Topic 7

Question 1

Point Estimation

Answer 1

Provide a single best guess for the parameter (eg. using mean or max likelihood estimate) logisitic regression model

Question 2

Interval Estimation

Answer 2

Provides a single range of plausible values for the parameter (confidence intervals) linear regression

Question 3

Central Limit Theorem

Answer 3

When a sufficiently large number of samples drawn from indepdendent random variables, the mean of their distribution will be normal distribution

Question 4

Standard Error (SD of the sampling distribution)

Answer 4

Inversely proportional to the the root of the sample size: SE = σ / √n

Question 5

Confidence Interval

Answer 5

A plausible range of values for the population: Point Estimate +- (Critical Value x Standard Error)

Question 6

Critical Value / Critical Z-Score

Answer 6

Chosen to define the interval, eg. 1.96 for a 95% CI

Question 7

Margin of Error

Answer 7

z* x SE

Question 8

Null Hypothesis

Answer 8

Assuming that results are indepdendent and differences are due to chance (gender<->exam results)

Question 9

Alternative Hypothesis

Answer 9

Hypothesise that results aren’t independent and the differences reflect a real difference in the population