Assessing Normality Flashcards

1
Q

What is the Kolmogorov-Smirnov test used for?

A

Used for large datasets (greater than or equal to 2000)

Also known as K-S Lilliefors, it is more appropriate for extremely large data sets.

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

What is the Shapiro-Wilk test used for?

A

Used for small datasets (less than 2000)

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

What are the rules of thumb for assessing normality using skewness and kurtosis?

A

If kurtosis and skewness are not between -2 and +2, correct the data before applying tests that assume normality. Some authors use -1 to +1 as a stricter criterion.

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

What does a large ratio of skewness to its standard error indicate?

A

Indicates departure from symmetry.

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

What is the Kolmogorov-Smirnov statistic known for?

A

Has very high power, especially with large sample sizes.

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

What does a kurtosis value less than 0 indicate?

A

Platykurtosis (flatter distribution)

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

What does a kurtosis value greater than 0 indicate?

A

Leptokurtosis (more peaked distribution)

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

What is skewness?

A

The lack of symmetry in a distribution.

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

What does a skewness value of zero indicate?

A

A normal distribution.

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

What are the possible interpretations of negative and positive skewness?

A
  • Negative skewness indicates data skewed left
  • Positive skewness indicates data skewed right
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is kurtosis a measure of?

A

Whether the data are peaked or flat relative to a normal distribution.

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

How does SPSS define kurtosis?

A

SPSS computes ‘excess kurtosis’, adjusting the standard normal distribution to have kurtosis of zero.

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

What does a kurtosis value of 3 indicate?

A

It indicates the kurtosis for a normal distribution.

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

What does a Q-Q plot assess?

A

Determines if data sets come from populations with a common distribution.

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

What indicates a normal distribution in a Q-Q plot?

A

Points clustering closely around a straight line.

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

What is the difference between numerical and graphical methods for assessing normality?

A
  • Numerical methods: Objective, based on statistical tests
  • Graphical methods: Subjective, based on plots/charts/graphs
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is the purpose of assessing normality?

A

To determine if data satisfy assumptions for normality in statistical tests.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What happens if skewness and kurtosis values tend toward 0?

A

The distribution approximates a normal distribution.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What are the key properties of the standard normal distribution?

A
  • Symmetric about the mean
  • Mean, median, and mode are the same
  • Asymptotic behavior at extremes
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What does a P-P plot assess?

A

Plots cumulative proportions against those of the test distribution.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What does a negative skew indicate on a Q-Q plot?

A

An upward curve.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What does a positive skew indicate on a Q-Q plot?

A

A downward curve.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is the main takeaway regarding normality tests?

A

Both numerical and graphical methods require judgment to conclude normality.

24
Q

What does a leptokurtic distribution indicate?

A

More peaked than a normal distribution.

25
Q

What does a platykurtic distribution indicate?

A

Flatter than a normal distribution.

26
Q

What is the formula for skewness in univariate data?

A

Skewness = (mean - median) / standard deviation

27
Q

What is the formula for kurtosis in univariate data?

A

Kurtosis = [N(N+1) / (N-1)(N-2)(N-3)] * Σ[(xi - mean) / standard deviation]^4 - [3(N-1)^2 / (N-2)(N-3)]

28
Q

What is the primary function of the Q-Q plot?

A

To visually assess whether two data sets come from the same distribution.

29
Q

What is the significance of the area beneath the curve of the standard normal distribution?

A

Corresponds to probabilities (total area equals 1).

30
Q

What does a Detrended Q-Q plot show?

A

Differences between observed and expected values of a normal distribution.

31
Q

What is the outcome of a Q-Q plot that deviates from normality?

A

Points will not lie along the straight line.

32
Q

What is the purpose of assessing normality in biostatistics?

A

To determine if data follows a normal distribution, which is essential for many statistical tests.

33
Q

True or False: A normal distribution is characterized by a symmetric bell-shaped curve.

34
Q

What graphical method can be used to assess normality?

A

Q-Q plots (quantile-quantile plots).

35
Q

Fill in the blank: The _____ test is commonly used to test for normality.

A

Shapiro-Wilk

36
Q

What does a p-value less than 0.05 in a normality test indicate?

A

It suggests that the data significantly deviates from a normal distribution.

37
Q

Which of the following is NOT a method to assess normality? A) Histogram B) Shapiro-Wilk test C) ANOVA D) Q-Q plot

38
Q

What is the central limit theorem’s relevance to normality?

A

It states that the distribution of sample means will approximate a normal distribution as sample size increases, regardless of the population’s distribution.

39
Q

True or False: Skewness and kurtosis are measures that can indicate the normality of a dataset.

40
Q

What is skewness?

A

A measure of the asymmetry of the probability distribution of a real-valued random variable.

41
Q

What does a skewness value of 0 indicate?

A

The data is perfectly symmetrical.

42
Q

Fill in the blank: A kurtosis value greater than 3 indicates a distribution that is _____ than normal.

A

more peaked

43
Q

What is the range of values for skewness in a dataset?

A

Skewness can range from negative infinity to positive infinity.

44
Q

Why is normality important for parametric tests?

A

Many parametric tests assume that the data follows a normal distribution, affecting the validity of the results.

45
Q

True or False: Non-parametric tests do not require the assumption of normality.

46
Q

What is a common graphical representation used to visually assess normality?

A

Histogram.

47
Q

What is the implication of a right-skewed distribution?

A

It indicates that the tail on the right side is longer or fatter than the left side.

48
Q

What is the implication of a left-skewed distribution?

A

It indicates that the tail on the left side is longer or fatter than the right side.

49
Q

Fill in the blank: The _____ test is used to check for normality when sample sizes are small.

A

Shapiro-Wilk

50
Q

What does a Q-Q plot compare?

A

The quantiles of the sample data against the quantiles of a normal distribution.

51
Q

True or False: A Q-Q plot that forms a straight line indicates that the data is normally distributed.

52
Q

What does it mean if the data points deviate from the straight line in a Q-Q plot?

A

It indicates that the data may not be normally distributed.

53
Q

What is the significance of the Kolmogorov-Smirnov test in assessing normality?

A

It compares the empirical distribution function of the sample with the cumulative distribution function of a normal distribution.

54
Q

Fill in the blank: A kurtosis value of less than 3 indicates a distribution that is _____ than normal.

55
Q

What is the effect of a small sample size on normality tests?

A

Small sample sizes can lead to unreliable results in normality tests.

56
Q

True or False: Data transformations can help achieve normality.