Week 5 of notes
Week 5 of notes 400
Popular in Research in Political Science
Popular in Public Relations
This 3 page Class Notes was uploaded by Dora Notetaker on Friday September 25, 2015. The Class Notes belongs to 400 at University of Alabama at Birmingham taught by John E McNulty in Summer 2015. Since its upload, it has received 57 views. For similar materials see Research in Political Science in Public Relations at University of Alabama at Birmingham.
Reviews for Week 5 of 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: 09/25/15
PSC 4002D Research in Political Science Dr McNulty Set of Notes 5 Week of Sept 21 Tue Se t22 The first problem set is on canvas and it s due a week from Tuesday on Sept 29 in class Continuing with Criteria of Causality Recap 1 Correlation 2 Time Order 3 Causal Mechanism 4 Controlling for Confounds Time Order Clock 0 Endogene y 0 One variable is related to another variable 0 Exogene y 0 One variable is completely unrelated to another variable or the rest of the variables Example Life of Julia 0 It was a cartoon made by the Obama campaign about how the government supports Julia from the age of 3 to 67 0 Julia could support Obama for any reason or some but not others or all reasons Causal Mechanism 0 It is a hypothetical process about how a change in the dependent variable will change the independent variable 0 It answers why 0 Like why does poverty cause political strife 0 Or why does water turn to steam when heat is introduced Controlling for Confounds 0 Time order is related to this We may see a correlation between the independent and the dependent variable 0 X affects Y 0 Julia is prochoice gt She will vote for the prochoice candidate Confounds are other explanations that could be causing the change in the independent variable Example The number of murders in a community relates to the amount of ice cream sold in that community more ice cream more murder X gt Y ice cream gt murders But Z is the confounding variable that affects them both Z heat I People buy more ice cream when it is hot I And tempers flare more quickly when it39s hot How would you control for a confounding variable 0 Hold a constant I Only look at murder rates in a specific period Like the summer Look at what days weekends So you have to control for the months June August the days of the week weekends I and the hours of day evenings When you control for a confound the proposed relationship between X and Y goes away You need 2 things for a confounding variable 0 1 You need Z to cause Y Z gtY o 2 You need X to correlate with Z XZ You can never rule out confounds completely 0000 4 C s of causality 1 2 3 4 Correlation Clock Causal Mechanism Controlling for Confounds Thursday Sept 24 2015 Measures of Central Tendency Mode 0 The most frequently occurring value 0 Nominal Ordinal Scale Median o The middle value when data are sorted in order 0 Ordinal Scale Mean Average o The sum of the values divided by the number of cases 0 Scale 0 Scale a ratio when describing a level of measurement Example Ranking things from excellent to poor Excellent Very Good Good Fair Poor 8 15 17 8 2 In this case your median would be Good If it is a number not a categorical value it can be averaged to show the median Because when you have an even number of cases your median will be an average So if you have 50 cases like above you can average 2527 to get a median Mode o It is important even if it tells you little it can be significant 0 Examples 0 Modal race in the US white 0 Modal religion in the US Christian But central tendencies don t tell you everything you have to worry about spread Measures of spread o What is spread o The dispersion of data 0 How far data ranges from the central tendency How is spread determined displayed 1 Visually a Scatterplots b Histograms c Barchans d Pie charts 0 Example When you use central tendency to determine that the average age in a college classroom and an elementary school are both around 24 but they are 2 very different data sets 2 Numerically a Nominal i Can t really do it list only ii Think of it as buckets of numbers b Ordinal i Buckets put in order ii Percentiles tenths Deciles hundredths Quintiles fifths Quartiles fourths c Scale i Standard Deviation
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'