Descriptive statistics Flashcards
Measures of central tendency definition?
the relationship of the values with the central point
Least to most precise/ sensitive MOCT
mode -> median -> mean
how to calculate mean ?
= the average
add up all numbers/ number of numbers
how to calculate mode?
= most common number, may be more than 1
putting similar scores together, and counting which appears most frequently
median calculate?
= central value
- arranging scores in order and finding mid point
advantages of the mean?
+ appropriate to use for further statistical analysis such as standard deviation
+ appropriate to use for ordinal, interval, ratio levels of data
mean disadvantages?
- affected by extreme scores so can misrepresent no.s
- may produce a value that no ppt in the data set achieved
mode advantages?
+ unaffected by extreme scores
+ can be used with nominal (categorical data) & provides info abt freq
+ unlike mean and median, there is always a modal score
mode disadvantages?
- ignores values by only looking at the freq of no.s, this may lead to biased representation as an outlier score may be the most frequent
- can be unclear as data may have several modes - bimodal = 2
median advantages?
+ makes use of all the values but is not as biased by extreme scores as mean
+ can be used with ordinal data
median disadvantages?
- more open to bias from extreme scores than mode
- unhelpful for further statistical analysis such as standard deviation
what is measures of dispersion?
how dispersed or spread out the data are
range calculated?
the range is a measure the spread of a set of scores, shown by the difference between highest and lowest
standard deviation?
measure of the spread of data around th mean.
higher value = more variation in your scores
range +?
+ easier to calc than standard deviation
+ takes into account extreme values
range -?
- affected extreme values and does not take into account the no. of observations in the data set
- it does not give info on whether the scores are clustered around the mean or spread out
SD +?
+ Gives more precise and informative measure of dispersion than range, as it doesn’t just take into account highest & lowest
+ less affected by anomalous results than range - extreme scores are ignored
SD -?
- more complicated to calculate then range
- can only be used when data set is normally distributed (bell shaped curve) and not skewed
What is meant by low standard deviation?
Data is clustered around average
what is meant by high standard deviation?
Tells us data is dispersed
When is SD used?
When distribution of data is approx normal- a bell shaped curve
To tell when data is normal, expected, unusual
What is the 68-95-99.7 rule?
About 68% of data falls within the 1st sigma
About 95% of the data falls within the 2nd sigma
About 99.7% of data falls into 3rd sigma
Acting with the mean SD allows us to determine whether
A value is statistically sig or as a part of standard deviation (expected)