Midterm Lec 6b Flashcards
What are statistics?
The study of methods for:
-Describing and interpreting quantitative information
-Includes techniques for organizing and summarizing data
-Includes techniques for making generalizations and inferences from data
-Mathematical tests done on data collected from either populations or samples
Population
- The total collection of people, things, or events of interest
-N
Sample
-A subset of the population
-Smaller sets of cases selected frim a larger pool
-n
-Parametric statistical tests
-Not to be confused with population parameter
-Interval or ratio data
-Assume the data are normally (or near normally) distributed
Non-parametric statistical tests
-Data are counted (nominal scales) or ranked (ordinal scale)
-These statistics do not require a normally distributed population
Distribution of Scores
-Once we have collected our data, we can plot each data point in order to see the “shape” or “pattern” of the scores across the population or sample
Normal Distributions
- Normal distributions will have the same overall shape
- The exact shape of a distribution curve is described by the mean and the sd
- If you move the mean along the horizontal axis without changing the standard deviation, you will change the shape of the curve
- The mean is located at the centre of the symmetric curve, and will be the same as the median
- If you move the mean along the horizontal axis without changing the sd, you will change the shape of the curve
- The larger the sd, the more spread out the curve (aka flattening the curve)
- Normal Distributions: The 68-95 Rule
(Normal distributions)
In order to be considered ‘normal’ they should be:
- Symmetrical
- Single peaked
- Bell-shaped
The 68-95 Rule
In a NORMAL distribution:
68% of the observations will fall between the mean and the sd (+ /-1)
-34.13% to the left, and 34.13% to the right of the mean
95% of the observations will fall between the mean and two sd’s (+ /-2)
-47.5% to the left, and 47.5% to the right of the mean
99.7% of the observations will fall between the mean and three sd’s (+ /-3)
-49.8% to the left, and 49.8% to the right of the mean
Normal Distributions
-Why don’t standard deviations add up to 100%?
-The 0.3% remaining is equal to 0.15% in each end or tail
-Represents extreme scores and as such, are relatively rare
Standard Deviation sd
measure of the amount of variation such as spread, desperation from the mean exits
Two key characteristics of a distribution of scores
Central tendency: The value of a “typical” score
Variability: The extent to which scores differ from one another
Measures of Central Tendency
Mean / Median / Mode
Mean
-The most common measure of central tendency
-Quickest estimate of central value and shows the most typical case
-Sensitive to extreme scores
-Add all the scores and divide by the number of scores
-Not a great representation of all the scores
Median
-A measure of position; score that lies in the middle
-Not sensitive to extremes and therefore may be a more realistic measure of CT than the mean