Stats Test 1 Notes.doc

6 Pages
Unlock Document

Shirin Montazer

CH.1 The stages of social research 1. research qs 2. hypothesis 3. method 4. collect data 5. analyze data - Experiment; a type of research where the researcher manipulates one or more independent variables. - Experimental also known as a treatment group; the group that is manipulated - Control group; the group is not manipulated - Participant observation; research where the researcher participates in the daily life of study. - Secondary analysis; use data that was collected by other researchers - Qualitative data; a set of observation where any single observation is a word or code that represents a class or category (use a small N, open ended interviews) - Quantitative data; a set of observation where a single observation is a number that represents an amount or count (use large N) - Variable; characteristics that differ from one individual to the other - Hypothesis; a statement of relationship between 2 or more variables - Dependent variable; the presumed outcome or effect resulting from some treatment or exposure. - Independent variable; presumed cause or influence affecting the dependent variable. Level of measurement - nominal; involves naming or labelling not in order - ordinal; involves the ordering of categories - interval; ordering and exact distance ($, degrees, yrs of education) - ratio level; same as interval but includes an absolute or zero point( age, hours worked) Discrete variable; separate and distinct specific values (gender, religion, # of dependents) Continuous variable; infinite range of possible values (weight, age, income) 2 functions of stats; inferential and descriptive Ch.2 Frequency distribution 2 popular methods: - Proportion; number of cases compared to the total size of distribution P= f/n - Percentage; the frequency per 100 cases %= (100) f/n - ordinal and interval data must be in a sequence order in a frequency table - class intervals must be mutually exclusive. Ex; 1-5, 6-10 NOT =>1-5, 5-10 - whole numbers preferable to decimals - Steps of constructing frequency distribution 8. specify the number of class intervals 9. The largest data- the smallest data/ number of classes= class width (w=l-s/k) Stated vs. True Limits - true classes; classes that upper true (or real) limit of that class is the same as the lower true limit of the next class - stated classes; those classes that we see in grouped frequency Bottom of interval: 1/2unit below stated & Top of interval: 1/2 unit above stated - The number of decimal places of stated limits determines the number of zeros before the ``5`` that is subtracted or added to obtain the true limit (1 decimal place =.05; 2 decimal places= .005, etc The Midpoint - class intervals have a midpoint - Midpoint- SUM of the lowest and highest scores divided by 2. M= LS+HS/2 Cumulative Distributions - cf is cumulative frequencies. They are the total # of cases having any given score or a score that is lower. The cumulative frequency for any category or class interval is obtained by adding frequency in that category to the total frequency for all categories. - Cumulative percentage –percentage of cases having any score or a lower score. c%=(100) cf/N Cross Tabulations -frequency distributions of each variable separately can be found along the margins of a 2 way cross tabulation is called “marginal distributions” •Rule of Thumb: •If the independent variable is on the rows, use row percents. Row %= (100) f/N row •If the independent variable is on the columns, use column percents. Col %= (100) f/N column •If the independent variable is unclear –use whichever is most meaningful. •IN OUR CASE: we use column percentages because the independent variable is on the column Graphs - pie charts are good for nominal data - Bar graphs used primarily for discrete variables - Histograms used to show continuity along a scale - Frequency polygons useful for ordinal and interval data Ch.3 - 3 main types: mean, median and mode - Mode; most frequent value in a distribution. Unimodal- 1 mode, Bimodal- 2 mode - Median is the middle case of a distribution Md= n+1/2 (n= odd number of cases) Even= no middle cases then Md= n/2 case…(n/2)+1 and the value in between 2 numbers average it (a+b/2) - Mean X= Ex/N X=mean Sum= E X = raw scores in a set of scores N = total number of scores in a set - Three factors in choosing a measure of central tendency 1. Level of measurement 2. Shape or form of the distribution of data 3. Research Objective - In symmetrical distribution –mode, median, and mean have identical values - In skewed data, the measures of central tendency are different - Mean is always near and towards the skewed graph x = md1f1+ md2f2+ md3f3n - Deviation; distance and direction of any raw score from the mean. D= x (any raw score)- _X(mean of the distribution). The greater the deviation, the greater is the distance of that raw score from the mean of the distribution. CH 4 Measure of variability - range= difference between the highest and lowest scores in a distribution. R=H-L The variance and standar
More Less

Related notes for SOCC31H3

Log In


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.