Week 7 - Sampling Distributions Flashcards

1
Q

Sample descriptive statistics provide an estimate of what?

A

The population parameter

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

What is statistical inference?

A

Being able to infer and generalize from a sample to a larger population

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

Fixed means…

A

If you were to sample everyone it would be the same mean and SD

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

What is the difference between what sampling and population distributions show?

population: Spread
sampling: Variation

A

Population distributions: the spread of the variable of interest across individuals in the target population
Sampling distributions: show how the estimate of the population mean varies between samples if the experiment was repeated and the mean was recalculated each time

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

As sample size increases, what happens to the data?

A

The data becomes more normally distributed

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

How does the increase in the n value affect the distribution of the mean?

A

The larger n is, the closer the sample mean matches the population mean

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

What are the properties of sampling distribution?

A
  1. The mean of the sampling distribution is equal to the sampling and population mean
  2. SD of the sampling distribution is equal to the SD of distribution mean and the standard error of the mean
  3. The shape of he sampling distribution is a normal bell curve and as sample size increases, approximation to the normal distribution does too (even if the population distribution is not bell-shaped)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the central limit theorem? What n value is considered normally distributed for sampling distributions based on the mean?

A

When n => 30 for sampling distributions based on the mean, the data is considered normally distributed

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

As sample size increases, what occurs to the sampling distribution?

A

Variability in the mean measurements decreases; standard error (SE) decreases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the 95% confidence interval?

A

If we were to conduct the experiment 100 times, 95 times out of the 100, the value would fall within the 95% confidence interval range.

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

What are parametric vs non-parametric tests?

A

Parametric tests assume the data is normally distributed (t-tests, ANOVA) while non-parametric tests are data that do not follow a normal distribution.

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

What is the calculation to determine the 95% CI for a single population when the population SD is known?

A

Lower limit: mean - 1.96 (SE)
Upper limit: mean + 1.96 (SE)

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

What is the calculation to determine the 95% CI for a single population when the population SD is not known?

A

Xu = m + tu x SE
XL = m + tL x SE

Tlower and Tupper are standardized test scored found using the t-distribution table

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

What does the t-distribution look like?

A

The shape varies depending on sample size yet is still symmetric, bell-shaped, and centered on mean = 0.
The larger the df, the more the sample SD approximates the population SD, and the shape approximates the normal distribution.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

How do you calculate the degrees of freedom for t-distribution?

A

df = n - 1

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

What is the difference between 1- vs 2-tailed tests?

A

One-tailed: there is a specific direction (question example: is a value larger or smaller)
Two-tailed: no specific direction (question example: is the value different)

16
Q

When do you use the general formula for calculating the 95% CI?

A

If you have the population standard deviation
If the study population is equal to or greater than n=30

If not you use the t-distribution formula

17
Q

What does a p-value tell you?

A

Tells you if the effect or difference is significant where values closer to zero are not likely due to chance and values closer to 1 are likely due to chance (0.05 cutoff)