Lecture 5 - effect estimation

Question 1

what is preferably to using p values

Answer 1

emphasis on size and precision rather than p values

Question 2

what is the aim of a hypothesis test?

Answer 2

provides a frame work to determine the strength of the evidence provided by the data

Question 3

what is the null hypothesis?(h0)

Answer 3

specifies properties of an assumed population characteristic

Question 4

what is the alternate hypothesis? (h1)

Answer 4

outlines a contradictory statement from the null hypothesis

Question 5

when would you use a two-tailed test

Answer 5

testing if calcuated value is above or below what it is expected to be

Question 6

when would you use a one-tailed test

Answer 6

testing if the calculated value is ONLY below or ONLY above the expected

Question 7

what is the default position?

Answer 7

assuming the null hypothesis is true

Question 8

what are the steps in hypothesis testing?

Answer 8

Determining the Two Hypotheses
Computing the Sampling Distribution
Collecting and Summarising the Data(calculating the observed test statistic)
Determining How Unlikely the Test Statistic is if the Null Hypothesis is True (calculating the P-value)
Making a Decision/Conclusion(based on the P-value, is the result statistically significant?)

Question 9

what is the p-value?

Answer 9

probability of observing data as extreme or more extreme than in a sample, assuming that the null hypothesis is true

Question 10

what does a small p value suggest?

Answer 10

small p value suggests that the observed data is unlikely to occur if the null hypothesis is true

Question 11

what will the null hypothesis usually be phrased as ?

Answer 11

no change / no relationship / no difference

Question 12

what will the alternate hypothesis usually be phrased as ?

Answer 12

change present / there is a relationship / there is a difference

Question 13

when would you reject the null hypothesis

Answer 13

p value < 0.05 and conclude that a statistically significant relationship exists

Question 14

what is the significance level?

Answer 14

cut off for the p-value

Question 15

what is a type I decision error?

Answer 15

occurs we reject the null hypothesis but infact the null is true
- the probability of this occuring is equal to the cut off for the p value

Question 16

what is a type II decision error?

Answer 16

rejecting the alternate hypothesis when the alternate hypothesis is true
denoted by beta

Question 17

what does the chance of an error depend on?

Answer 17

sample size
magnitude of true relationship
cut off for the p-value

Question 18

what is the power of a test?

Answer 18

probability that the sample we collect will lead us to reject the null hypothesis when the alternative hypothesis is true
probability of not making a type II error –> 1-B

Question 19

what is the recommended power and how can it be increased?

Answer 19

80-90%

increased by increasing the sample size

Question 20

what should be considered alongside the p-value

Answer 20

size (strength)
precision ( confidence intervals )
quality of research design
confounding variables

Question 21

what does the chi-squared statistic measure?

Answer 21

magnitude of the difference between the sample observations and the calculated expectations

Question 22

what do chi-squared values suggest

Answer 22

If expectations in the population are the same, then the Chi-squared tends to be small (near 0)
If expectations in the population are different, then the Chi-squared tends to be large

Question 23

what is the critical value for 2x2 table?

Answer 23

3.84

a value greater than this suggests a statistically significant relationship

Question 24

when is the fisher’s exact test applied?

Answer 24

if there are any expected values <5

more conservative

Question 25

what does the Chi-squared statistic show?

Answer 25

whether or not there is a statistical relationship between two categorical variables

Question 26

what does the chi-squared statistic not tell you?

Answer 26

the direction of association

RR / OR can identify this

Question 27

why are 95% CI more informative than a test of significance ?

Answer 27

they stipulate the level of precision of the sample estimate of the RR

Question 28

what are two key conclusions regarding the 95% CI of the RR

Answer 28

if it includes 1 it is not statistically significant

if it excludes 1 it is statistically significant

Question 29

what is the mcnemars test

Answer 29

Chi-squared test for matched samples

• measurement of the same individuals at different time points
• chi squared would ignore the correlation between individuals

Question 30

what are the t/z test used for?

Answer 30

continuous data

Question 31

what is h0 and h1 for a single mean?

Answer 31

h0 = population mean equals a certain value
h1= population mean does not equal a certain value

Question 32

what test can you apply with > 30 observations

Answer 32

z test

no assumptions

Question 33

what test can you apply < 30 observations and what are the assumptions

Answer 33

t-test
sample was selected randomly
must be taken from a normally distributed population

Question 34

what happens when you have an independent sample for two means in terms of the hypothesis?

Answer 34

h0= population mean in sample 1 will equal the sample of 2