Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
statistics
| Question | Answer |
|---|---|
| measures of central tendency (average) | mean, median, and mode |
| mean | add all up and divide, average. best when data is not skewed; the mean can be thrown off by extreme scores so sometimes the median is a better measure of central tendancy |
| median | middle. best to use when data is skewed or there are extreme scores. if there is an even # of scores the median is the avg of the middle two scores |
| mode | most occuring. bimodal means there are two modes. the mode is the most appropriate measure of central tendency to report for nominal data |
| measures of variability (spread) | range, standard deviation. reveal how spread out or dispersed the data in a distribution is |
| range | highest minus lowest. the bigger the range, the bigger the standard deviation |
| standard deviation | average distance from the mean (avg) for a set of scores; indicates how widely spreadd scores are from one another (deviate from mean). -low sd means data is closely related to avg -high sd means large variance between data & avg |
| regression towards mean | tendancy for scores to average out over time |
| frequency distrubution | shows how frequently something occurs |
| histogram | allow us to see distribution of data. graphs the approximate representation of the distribution of numerical data; it groups numbers into ranges. the height of each bar shows how many fall into each range. bars DO touch, to show data is continuous |
| (frequency) polygon | change over time. used to show continuous data measured. it helps researchers see themes/ patterns in data. useful for plotting multiple data sets which could be overwhelming on histogram. |
| bar graph | compare variables. useful for categorical or nonnumerical data. when creating bar graph, leave a space between the bars; the space between each of the bars signals that the data are categorical. |
| z scores | tell us what deviation you're on |
| percentile ranks | if compares, provides infor where an individuals score falls relative to distribution. statistical measure that indicates the % of scores in a distribution that are = to or below a particular value; where an individuals score falls to rest |
| z-score: 0 percentile rank: | 50% |
| z-score: +1 percentile rank: | 84% |
| z-score: +2 percentile rank: | 98% |
| z-score: +3 percentile rank: | 99.9% |
| z-score: -1 percentile rank: | 16% |
| z-score: -2 percentile rank: | 2% |
| z-score: -3 percentile rank: | 0.01% |
| In a normal distribution of scores, approximately what percent of all scores will fall within one deviation above and below the mean? | 68.2% |
| In a normal distribution of scores, approximately what percent of all scores will fall within two deviations above and below the mean? | 95.4% |
| In a normal distribution of scores, approximately what percent of all scores will fall within three deviations above and below the mean? | 99.7% |
| pie chart | useful for displaying nominal or categorical data or any data that consists of percentages and proportions |
| shapes of distribution | help US understand the spread of given distribution. Distributions- normal (bell curve) or skewed (positive or negative) |
| normal/bell curve | mean median and mode are all the same or close. most scores are in the middle; predictable as data falls round the mean in the same way each time. The curve has a symmetrical bell shape so it represents 50% of scores to left & 50% scores to right |
| negative skew | left skew, most scores are in the high range and very few are low. this mean will be less than median, and median will be less than the mode. tail or slope falls to the left. (mean, median, mode) |
| positive skew | right skew, most scores are in the low range, very few are high. the mode will be less than the median and the median will be less than the mean. tail or slope falls to the right. (mode, median, mean) |
| bimodal graph | refers to two modes or peaks around which values tend to cluster, such that the frequencies at first inscrease then decrease around each peak. |
| inferential stats | methods for determining the likelihood the result of an experiment is due to manipulation of indep. var.s or is due to chance. |
| p-value | can be though of as probability value- the closer the p-value is to zero, the less likely the result to due to chance. a p-value of 0 would indicate 100% certainty the results were due to the experimental manipulation, but this is nearly impossible. |
| p value of 0.05 or less is acceptable for results to be considered.. | statistically significant, thus there needs to be less than a 5% chance that the results were to do coincidence |
| we always want to be __% certain results weren't due to chance | 95 |
| p> 0.05 (probability greater than 0.05) means... | it is NOT statistically significant |
| p<0.05 means... | it IS statistically significant. we can reject the null hypothesis |
| null hypothesis states | that the indep. var. has no impact on the dep. var -when u reject null hyp. u are saying the indep var had an impact on the dep var |
| effect size | while statistical significance shows us that an effect (result) was likely not due to chance & is probably a reliable effect, it doesn't show how large the effect is, so perhaps there is a statistical significance, but tiny. |
| effect size measures how much | of an impact something has and helps researchers understand if the study has produced a small, medium-sized, or large effect. In sum, it is the size of relationship between two variables |
Created by:
113014