Module 3, Measures of Central Tendency Flashcards
What are the 3 Measures of Central Tendency?
- mode
- median
- mean
Mean
- arithmetic average of a set of scores
- the mean can be considered a balancing point in the distribution of scores for a variable
- the average value of the variable (the most common measure of central tendency
How to Calculate the Mean?
to calculate:
1. multiply each score (X) by its frequency (f)
2. sum of the products (fX)
3. divide by the total number of scores
- you need unique values for mean and thus cannot calculate from grouped frequency table (have to know what each value in the data set is)
Score - Mean
if we subtract the mean from each score:
- the sum of the negative differences will always equal the sum of the positive differences
- score - mean is always going to add up to 0 in the end
* the mean as a balancing point
Asymmetric Distributions (positive): Mean and Median
in a positively skewed distribution the value of the mean is usually greater than the median
Asymmetric Distributions (negative): Mean and Median
in a negatively skewed distribution the mean is a smaller value than the median typically
Mode and Modality: 1 Mode; Unimodal
- mode is most frequently occurring value (represented by highest bar in a histogram)
- unimodal as there is only one peak
Mode and Modality: 2 Mode; Unimodal
2 bars that are of even height (2 values that have same frequency), however there is really only one peak which would mean it is still unimodal (mode and modality are distinct concepts - cannot be used interchangeably)
- even if there is a slight gap in between the modes it is not enough to create a bimodal distribution as there is not enough of a dip meaning the valley should come down all the way and go back up
Mode and Modality: 1 Mode; Bimodal
- there is 1 mode, the other value is not as great - goes down and comes back up (bimodal)
◦ in order to assess modality you must look at HISTOGRAM (need to visually see it) - shape of distribution
Mode
- most common or frequently occurring score
- score or value of a variable that appears most frequently in a set of data
*to identify mode look down the frequency column and see what value is seen the most and we identify the tallest bar in the bar chart or histogram or the highest data point in the polygon
What are Strengths and Weaknesses of the Mode?
strengths
- easy to determine
- can be used to summarize nominal data
- represents an actual value (in the data set)
- takes in account multiple modes (when it follows by bimodal for instance)
- not affected by outliers
weaknesses
- can not be used in hypotheses testing (when conducting inferential statistical analyses)
- oversimplified use of one score rather than the whole set of data
Median
- the value of the variable in the center of the distribution
- the value of a variable that splits a distribution of scores in half, with the same number of scores above the median as below (arrange from lowest to highest, calculate the median score in the set of data and determine the value of the median score)
odd number of scores: one in the middle
even number of scores: take middle two values and average it
What are Strength and Weaknesses of the Median?
strengths
- provides a more accurate measure of central tendency in skewed (asymmetric) distributions
◦ the mean is not an accurate
measure of central tendency
when it is skewed
weaknesses
- relies on only the middle one or two scores, not the whole data set (the whole data set is not represented)
- cannot be used in hypothesis testing (when conducting inferential statistics
- inaccurate for bimodal distributions (it falls in the middle of the distribution, in the valley where most of the data is not)
Sample Mean
the sample mean is an example of a descriptive statistic and it describes the average score of a variable from the data we have collected
Population Mean
the population mean is unknown to us but we can estimate the population mean depending on what we know for our sample data
- parameters = unknown population mean