Study Guides (248,644)
York University (10,209)
KINE 2050 (24)
Final

# Stats study notes

4 Pages
246 Views

Department
Kinesiology & Health Science
Course Code
KINE 2050
Professor
Merv Mosher

This preview shows page 1. Sign up to view the full 4 pages of the document.
Description
-1- Stats Study Notes Statistics- Data used to make judgment (decision) about a situation 1. Descriptive - Polls and Survay - Correlation 2. Inferential -Cause and effect relationships Population > Parameter Sample> Statistic 4 Levels of measurement 1. Nominal- (catigories, can only measure frequency) 2. Ordinal- Data is ranked (1 2 3 ) Don’t know how far they are from each other, first might be 4 seconds and second might be 4.1 seconds or 10seconds we don’t know we only know where it is in relation to other scores) 3. Interval- Equal points or units of measurement assigned but 0 is a value, so therefore things cant be proportional. Ex tempature 4. Ratio- Measures the distance from 0 (zero means nothing) therefore comparisons can be made, ex 50kg is half of 100kg. Weight, distance Independent Variable- The one that is controlled or manipulated Dependant- The one we see how it is effected Frequency Distribution- Ungrouped- each value has its own group (frequency of 1, 5 times/ frequency of 2 3 times/ frequency of 3 9 times) Grouped- Values are put into intervals (frequency of 1-3, 17 times. Frequency of 4-6 10 times) Making intervals - Find N of scores - Look up #of intervals for that N on the chart - i=(biggest value- smallest value)/ # of i Shapes of Curves Normal Distribution = Bell curve (mean = median= mode) Bimodal= 2 modes (usally when you have 2 characteristics ) -1- -2- Leptokurtic- Not enough intervals (too narrow) Platykurtic- Too many intervals (too wide) Positively skewed- someone grabbed the positive side and stretched it (an extreme big score) Measures of central Tendency – Meant to tell us where bulk of score lies Mean- Interval and Ratio (unless badly skewed –because mean moves towards skew) Median-Ordinal always Mode- (frequency/Which one happens most)- used with nominal always Measures of Variance Range- Highest- lowest (gives range between where 100% of values fall) Standard Deviation- SD= √Variance (measures deviation of all scores from mean) Formula >> Variance= same thing but no sqrt +/-1SD tells you where 68% of the scores lie So if SD is 15 and the mean is 100 68% of scores are from 85-115 The bigger the SD the more spread out the data If mean and median differ by more then 1SD use median Z-scores- shows raw score in relation to group (how many SDs from the mean the score is) Percentile-Percentage of people that got same ore worse then you Tscore- Keeps everything positive numbers (T=10Z+50) Sampling error- Is the error when choosing a sample from a population (maybe you choose all the tall kids) Bigger SD = Bigger SEM Bigger N= Smaller SEM SEM= SD/√N 1SD- where 68% of scores fall 1SEM- Where 68% of means fall If we want 95% interval multiply SEM by 1.96 99% 2.58 -2- -3- If N<30 then look up the value that you have to multiply SEM with on the t-table using the right amout of DF Probability- Chance that an event will occur P(A)
More Less

Only page 1 are available for preview. Some parts have been intentionally blurred.

Unlock Document

Unlock to view full version

Unlock Document
Me

OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Just a few more details

So we can recommend you notes for your school.