proportions across two or more groups. Groups are not related.
Nominal or Ordinal Variables
Summarized in a contingency table
Eg (Blood types, preference in car colour, vaccine)

Question 9

McNemar Test

Answer 9

Data points that are paired across two groups. Groups are related in some way.
Nominal or Ordinal Variables
Only works for yes or no questions, 2 outcomes.
Eg (nicotine patch & whether smoking before & after makes a difference)

Question 10

One-sample t-test

Answer 10

Comparing a measure with a fix value
Binomial or goodness-of-fit
Interval or Ratio Variables
Eg (Comparing VO2 max scores of 20 male students against published VO2 max norms)
Parametric

Question 11

Independent test

Answer 11

Comparing a measure across two groups
Interval or Ratio Variables
Chi-square of association
Variables not related to each other
Eg (Comparing exam marks for students in group A to student in group B)
Parametric

Question 12

Paired t-test

Answer 12

McNemar’s test
Interval or Ratio Variables
Variables related to each other
Eg (Comparing weight before & after COVID-19 lockdown)
Parametric

Question 13

One-tailed

Answer 13

Test to see if one mean is higher than another

Question 14

Two-tailed

Answer 14

Test to see if there is a difference between the means

Question 15

Welch’s t-test

Answer 15

Conducted when normality is checked, but data does not have equal variance (p < 0.05)
Two Groups, unpaired

Question 16

Normality (Shapiro-Wilk)

Answer 16

Sampling of the means is distributed normally
Central Limit Theorem

Question 17

Levene’s Equal Variance

Answer 17

Used between Independent and Welch Tests.
if p > 0.05, Independent test is used
if p < 0.05, Welch’s t-test is used

Question 18

Reporting Goodness-of-fit

Answer 18

X2(df) = X2 value, p=p value

Question 19

Reporting Test of Association

Answer 19

X2 (df, N value) = X2 value, p=p value

Question 20

Reporting T-statistic

Answer 20

t (df) = statistic value, p=p value

Question 21

Binomial test

Answer 21

Binomial Test is a statistical test that concerns a proportion observed in your data is different from a known proportion

Question 22

Confidence Intervals

Answer 22

Confidence intervals are often used to define in which true proportion may lie

Question 23

Benford’s Law

Answer 23

The frequency of first digits of naturally occurring numerical data follow a particular proportion