Chapter 7- Hypothesis Testing Flashcards

1
Q

What is a z-test?

A

A z test is a hypothesis test which we compaere data from one sample to a population for which we already know the means and the standard deviation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

How do you calculate a z score?

A

A z score is calcuated by subtracting the mean fromn obersvationv and dividing it by the standard deviation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the 3 types of distribution and are they theoretical or observed?

A

Population Distribution is theoretrical; Sample distribution is observed; Sampling distribution is theoretical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are three ways to describe the same score within a normal distribution?

A

The three ways to describe the same score within a normal distribution is a raw score, z score, and percentile rankings.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are assumptions?

A

Assumptions are the characteristics that we ideally require the population to meet before running an inferential test to make sure our inferences are correct

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are parametric tests?

A

Parametric tests are statistical analyses based on a set of assumptions about the population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are non-parametric tests?

A

Non-parametric tests are statistical analyses that are not bases on a set of assumptions about the population. These tests are used with assumptions are violated.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are 3 assumptions for parametric tests?

A
  1. We assume the dependent variable is assessed using a scale measure (interval or ratio)
  2. We assume the participants are randomly selected and independent
  3. The population of interst must be approximately normal.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What are robust hypothesis?

A

Robust hypothesis tests are thosxe that produce fairly accurare results even when the data suggests the population might not meet some of the assumptions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What assumption is usually violated?

A

Random and independent sampling because convenience samples are used.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What assumption is usually met?

A

Scale measure - interval or ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What assumption is usually needed?

A

Population distribution because we want the sampling distribution of the means to be normal. If the pop is normally distributed, sampling distribution will be normally distributed or if we sue N>30 then can invoke Central Limit Theorm

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are the 6 steps of hypothesis testing?

A
  1. Identify the population distrtibution, sampling distribution, inferential test and check assumptions
  2. State null (H0) and alternative hypothesis (H1)
  3. State characteristicss of null (sampling distribution) (Mm and Om) standard error
  4. Determine critical values or cut off points. Under null hypothesis our observed results occur less than 5% of time. Percentiles can be expressed as probabilities– p-level or p-value; z test critical regions, one tailedz>1.65 reject the null
  5. Calculate teh test statistic
  6. Make a decision ( reject null hypothesis-statitically signifigant result– or fail to reject
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Define statistically signifigant

A

Statistically signifigant is usually when the data differs from what we would expect by chance, if there were, in fact no actually difference. This does not mean that it is more important or meaningful. A small difference could be statistically signifigant without indicating anything important

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is a one tailed test

A

A one tailed test is a hypothesis test which the research hypothesis is directional positioning a mean decrease or increase in the dependent variable but not both as a result of the independent variable. This is rarely seen in research unless the researcher is absolutely certain that the results cannot go in the opposite direction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is a two tailed test?

A

A two tailed test is a hypothesis test in which the research hypothesis does not indicate a directon of the mean difference or change in the independent variable but indicates there will be a mean difference.