Textbook Notes (363,232)
Canada (158,276)
Sociology (1,668)
Neil Holt (8)
Chapter 11

Research Methods - Chapter 11.doc

4 Pages
Unlock Document

Western University
Sociology 2206A/B
Neil Holt

Research Methods Chapter 11: Analysis of Quantitative Data [Introduction] - Analysis is complex field of knowledge [Dealing with Data] Coding Data - Systematically reorganizing raw numerical data into a format that is easy to analyze using computers - Hard when data is not organized or in form of numbers - Develop rules to assign numbers variables - Codebook: document describing the coding procedure and location for data that computers can use Entering Data - Needed in grid format - Each row represents respondent, subject, case - Columns represent specific variables - 4 ways to get Quantitative data into a computer: 1. Code Sheet: gather info, transfer from original to grid, type in info line by line 2. Direct-Entry Method: include CATI, as info is collected it is imputed 3. Optical Scan: gather info, enter into optical scan sheets by filling in correct “dots”, use optical scanner to transfer info to computer – LIKE SCANTRON 4. Bar Code: gather info, convert into different widths of bars that are associate with specific numerical values, use bar-code reader to transfer info to computer Cleaning Data - Verify coding in 2 ways: 1. Possible Code Cleaning: (wild code checking) checking categories of all variables for impossible codes 2. Contingency Cleaning: (consistency checking) cross-classifying two variables and looking for logically impossible combinations [Results with One Variable] Frequency Distributions Descriptive Statistics: describe numerical data Univariate Statistics: describe one variable Frequency Distribution: easiest way to describe numerical data of ONE VARIABLE - Done in histogram or bar/pie charts Research Methods Chapter 11: Analysis of Quantitative Data Measures of Central Tendency Mean (used with interval and ratio levels), Median (used with ordinal, interval, ratio levels) , Mode (used with all 4 levels of measurement) - Normal and Skewed distribution Measures of Variation Range: consists of largest and smallest scores (ordinal, interval ratio) Percentiles: tell the score at a specific place within a distribution (ordinal, interval ratio) Standard Deviation: measure of dispersion; most difficult to compute (interval, ratio); used for comparisons Z-scores: compare two or more distributions; expresses points or score on a frequency distribution in terms of a number of standard deviations from the mean [Results with Two Variables] Bivariate Relationship - considers 2 variables and describe relationship between them - Covariation: means things go together; associated - Independence: no association Seeing the Relationship: Scattergram - graph which researcher plots each observation - constructed by range of 2 variables, with axis - Tell reader 3 things: - Form: - Independence – no relationship - Linear – middle line from corner to corner - Curvilinear – form a u (or inverted u), or s curve - Direction: - Positive – lower left  upper right - Negative – upper left  lower right - Precision: amount of spread in points on graph - High = when points hug line of best fit - Low = points widely spread around line Bivariate Tables (Contingency table) - Table based on Cross-Tabulation: cases organized in
More Less

Related notes for Sociology 2206A/B

Log In


Don't have an account?

Join OneClass

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

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.