Week 2

Question 1

What is the Standard Error?

Answer 1

The amount of standardised ‘deviation’ between the population and the sample

Question 2

Explain the effect/error equation

Answer 2

If the error is high, a large effect is needed

If the value comes out as less than 1, this indicates that there is no effect.

Question 3

Explain how variance is calculated

Answer 3

Calculated by determining how much each score differs from the mean average
Then squaring each value
And adding them up - SUM OF SQUARES
Then divide by the number of scores

Question 4

What is the mean square?

Answer 4

The division of the sum of squares by N(-1)

Gives the estimate variance in the population

Question 5

What are the different things error bars could represent?

Answer 5

1) Standard Error
2) Standard Deviation
3) 95% Confidence Intervals

Question 6

What do 95% confidence intervals assume?

Answer 6

That data is normally distributed and takes into account the SE
In a normal distribution 95% of the data falls up to 2SDs away from the mean
1.96 (2SD) x SE
“We are 95% confident that the mean in the population will fall between ___ and ___”

Question 7

What does the 95% confidence interval indicate?

Answer 7

How much overlap we might have between 2 groups in the population.
If the amount of overlap in your 95% CI is large it is less likely that you will find an effect in your sample.

Question 8

How is the t value calculated?

Answer 8

mean 1 - mean 2 / SE of the differences

Question 9

How can bias in sampling be reduced?

Answer 9

By randomly assigning PPs to groups/conditions