Chapter 8- Confidence Intervals, Effect Size and Power Flashcards Preview

Chapter 1 Statistics > Chapter 8- Confidence Intervals, Effect Size and Power > Flashcards

Flashcards in Chapter 8- Confidence Intervals, Effect Size and Power Deck (15):
1

What is a point estimate?

A point estimate is a sample statistic that is just one number used as an estimate of the populaton parameter

2

What is an interval estimate?

An interval estimate is a sample statistic that provides a range of plausible values for the populaton parameter

3

What is a confidence interval?

A confidence interval is an interval based on the sample statistic that includes the population mean a certain percentage of the time, if we were to sample from the same population repeatedly (95 percent of the time),

4

What is effect size?

Effect size indicates the size of a difference and is unaffected by sample size. It tells how much two populations DO NOT overlap. The less the overlap, the bigger the effect size.

5

What are two ways the effect size can be decreased?

The two ways the effect size can be decreased is a) if their means are farther apart, b) variation within populatoin is smaller

6

To fairly compare distributions, what populations should be we look at?

To fairly compare distributions, we should look at population distributions because the bigger sample will create a skinnier distribution

7

What happens when the sample size increases?

When the sample size increases, the test statistic becomes more extreme and it becomes easier to reject the null hypothesis

8

Effect sizes are calculated with respect to _____

Effect sizes are calculated with respect to scores rather than means so are not congruent on sample size

9

What is Cohen's d?

Cohen's D is a measure of effect size that compares the difference between means in standard deviation units of the population

10

What are the rule of thumb effect sizes

0.2 small, 0.5medium and 0.8 large

11

How is Cohen's d calculated?

Cohen's d is calculated by observed mean- means divided by SD

12

What is Power?

Power is the probability that we will reject the null hypothesis , if the null hypothesis is false. In other words, our likelihood that we will detect an effect if its really there

13

When is power calculated?

Power is ideally calculated before the study is run to help determine how many participants to collect in order too detect an effect

14

Ideally what percentage of power do you want?

About 80

15

What are 5 ways to increase Power?

The five ways to increase power is 1) increase alpha (cut off value- rarely used), 2) Used one tailed test 3) increase sample size 4) increase effect size 5) decrease standard deviation