2 Psychology Statistics 3010 Utah State University Exam 2

What is the broad concept of the two-sample t test?

See if the difference between the means is due to chance, based on the variability of each sample

Why do you need to know the df of your t test?

So you can compare it against the correct t distribution

Which is the null distribution for the two-sample t test?

The sampling distribution of the difference of the means, as approximated by the t distribution

What is the difference between a point estimate and an interval estimate?

A point estimate gives a single number to represent an unknown population parameter, and an interval estimate gives a range of numbers

Which of the following is a correct interpretation of a confidence interval?

We are 95% confident that the population parameter lies within the confidence interval

What is the relation between confidence intervals and null hypothesis testing?

For the correct alpha for the chosen C, we can reject the null if the null is not in the confidence interval

What are the key pieces of information needed to calculate confidence intervals?

The SE or SD, The critical value, The point estimate

Which assumption is always included?

Independent and random sampling

Which assumptions apply ONLY to methods comparing multiple variables (rather than only single variables)?

Homogeneity of variance

What is homogeneity of variance?

the variance (SD) of both populations is the same

When can statistics guarantee the null is 100% false?

Never

What is the difference between a Z-score for individuals and the Z-score for groups?

The denominator for individuals in the sample SD, and the denominator for groups is the SE

When should we use the one-sample Z test?

The sample is truly random and independent, When the population mean is known

Why do we calculate a group z-score for the one-sample Z test?

It tells us the probability of getting a certain mean, assuming the null is true

What is the null distribution?

The distribution of results (such as the mean, or difference in means) assuming that the null hypothesis is true

How is the critical value of the t statistic different from the critical value of the z statistic?

It changes based on sample size (i.e., the degrees of freedom), whereas the critical value of the z statistic stays the same

What is the relationship between a z test and a t test?

They both test the probability of your result, but one uses the population SD and the other estimates using the sample SD

What is power in statistics?

The ability (probability) of finding an effect when there really is one

What is the difference between significant and important?

Significant means NOT due to chance, imporant means the finding has real life meaning

Which of the following tells you how big the difference is?

 

Effect size, such as Cohen's d

What is the relationship between avoiding type I errors and power?

Inverted, as one goes up, the other goes down

What is one of the best ways to increase power?

Increase sample size

(In general) What two pieces of information do you need to calculate your degrees of freedom?

Sample size and how many population parameters you estimated

What is the null hypothesis?

The idea your results are due to chance

What does it mean to test the null hypothesis?

To check the probability of your result, assuming the null is true

What does it mean to reject the null hypothesis?

To conclude that "by chance" is the worse explanation

When do you reject the null hypothesis?

 

When the probability of your result occurring (if the null were true) is low enough

Why do we use the phrase: "fail to reject the null hypothesis"?

Because there could be an alternative explanation, but we don't have enough evidence to reject the null

What is a limitation of null hypothesis testing?

It cannot provide alternative explanations

What is a Type I error?

When we reject the null, even though it is true

What is a Type II error?

When we accept the null, even though it is false