Week 2 notes
Week 2 notes SWRK 344
Popular in Social Work Statistics and Data Analysis
Popular in Social Work
verified elite notetaker
This 4 page Class Notes was uploaded by Kirsten Swikert on Tuesday September 13, 2016. The Class Notes belongs to SWRK 344 at Western Kentucky University taught by Dr. Getch in Fall 2016. Since its upload, it has received 7 views. For similar materials see Social Work Statistics and Data Analysis in Social Work at Western Kentucky University.
Reviews for Week 2 notes
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 09/13/16
Discrete and Continuous Variables • Discrete variables have a limited (finite) number of attributes o Scores on achievement tests • Continuous variables have limitless attributes; theoretically, these can go into infinity o There can be measurements in-between the measures we have taken o Height is a good example Dichotomous Variables: • It is discrete • It only has 2 attributes • Ex: o Present/absent o Yes/no o Win/loss Binary Variables: • Is a particular kind of dichotomous variable • The variable is assigned a 1 or 0 based on the presence or absence of an attribute • This is done for statistical analysis to be possible • You must have numbers to run an analysis (you cannot run analyses on yes/no or present/absent) Dummy Variables: • A particular kind of dichotomous variable • Giving a number to a nominal level • Number of dummy variables completed equals the total number of attributes of the variable – 1 o The other attribute is assumed to be present if all other attributes are given a value of 0 • We are creating a dichotomous variable at the ratio level • This allows us to run a statistical analysis o Treatment group (1); control group (0) Independent Variables: • This is the variable that is predicted to or actually influences another variable • We can think of it as a “predictor” variable • Calorie consumption influences weight o Calorie consumption o Weight Dependent Variable: • This is the variable that is influenced by another variable Research Hypotheses (3 forms/3 types): • One tailed (directional) • Two tailed (non-directional) • Null (not related) One Tailed (Directional): • States that the variables have a relationship and predicts the direction of the relationship o Male EMT student demonstrate more decisiveness in emergency situations than female EMT students Two Tailed (Non-Directional): • States that the variables have a relationship but does not predict the direction of the relationship o Social work majors and psychology majors differ in their comfort level with statistics Null (Not Related): • States that two or more variables do not have a relationship o There will be no relationship between anxiety and decisiveness in emergency situations between male and female EMT students Non-Causal Research Hypotheses: • Non-Causal relationship o There is a relationship pattern between multiple variables but evidence to prove that the attributes of one variable contributes to or causes the attributes of another variable is lacking • Causal relationship o The attributes of one variable are believed to cause or be a contributor to the attributes of another variable Two types of Non-Causal Relationships: • Association o Predicts that specific attributes of one variable will be found with specific attributes of another variable § These attributes of the variable happen together • Correlation: describes a relationship between two variables o Positive correlation: high attributes of one variable are paired with high attributes of another variable o Negative correlation: high attributes of one variable paired with low attributes of another variable o These must be measurable minimally at the ordinal level and they must have an actual value Correlation: • You can have a high positive correlation or a low positive correlation o The closer the co-efficient is to either +1.00 or -1.00 the stronger or higher the correlation o The closer the co-efficient is to zero, the lower or weaker the correlation • You can have a high negative correlation or a low negative correlation • There can also be no systematic relationship between the variables (no correlation or a zero correlation) o The coefficients would hover around zero indicating no relationship § +.08, -.07 § These coefficients are so low that we cannot state there is any correlation between the variables under investigation § If we measured height for a group of students and compared these to the scores on a statistics test for that group of students, we are unlikely to find a correlation Positive Correlations: • Remember a correlation is when two variables fluctuate together • A positive correlation is when two variables fluctuate in parallel with one another o Variable A increases as variable B increases o Variable A decreases as variable B decreases o The increase or decrease is going in the same direction Negative Correlation: • When attributes in one variable go up the attributes in the other variable go down o It is like a see-saw, as one goes up the other goes down, when they are in the middle there is no correlation Covariance: • When attributes of one variable are found disproportionately with specific attributes of another variable • Basically how much two random variables fluctuate or vary together • When you have two attributes of one variable, you also find attributes of the other variable Independent Variables: • This is the variable that is predicted to or actually influences another variable • We can think of it as the predictor variable • Calorie consumption influences weight o Which is the independent variable? § Calorie consumption § Weight Dependent Variables: • These are the variables that are influenced by another variable • This is the variable that we are interested in and the levels of change as a result of an independent variable • We do not manipulate the dependent variable o If anxiety is the dependent variable, then independent variables could be different doses of a medication to reduce anxiety § Our hope is that the medication will reduce anxiety § Anxiety is the dependent variable Confounding (Extraneous) Variables: • These occur with or happen in a way that their effects or impact cannot be separated clearly • This “confuses” our ability to interpret the impact of the independent variables on our dependent variable o These make it difficult for us to clearly separate the relationship between dependent and independent variables • These may also be referred to as o Antecedent variables o Obscuring variables o Intervening variables
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'