Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
10 Cards in this Set
- Front
- Back
|
Summarize the major kinds of data that are possible using the 4 kinds of measurements scale? |
1. Nominal: categorical, = or =/ 2. Ordinal: ordering or ranking, >,< 3. Interval: No 0, but but integers are meaningful 4. Ratio: Absolute 0 |
|
|
Distinction between discrete and continuous data. Can data be discrete and interval/ratio? Can data be both continuous and categorical? |
Discrete basically means there are specific, distinct intervals. It can be categorical, but it can also be quantitative, such as number of people in a family. However, data cannot be both continuous and categorical. |
|
|
Mode is the most frequently occurring score, but also explained as the highest point on a distribution. Explain mean and median both conceptually and computationally. |
Mean: the average. found by adding all data together and dividing by number of data points. It would be the balance point of the distribution. Median: equal area on both sides of the distribution. Equal number of data points (not value, but just number of data) on both sides |
|
|
How do the mean, median, and mode relate on skewed distributions? |
Right (positively) skewed: mean is greater than median, median is greater than mode. Left (negatively) skewed: mode is greater than median, which is greater than mode. Mean is always closest to the tail and median is always in the middle. |
|
|
Explain mean, median, and mode as physical quantities (wooden blocks) |
Mode: location with the highest stack of blocks Median: point with same number of blocks above and below Mean: point where the distribution would balance if placed on a scale |
|
|
What is variance? |
Variance is the average of squared distances of scores from their mean. Averages are found by taking the sum of values and dividing that by the number of values. For variance, however, you divide it by the number of values minus 1. So to find variance, you subtract the scores from their mean, square them, sum up all those values, and divide by the number of values minus 1. |
|
|
Explain "mean deviation" statistic and the standard deviation statistic. |
Mean deviation just means average deviation. It's similar to variance, but instead of squaring the distance of a value from it's mean, you just sum the absolute values of those distances. It's never used. Standard deviation is simply the square root of the variance. Standard deviation and variance are what are used. They are Pythagorean. |
|
|
Explain skew and kurtosis and how they are used with the mean and the standard deviation to specify the shape of a distribution. |
Skew: If there are extreme scores on one end of the distribution. Right or positively skewed means the extreme tail points to the right. Left or negatively means the extreme tail points to the left. Kurtosis: defined relative to the Gaussian distribution, which is a normal curve, or mesokurtic. Leptokurtic means the distribution "leaps up" in the middle, or the center is higher and the intermediate regions are lower, and tails are fatter. Platykurtic means relatively flat. The middle is lower, intermediate regions are higher, and tails are lower. |
|
|
You multiply all scores by a constant (ie, 3), what effect would it have on mean, variance, standard deviation, and SIR? |
Mean: 3x original mean Variance: (3*2)x the original variance Standard deviation: 3x original S SIR: 3x the original SIR |
|
|
Do the derivation of the computational formula for covariance from the definitional formula. |
cov=(sumxy)/(N-1) or sum(X-meanX)(Y-meanY)/(N-1) |
