Exam 3 Material

Question 1

Null hypothesis (Ho)

Answer 1

A research perspective in which there is no true difference between the comparison groups

Accepted - there is NO difference
Rejected - there IS a difference

Question 2

Nominal data

Answer 2

Dichotomous/binary; non-ranked; named categories

No magnitude/order
No consistency of scale
No rational/absolute zero

Ex. Male vs. Female / colors / ethnicities

Question 3

Ordinal data

Answer 3

Ordered, rank-able categories

HAS magnitude/order
No consistency of scale
No rational/absolute zero

Ex: satisfaction surveys / mood levels / pain scale (though some researches see it as interval data)

Question 4

Interval data

Answer 4

HAS magnitude/order
HAS consistency of scale
No rational/absolute zero (can have negative values)

Ex: temperature / height / specific number on a known scale

Question 5

What is the difference between interval and ratio data?

Answer 5

Interval data has an arbitrary 0 - can have (-) numbers

Ratio data has an absolute 0 - cannot have (-) numbers; “0” represents the absence of a measured value; typical of physiological measurements like BP, height, etc.

Question 6

Discrete vs. Continuous data sets

Answer 6

Discrete = Nominal and Ordinal data

Continuous = Interval/ratio data

Question 7

Descriptive statistics

Answer 7

Non-comparative, simple description of various elements of a study’s data

Question 8

Mean vs. Median vs. Mode

Answer 8

MEAN = average

MEDIAN = the middle of a data set

MODE = most frequent number in a data set

Ex. 1, 1, 1, 2, 4, 5, 5, 8, 8
Mean = (1+1+1+2+4+5+5+8+8)/9 = 3.88
Median = 4
Mode = 1

Question 9

What do outliers affect?

Answer 9

The mean/average of a data set

Question 10

Interquartile range

Answer 10

IQR = Q3 - Q1

The middle 50% of a range of data

Question 11

Variance

Answer 11

The average of the squared differences between each individual measurement value and the groups’ mean

Question 12

Standard deviation

Answer 12

Square root of the variance

Question 13

Normal distribution

Answer 13

When the mean of a data set is equal (or nearly equal) to the median, such that there is equal dispersion of a curve’s tails on either side of the mean

Skewness = 0
Kurtosis = 0

Question 14

What tests are useful for normally distributed data?

Answer 14

Parametric tests

Question 15

Positive skew

Answer 15

When the mean > median for a data set

Results in a curve shifted to the LEFT (tail point to the right)

Question 16

Negative skew

Answer 16

When the mean < median in a data set

Results in a curve shifted to the RIGHT (tail points to the left)

Question 17

Given: mean = 15 / median = 3 / mode = 0

Is the data skewed? How do you know?

Answer 17

Yes: Because the mean > median, the data is positively skewed

Question 18

Skewness

Answer 18

A measure of asymmetry of distribution

Normal distribution is symmetrical (skewness=0)

Question 19

Kurtosis

Answer 19

A measure of the extent to which observations cluster around the mean:

(+) kurtosis indicates more cluster
(-) kurtosis indicates less cluster

Normal distribution “clusters” evenly about the mean (kurtosis=0)