Beruflich Dokumente
Kultur Dokumente
Descriptive techniques
Central tendency Variability
Descriptive Statistics
Descriptive statistics are used to summarize or condense a group of scores They include measures of central tendency and measures of variability
Descriptive Techniques
Variability scores
Standard deviation Variance Range of scores
Central Tendency
Measures of central tendency describe the average or common score of a group of scores Common measures of central tendency include the mean, median, and mode
Mean
The mean is the arithmetic average of the scores The calculation of the mean considers both the number of scores and their value The formula for the mean of the variable X is:
X M n
8
Mean
Six men with high serum cholesterol participated in a study to examine the effects of diet on cholesterol At the beginning of the study, their serum cholesterol levels (mg/dL) were: 366, 327, 274, 292, 274, 230 Determine the mean
Mean
366 327 274 292 274 230 M 6 1,763 M 6 M 293.83
10
Analyze -> Descriptive Statistics -> Frequencies command may be used to determine the mean (you will need to select the Statistics button to choose the Mean
6 0 293.83
11
Median
The median is the middle point in an ordered distribution at which an equal number of scores lie on each side of it It is also known as the 50th percentile (P50), or 2nd quartile (Q2)
12
Median
n 1 Mdn 2
13
Median
Example: Calculate the median for the following measurements for height: 71, 73, 74, 75, 72
14
Median
Step One: Place the scores in order from lowest to highest. 71, 72, 73, 74, 75 Step Two: Calculate the position of the median using the following formula:
n 1 Mdn 2 5 1 Mdn 3rd score 2
15
Median
Step Three: Determine the value of the median by counting from either the highest or the lowest score until the desired score is reached (in this case the 3rd score)
16
Median
Suppose that in our previous distribution we had a sixth score as follows: 71, 72, 73, 74, 74, 75 What are the position and value of the median?
17
Median
Consider the following example: Nine people each perform 40 sit-ups, and one does 1,000 The median score for the group is 40, and the mean (arithmetic average) is 136 The median would still be 40 even if the highest score were 2,000 instead of 40
18
10 0 236.00 40.00
19
Mode
The mode is the most frequently occurring score Which of the following scores is the mode? 3, 7, 3, 9, 9, 3, 5, 1, 8, 5 Similarly, for another data set (2, 4, 9, 6, 4, 6, 6, 2, 8, 2), there are two modes; What are they? What is the mode for 7, 7, 6, 6, 5, 5, 4 and 4
20
Mode
A distribution with a single mode is said to be unimodal A distribution with more than one mode is said to be bimodal, trimodal, etc., or in general, multimodal
21
Analyze -> Descriptive Statistics -> Frequencies command may be used to calculate the mode (you will need to select the Statistics button to choose the mode, etc Note differences in the SPSS output when the distribution is unimodal, multimodal, or when there is no mode
22
10 0 3
23
10 0 2a
24
8 0 4a
25
Variability
Measures of variability describe the extent of similarity or difference in a set of scores These measures include the range, standard deviation, and variance
26
Standard Deviation a measure of the variability, or spread, of a set of scores around the mean Intuitively, the sum of the differences between each score and the mean (known as deviation scores) appears to be a good approach for measuring variability around the mean
27
SD
X M
M 6
28
SD
X M
= (1-6) + (2-6) + (6-6) + (6-6) + (15-6) = (-5) + (-4) + (0) + (0) + (9) = = -9 + 9 = 0
29
SD
We can avoid this problem (deviation scores sum to 0) by squaring each deviation score before summing them This would be written symbolically as
X M
30
SD
Substituting our X scores again, = (1-6)2 + (2-6)2 + (6-6)2 + (6-6)2 + (15-6)2 = (-5)2 + (-4)2 + (0)2 + (0)2 + (9)2 = 25 + 16 + 0 + 0 + 81 = 122
31
SD
We then divide this value by n-1 to arrive at the mean squared deviation 122/4 = 30.5 We then take the square root of this value to bring the units back to the raw score units
30 .5 5.52
32
Subj
Score (x)
Deviation
(x)2
X 1740 193 .3 X=
n 9
( x X )2 11774.01 s2 147175 . n 1 8
1
2 3 4
216
144 183 138
22.7
-49.3 -10.3 -55.3
515.29
2430.49 106.09 3058.09
5
6 7 8 9
212
180 200 264 203 =1740
18.7
-13.3 6.7 70.7 9.7 =0
349.69
176.89 44.89 4998.49 94.09 =11774.01
( x X )2 s 38.4 n 1
Analyze -> Descriptive Statistics -> Frequencies command may be used to determine the standard deviation (you will need to select the Statistics button to choose the Std. deviation
5 0 5.523
34
Variance
The variance is the square of the standard deviation It is used most commonly with more advanced statistical procedures such as regression analysis, analysis of variance (ANOVA), and the determination of the reliability of a test
35
Variance
X M s n 1
2
36
Range
The range is equal to the high score minus the low score in a distribution It is considered an unstable measure of variability, and can change drastically if extreme scores are introduced to the distribution
37
Range
As a result of gas analysis in a respirometer, an investigator obtains the following four readings of oxygen percentages: 14.9, 10.8, 12.3, and 23.3 What is the range?
38
Analyze -> Descriptive Statistics -> Frequencies command may be used to calculate the range (you will need to select the Statistics button to choose Minimum, Maximum, and Range
40
Confidence Intervals
Provide an expected upper and lower limit for a statistic at a specified probability level (usually 95% or 99%) CI is dependent upon the sample size, homogeneity of values within the sample and the level of confidence selected by the researcher
41
sM s / n
42
Calculating a CI
Example: n = 30, M = 40, s = 8 CI = 40 (1.46 2.045) CI = 40 2.99 = 37.01 to 42.99 The value 1.46 came from the following formula: sM 8 / 30
44
Correlation
Correlation indicates the extent to which two variables are related or associated-that is, the extent to which the direction and size of deviations from the mean in one variable are related to the direction and size of deviations from the mean in another variable
Z r
ZY
45
Example of Correlations
46
Parametric
Normal distribution Equal variances Independent observations
Normal curve
Skewness Kurtosis
47
Normal Curve
48
Skewness
49
Kurtosis
50
Statistics
51
Next Class
Chapter 7 Abstract
52