Statistics For Researchers

Front 1

Alternative Hypothesis

Back 1

The claim trying to be proved

Front 2

Ha or H1

Back 2

Alternative Hypothesis

Front 3

Null Hypothesis

Back 3

The opposite of the alternative hypothesis

Front 4

Ho

Back 4

Null Hypothesis

Front 5

Reject Ho

Back 5

Enough data evidence that Ha is proven beyond a reasonable doubt and Ho is false

Front 6

Fail to reject Ho

Back 6

Not proof beyond reasonable doubt that Ha is proven beyond reasonable doubt, does not imply Ho is true

Front 7

Type 1 error

Back 7

Reject Null Hypothesis (Ho) when it is in fact true-say you have proven something (Ha) that is not true-
More serious error than Type 2

Front 8

Type 2 error

Back 8

Failure to reject the Null Hypothesis (Ho)-What you are trying to prove (Ha) is true, but you did not find enough evidence to support-Less serious error than Type 1

Front 9

Level of Significance (Alpha)

Back 9

Maximum allowable chance of making a type 1 error. (.05 most common)

Front 10

P-Value

Back 10

Based on observed data, smallest level of significance that allows Null (Ho) to be rejected

Front 11

If P-Value is smaller than Alpha

Back 11

Proof beyond reasonable doubt that Ha proven and reject Ho

Front 12

When is Alpha level set

Back 12

Before looking at data

Front 13

When is P-Value determined

Back 13

After data is analyzed

Front 14

Mean & Median are both measures of:

Back 14

Center

Front 15

Variance

Back 15

Standard Deviation squared

Front 16

Standard Deviation

Back 16

Typical amount population values differ from population average-how spread out population is

Front 17

Empirical rule for mound shaped populations

Back 17

68% within 1 SD +/-
95% within 2 SD +/-
99.7% within 3 SD +/-

Front 18

Interquartile Range

Back 18

25%ile to 75%ile
Distance from Q1 to Q3

Front 19

Small Interquartile range signifies

Back 19

Consistent population

Front 20

Best way to describe spread when population not mound shaped

Back 20

Median & Interquartile range

Front 21

Best way to describe typical spread of values for mound shaped population

Back 21

Mean & Standard Deviation

Front 22

Best way to describe typical spread of values for skewed population

Back 22

Interquartile Range & Median

Front 23

Shapiro-Wilk P-Value

Back 23

The probablity of seeing a histogram as skewed as your sample. Larger
S-W numbers are better.

Front 24

Shapiro-Wilk < or = 0.5

Back 24

Proof beyond reasonable doubt of skewed population

Front 25

Shapiro-Wilk > or = 0.5

Back 25

Proof beyond reasonable doubt of Mound shaped population

Front 26

Box plot symmetry signifies

Back 26

Indication of mound shaped population

Front 27

Hypothesis Tests: Three common forms:

Back 27

1. Ha typical value of population not equal to the test value (2 tailed)
2. Ha typical value of population > test value.
3. Ha Typical value of population < test value

Front 28

2-Tailed: Difference can be on__side of test value

Back 28

Either

Front 29

1-Tailed: Observed data will support difference to be___

Back 29

> or < but not both

Front 30

SPSS: Sig=

Back 30

P-Value

Front 31

Both 1-Tailed P-Values should add up to___

Back 31

One

Front 32

Confidence Intervals for Mean and 2-Tailed Hypothesis test will always___with each other

Back 32

Agree

Front 33

1-Tailed Hypothesis test can have____
data to Confidence Interval (rare)

Back 33

Contradictory

Front 34

1-Tailed Hypothesis tests are more___

Back 34

Powerful

Front 35

Confidence Intervals give a range that is_____

Back 35

Easy to understand

Front 36

1-sample T-Test assumptions

Back 36

1. Random sample (ideal) or at least try to eliminate bias.
2. Mound shaped population or n.>/= 30

Front 37

If n>/= 30 but sample is still skewed then better to use_______rather than T-Test

Back 37

Sign Test

Front 38

What does 5% trimmed mean do

Back 38

Throws out largest and smallest of each 20 samples to eliminate outliers

Front 39

Sign Test for population median assumption (only one)

Back 39

Random sample

Front 40

Practical significance is a _______of statistical significance

Back 40

Subset

Front 41

Confidence Intervals:
Assumptions (three)

Back 41

1. Random sample
2. n>/= 30 or mound shaped population
3. Same as T-Test

Front 42

To check assumptions of mound shaped population when n<30
(three things)

Back 42

1. Knowledge of researcher
2. Shapiro-Wilk Test P-Value >/= .05
3. Histogram/Boxplots

Front 43

Paired Samples T-Test:
Assumptions (two)

Back 43

1. Random sampling
2. Population of differences must be mound shaped or n>30 however, if sample is skewed the median is more meaningful

Front 44

Skewed populations of differences:
Best Test:

Back 44

Sign Test (median)

Front 45

Matched pair data: which test to use:
1.) Mound shaped:
2.) Skewed:

Back 45

1. Paired Samples T-Test
2. Sign Test

Front 46

Confidence Interval for difference between matched pair populations:
What if zero is included in the range___

Back 46

Plausible that two averages might be the same