Descriptive Statistics Flashcards
Point statistics
Single values, or points that summarise a set of data such as mean or median
Interval estimates
Tend to be a range of values that summarise set of data such as variance or standard deviation
Visualisations
Figures that help display the point and interval estimates of data and can take various forms depending on data type
The mean
Measures average of a set of numbers
25 participants are asked how many years they have been driving. They response 7,1,2,6,3,4,3,4,3,4,5,4,7,5,6,5,5,4,5,6,5,6,3,2,5. Calculate the mean?
7,1,2,6,3,4,3,4,3,4,5,4,7,5,6,5,5,4,5,6,5,6,3,2,5 = 110
110/25(amount of numbers) = 4.4
X = 4.4 or M = 4.4
The median
Point estimate that is the middle number of a distribution where half are large and half are smaller. Divides the data in half
How to calculate the median
Sort values highest to lowest (sort from i(first value) to n(last value))
median is value at position (n + 1)/2
Count how many are in the row and divide by 2
What is the median position of 7,1,2,6,3,4,3,4,3,4,5,4,7,5,6,5,5,4,5,6,5,6,3,2,5
1,2,2,3,3,3,3,4,4,4,4,4,5,5,5,5,5,5,5,6,6,6,6,7,7 =25
Median position = (n+1)/2 = (25+1)/2 =26/2
Median position = 13
Position 13 = 5 median =5
What is the median of 20,20,10,12,10,14,12,20,14,14,14,13
10,10,12,12,13,14,14,14,14,20,20,20
Median position = (n+1)/2 = 12+1/2 = 6.5
Median = 14
The mode
Last point estimate, the value of category that appears most often in data set
How to calculate mode
Sort data set from smallest to largest
What number is there most frequently = mode
Calculate mode of 3,4,6,4,6,6,2,2,3,6,6
2,2,3,3,4,4,6,6,6,6,6
Mode = 6
Inferential
Statistic that allow you to make predictions about or comparisons between data (e.g., t-value, F-value, rho)
Z-scores
Any value on a continuous scale can be converted to a z-score (standard deviation units)
Confidence intervals
Specifically focus on 95% confidence interval using cut of value (assuming a =.05 and two-tailed) of z = 1.96 using key formulas:
Upper 95% CI = x + (z x SE)
Lower 95% CI = x - (z xSE)
One sample t-test
Compare your sample mean to a known test value. For example, compare sample IQ to population norm of 100
Between subjects t-test
Compare two groups or conditions where the participants are different in each group and have not been matched on broad demographics e.g only age
Within subject t-test
Compare two conditions where the participants are the same in both conditions matched on demographics such as IQ, reading ability but must be marched on certain number
Pearson correlation
Pearson product moment correlation measures the relationship between two variables that is the monotonic and linear. Measures the covariance or shared variance that standardises measure between -1 (the perfect negative relationship) and 1 (perfect positive relationship)