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;
66 Cards in this Set
- Front
- Back
Statistics |
Procedures for reducing large measures of data to manageable proportions and allow us to draw conclusions |
|
Population |
The complete set of events of interest |
|
Sample |
A set of observations or subset of population |
|
Population is to ________ as _________ is to Sample |
A) Parameters B) Statistics |
|
Descriptive stats |
Description of sample without making inferences |
|
Inferential Stats |
Stats drawing influences about parameters |
|
Random Sample |
Where each member of the population has a equal chance of being included |
|
Convenience Sample |
Sample of those conveniently available |
|
Random Assignment |
Assignment of participants to groups at random |
|
What 3 things do you consider when selecting a stats procedure? |
1. Differences Vs. Relationships 2. Number of groups or variables 3. Type of data (Measurement or Categorical) |
|
Measurement Data |
Data obtained from measuring objects or events |
|
Categorical Data |
Data representing counts or number of observations in each category Ex. How many females Vs. Males |
|
Variables |
Properties that objects can have with different values |
|
Discrete Variables |
Variables that have a small set of possible values Ex. Males or Female Ex. Rating from 1-5 |
|
Continous Variables |
Variables that can take on any values Ex. Time Ex. Weight |
|
Independent Variable |
The manipulated Variable |
|
Dependent Variable |
The measured variable |
|
Frequency Data |
Organizes data into a format that shows the frequency of scores's occurrence |
|
Continous data is to ________ as _________ is to discrete data |
A) Histogram, or Line Graph B) Bar Graph |
|
What are the 4 different distributions? |
1. Normal (Unimodal) distribution 2. Bimodal Distribution 3. Negatively Skewed 4. Positively Skewed |
|
Trimmed Mean |
The mean of a distribution in which we have removed a percentage of scores from either end of the distribution |
|
Variability |
The degree/amount individual data points are distributed around the mean |
|
Range |
The range between the highest and lowest end of scores, Outliers effect this Ex. Range= Highest Score - Lowest Score |
|
Interquartile range |
The range of the middle 50% of the observations |
|
Variance/Standard Deviation |
Average amount of difference between individual data points and the mean |
|
Degrees of freedom |
The number of independent pieces of information after estimating one or more parameters |
|
Winsorized Sample |
A sample where a percentage of scores on either end of an ordered set of scores are replaced by the remaining highest and lowest scores Step 1. 12345 Step 2. 234 Step 3. 22344 |
|
Is it better to have a larger or smaller sample size? |
Larger, because it is more normally distributed |
|
Ordinate |
Y-axis (Frequency) |
|
Abscissa |
X-axis (Score) |
|
Density |
The high of the curve for a given value of x |
|
What is the mean and variance/SD of the Standard Normal Distribution? |
Mean= 0 Variance/SD= 1 |
|
What is the Analytic View of probability? |
Analysis of possible outcome |
|
Frequentist View of probability |
Determining probability of something based on past performance Ex. Picking a red skittle 3 out of 5 times |
|
Subjective Probability |
Probability based on personal belief and likelihood of an outcome Ex. Low probability or 0% chance I will get married in 5 minutes |
|
Independent Events |
One event has NO effect of the probability of another |
|
Dependent Event |
The outcome of one event is related to the probability of the other (correlation) |
|
Mutually Exclusive |
When two events cannot occur together Ex. You cannot draw a blue M&M that is also yellow it can only be one colour |
|
Exhaustive |
Event that examines all possible outcomes |
|
Additive Law |
Given a set of mutually exclusive events, the probability of the occurrence of one or another is equal to the sum of their separate probabilites, uses single outcome and "or" Ex. P(blue or green)= p(blue)+p(green) |
|
Multiplicative Law |
The probability of two or more independent events occurring is the product of multiplying their independent probablity Ex. Step 1. P(Blue, Green)= P(Blue) x P(Green) Step 2. P(Green, Blue)= P(Green) x P(Blue) Step 3. P(Blue, Green) + P(Green, Blue) |
|
Joint Probability |
The probability of the co-occurence of 2 or more events Ex. Wearing a seatbelt and having a child |
|
Conditional probability |
The probability that one event will occur given another event has already occurred |
|
Sampling Distribution |
The variability of a statistic over repeated sampling from a specific population Ex. Sampling Distribution of the mean or mode |
|
Sampling Error |
Variability of a statistic from sample to sample or population |
|
What are the 6 steps of Hypothesis Testing? |
1. State the research hypothesis H1 2. State the null hypothesis Ho 3. Collect data 4. Look at the relevant sampling assuming Ho is true 5. Compute the probability of getting our result 6. Make a decision: Reject Ho or fail to reject Ho If P>.05 then it is not significant |
|
Rejection or Significance level |
The probability that we are to reject the Ho at .05 |
|
What are Cohen's conventions for correlation? |
Small .10 Medium .30 Larger .50 |
|
Restricted Range |
Case in which range over which x or y varies are limited Ex. Only looking at males or females in sample |
|
What are the 3 factors effecting correlation? |
1. Restricted range 2. Outliers 3. Heterogenous Subsamples Ex. Maybe no correlation for males and females, but when looking at groups separately there is a correlation |
|
Regression |
Predicting one variable using another |
|
In the absence of other scores what is the best predictor of another individuals score? |
The Mean of the sample |
|
What does r squared tell you? |
The proportionate reduction of error Ex. How much error can be accounted for Y because of X |
|
What are the 3 factors influencing regression? |
1. Outliers 2. The degree of scatter around the regression line 3. The validity of a single "Regression line or Line of best fit" |
|
Factors that affect the magnitude of T |
1. Actual obtained difference (Between sample and population) 2. The magnitude of the variance 3. Sample Size 4. Significance level .01 versus .05 5. Using a one versus two tailed test |
|
What are the two types of estimates of a paramater? (Confidence interval) |
-Point estimate: The specific value estimate of a parameter Ex. 50 people -Interval estimate: A range of values estimated parameters Ex. 50-60% of people |
|
Confidence Interval |
Is an interval estimate with limits at either end (upper and lower) and a specific probability of including the parameter being estimated Ex. Only 5% of the time the population will fall outside of the 95% confidence interval |
|
Related samples |
The study of the same participants in more than one treatment/condition |
|
Difference scores |
The set of scores representing the difference between subjects performances on two occasions |
|
Assumption of independent t-test |
1. Normality of distribution 2. Random Sampling 3. Independence of Observation 4.Homogenity of Variance Ex. Homoscedasticity: Populations equal Ex. Heteroscedasticity: Populations are not equal |
|
Power |
Probability of correctly rejecting a false null hypothesis |
|
4 factors affecting power |
1. The significance level (.01 or .05) 2. The true alternative hypothesis, the difference between populations 3. The sample size, larger sample size higher power 4. which test is employed |
|
Familywise error |
The probability of making at least one type 1 error in the comparrisons |
|
Draw Tukey's Significant test |
Using group 1=5 2=4 3=3 |
|
Chi-Square test |
Statistical test often used for categorical data |
|
Which method of improving Chi-Square does Howell tell us to use? |
Fisher's exact test, if expected frequencies are 5 |