3.80 Review.notebook 1 October 19, 2017 Apr 196:57 AM Review Twovariable Statistics TwoVariable Data Sets Twovariable data sets: • provide information about two attributes of each subject • can be ordered pairs, two column tables of values, scatter plots • can show a relationships between the variables Apr 196:57 AM Review Twovariable Statistics TwoVariable Data Sets Twovariable data sets: • provide information about two attributes of each subject • can be ordered pairs, two column tables of values, scatter plots • can show a relationships between the variables
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
3.80 Review.notebook
1
October 19, 2017
Apr 196:57 AM
Review Twovariable Statistics
TwoVariable Data SetsTwovariable data sets:• provide information about two attributes of each subject• can be ordered pairs, two column tables of values, scatter plots• can show a relationships between the variables
Apr 196:57 AM
Review Twovariable Statistics
TwoVariable Data SetsTwovariable data sets:• provide information about two attributes of each subject• can be ordered pairs, two column tables of values, scatter plots• can show a relationships between the variables
3.80 Review.notebook
2
October 19, 2017
Apr 196:57 AM
Review Twovariable Statistics
Effective SurveysEffective surveys:• should collect accurate and detailed information from subjects• should be ethical, designed for honest response, eliminate bias• can have five different types of questions
1. Dichotomous (two part classification)2. Multiple choice (limited number of predefined answers3. Rating scale4. Fill in the blanks5. Openended
Apr 196:57 AM
Review Twovariable Statistics
Effective SurveysEffective surveys:• should collect accurate and detailed information from subjects• should be ethical, designed for honest response, eliminate bias• can have five different types of questions
1. Dichotomous (two part classification)2. Multiple choice (limited number of predefined answers)3. Rating scale4. Fill in the blanks5. Openended
3.80 Review.notebook
3
October 19, 2017
Apr 196:57 AM
Review Twovariable Statistics
Effective SurveysEffective surveys:• should collect accurate and detailed information from subjects• should be ethical, designed for honest response, eliminate bias• can have five different types of questions
1. Dichotomous (two part classification)2. Multiple choice (limited number of predefined answers3. Rating scale4. Fill in the blanks5. Openended
Apr 196:57 AM
Review Twovariable Statistics
Collect and Organize DataPrimary data is collected by the researcher. When collecting primary data:• Plan the process in advance• Use random sampling to select your subjects• Keep the conditions the same for all participants
Researchers can also use secondary data, collected by another agency such as Stats Canada. When doing secondary research, keep track of all sources.
3.80 Review.notebook
4
October 19, 2017
Apr 196:57 AM
Review Twovariable Statistics
The Line of Best Fit• Linear regression determines an equation of the line (or curve) of best fit of a set of twovariable data• Linear correlation is a measure of the strength of the relationship between two variables. The correlation coefficient, r, can be used to determine how well the regression equation fits the set of data.• The closer the correlation coefficient is to 1 or +1, the better the fit• A correlation coefficient of 0 means that the line of best fit is horizontal and that no relationship exists between the two variables• The correlation coefficient does not indicate whether a relationship exists between the two variables.
Apr 196:57 AM
Review Twovariable Statistics
Analysis and Conclusions• For a causal relationship to exist between two variables, a change in the independent variable must result in a change in the dependent variable.• Regression can be used to determine an algebraic model of a relationship• Errors in data analysis can occur for a variety of reasons
1. Too little data2. Using linear regression for a nonlinear relation3. Using linear regression when the correlation is weak4. Reversing the cause and effect relationship5. Extrapolating outside the range of the data set6. Ignoring the effects of outliers and influential points
3.80 Review.notebook
5
October 19, 2017
Apr 196:57 AM
Review Twovariable Statistics
Analysis and Conclusions• For a causal relationship to exist between two variables, a change in the independent variable must result in a change in the dependent variable.• Regression can be used to determine an algebraic model of a relationship• Errors in data analysis can occur for a variety of reasons
1. Too little data2. Using linear regression for a nonlinear relation3. Using linear regression when the correlation is weak4. Reversing the cause and effect relationship5. Extrapolating outside the range of the data set6. Ignoring the effects of outliers and influential points
Apr 196:57 AM
Review Twovariable Statistics
Analysis and Conclusions• For a causal relationship to exist between two variables, a change in the independent variable must result in a change in the dependent variable.• Regression can be used to determine an algebraic model of a relationship• Errors in data analysis can occur for a variety of reasons
1. Too little data2. Using linear regression for a nonlinear relation3. Using linear regression when the correlation is weak4. Reversing the cause and effect relationship5. Extrapolating outside the range of the data set6. Ignoring the effects of outliers and influential points