Chapter 8 Flashcards
What do the critical values and region of rejection marked mean on a null distribution graph?
the specific range of values on a statistical distribution where, if your calculated test statistic falls within that range, you would reject the null hypothesis
When do you use a one-sample z-test?
when you want to compare a sample mean to a population mean
What information do you need to know to calculate a one-sample z-test?
Need to know the population standard deviation
What is the null hypothesis and alternate hypothesis equations for the on sample z test?
Null: H0: µS = µC
Alternate: HA: µS ≠ µC
When do you use Direction (or one-tailed) hypothesis?
Only use it when you are interested in one direction (how the test scores improve or not)
When do you use non-directional (or two-tailed) hypotheses?
Differences in either direction are interesting MOST EXTREME 5%
How do you write the null and alternate hypothesis for Direction (one-tailed) Null hypothesis POSITIVE:
AND
Direction (one-tailed) Alternate hypothesis POSITIVE
Direction (one-tailed) Null hypothesis POSITIVE (higher): H0: µS ≤ µC
Direction (one-tailed) Alternate hypothesis POSITIVE(higher): HA: µS > µC
How do you write the null and alternate hypothesis for Direction (one-tailed) Null hypothesis NEGATIVE:
AND
Direction (one-tailed alternate hypothesis NEGATIVE:
Direction (one-tailed) Null hypothesis NEGATIVE (lower): H0: µS ≥ µC
Direction (one-tailed alternate hypothesis NEGATIVE (lower): HA: µS < µC
How do you write the null and alternate hypothesis for non-directional (or two-tailed) Null hypothesis:
AND
non-directional (or two-tailed) Alternate hypothesis:
non-directional (or two-tailed) Null hypothesis: H0: µS = µC
non-directional (or two-tailed) Alternate hypothesis: HA: µS ≠ µC
What is the critical z value for Non-directional two-tailed test?
-1.96 and +1.96
What is the critical z value for Directional one-tailed test positive test?
+1.645
What is the critical z value for Directional one-tailed test negative test?
-1.645
What happens if the critical value of z for the Directional one-tailed negative test is lower or higher than -1.645?
Lower: you would reject the null hypothesis
Higher: nothing would happen it doesn’t matter you wouldn’t reject it
What happens if the critical value of z for the Directional one-tailed positive test is lower or higher than +1.645?
Lower: Nothing would happen it doesn’t matter you wouldn’t reject it
Higher: Then you would reject the null hypothesis
What happens if the critical value of z for the Non-directional two-tailed test is more lower than -1.96 or higher than +1.96?
Lower than -1.96: You would reject the null hypothesis
Inbetween -1.96 and +1.96: It doesn’t matter you wouldn’t reject it
Higher than +1.96: You would reject the null hypothesis
Does the sample size affect Cohen’s d?
NO IT DOES NOT
What happens to the groups if d increases and decreases?
Increases: the means are farther apart
Decreases: the means are closer together
What does it mean when d is positive, negative and zero?
Positive: The first group’s mean is higher than the second groups mean (sample mean is bigger than population mean)
Negative: The first group’s mean is lower than the second groups mean (the sample mean is smaller than the population mean)
Zero: The means are the same, there is no difference
What happens to the p value when the sample size (n) increases?
the p value gets smaller
When you want to falsify the null hypothesis (reject it) what is the best way of doing that?
By increasing the sample size (n)
What happens to the p value if the effect sizes (d) are the same and the sample size (n) gets larger?
the p value gets smaller
What happens to the p value if the effect sizes (d) are the same and the sample size (n) gets smaller?
the p value will get bigger
What happens to the p values if the sample sizes (n) are the same size and the effect sizes (d) are getting larger?
p values get smaller
What happens to the p value if the sample sizes (n) are the same size and the effect sizes (d) are getting smaller?
p values get bigger
What is the meaning of statistical significance?
When the calculated value for an inferential test goes in to the critical region and the null hypothesis is rejected. The results are not likely to have arisen by chance. (p values is lower than the alpha)
What are the most common value for alpha?
0.01, 0.05 and 0.10
What is the most common value for alpha out of the three? 0.01, 0.05 and 0.10
0.05
How do you know when to reject the null hypothesis based on the alpha value and p value?
You reject the null hypothesis when the p value is lower than the alpha value
What is another word/phrase for type 1 and type 2 errors?
- Type 1 error: it is a false positive
- Type 2 error: it is a false negative
How do you determine if data is a type 1 error or a type 2 error?
Type 1: When the sample effect says it is statistically significance BUT the population effect says that it is NOT statistically significant
Type 2: When the sample effect says it is NOT statistically significance BUT the population effect says that IT IS statistically significant
What happens if the population and sample both say the data is statistically significant (both get an effect)?
It is more accurate and it is a true positive
What happens if the population and sample both say the data is NOT statistically significant (both DO NOT get an effect)?
It is more accurate and it is a true negative
What can be concluded when the null hypothesis is rejected?
That there was a big effect (difference between the groups) in that data that wasn’t by chance
What can be concluded when the null hypothesis it is not rejected?
There is not enough evidence to conclude that there isn’t anything going on or not a big enough effect