Study Guides (248,337)
Canada (121,491)
Commerce (386)
COMM 291 (11)
Midterm

# The Return of The Greatest Stats Sheet Ever..pdf

6 Pages
141 Views

Department
Commerce
Course
COMM 291
Professor
Jonathan Berkowitz
Semester
Winter

Description
T HE R ETURN OF THE G REATEST S TATS S HEET EVER BERKOWITZ –“W HAT T OU SEW HEN T ABLE” Type of Test Outcome Variable (Y) Explanatory Variable (X) Two Sample t-test Measurement Binary ( 2 categories ex. M/F) Two Sample z-test Binary (M/F) Binary (B/W) χ test Categoric (≥2 categories) Categoric(≥2 categories) Simple Linear Regression Measurement Measurement Multiple Linear Regression Measurement Many Measurements or Categoric One-Way ANOVA Measurement Categoric “t” for means, “z” for proportions Questions to ask in pursuit of an appropriate hypothesis test: 1.▯ What kind of data do you have? Measurement/ Binary/ Categoric 2.▯ What parameter is of interest? Mean/ Proportion 3.▯ How many populations/samples do you have? ▯▯ is there matching or pairing? B ERKOWITZ ON “ERROR ” Ho is true Ho is false Accept Ho Correct Type II error Reject Ho Type I error Correct Ho: Defendant is not guilty Type I error – False positive (convict an innocent person) Pr(Type I error) = α Type II error – False negative (let a guilty person go free) Pr(Type II error) = β Power = Pr(correctly rejecting Ho) = (1-β) Test-statistic affects power: power goes up as Z increases)- σ , n , ( 0 ▯▯ by increasing n you reduce the chance of getting errors. A DDITIONAL FORMULAS N OT INCLUDED IN O VERVIEW T ABLE To find a required sample size in a One-sample z-test for p with given margin of error (E): z2α p(1− p) n = 2* E2 If 95% confidence interval(generally the ͧse…):; E= Margin of Error 1 n1 n2 2 1 2 2 2 n s ns 1 2 − n ▯ σ ▯ ▯ ▯ p 1 2 ▯ α, ▯ ( ) ▯ α 2 αdf = + − df p p ± ▯where▯ ▯wher1▯ 1 α2 x z n d n df n n = − − s s df n± n α,2 df − ± +1 2± + p z df x1 x2 whet s ( x ) t2 ± ± = − ( = − ) Confidence▯Interval▯(α=1▯C)▯ d t df n df n ▯where▯ min( 1, 1) 2 0 2 + − 2 0 ▯ n ▯0 0 + 1 2 − n ▯−▯ ▯σ▯ ▯− s n ▯ − s d n ▯ 1 n1 −2 n + n ▯ − 2 1+ 212 2▯− 1( ) ▯ x x d d − − 1 1 −2 s − 2s n p p0 p0 = = = x1 xsp D 0( 1) x1 x21) D 0 z t t ( ) ( ) Test▯Statistic▯ = = = z t sp t ABLE T where▯▯ VERVIEW O 0 0 2 ▯0▯ ▯2 ▯0▯ 0 ▯ ▯ 0 ▯ ▯2 ▯=≠<> 2 ▯=0≠<> ▯0 Hypotheses▯ 0 =d 0 =▯ ≠<>▯ ▯▯▯▯ =▯≠<>▯ ▯▯ ▯▯ ▯=▯≠<>▯ ▯=▯▯=<>▯ ▯ ▯≠d ▯1 ▯ ▯ ▯1 ▯ ▯1 ▯1 ▯ =p P=<>p 0▯a▯ :0 a▯ 0▯:a 0could▯be:0)a▯ 0▯:a 0▯:a :0 a▯ :0Pa▯ H H H H H H (d H H ▯▯▯▯Or▯▯▯▯▯▯ H H ▯▯▯▯Or▯▯▯▯▯ H H ▯ ▯ = )▯ )▯ 1 2 σ ssmaller smaller ▯ ▯2med ▯10▯ σis▯known▯ ▯10▯ Assumptions▯ sbigger▯ ≠1 sig2er▯ n n(1Not▯Normality▯ ▯ ▯▯CLT▯(lar▯▯N▯rmealtd▯ent▯Popns▯srn▯femt.ed σ (if▯σ ▯Normality▯(small▯n)▯ ▯ ▯ ▯ ▯d −1 2 1 2 s ▯ ▯ ▯ ▯ s ▯ ▯ ▯ )▯ ▯ 0 Test▯ Ontee▯ss▯orple▯Zt▯tesm▯foMe▯attteet▯▯pati▯sat▯ver▯sion)▯ti9Tewt▯tfs▯m▯p▯le▯ooled▯ne▯▯tamtpf▯ ▯ ▯ ▯ ▯ ▯ ▯ ) ) b b0 ( ( SE SE version▯above▯ × × p ▯▯▯▯ − − ▯▯▯ , 2 α,2 t t ± ±0 b b 1 0: same▯as▯pooled Note▯further▯calc’s▯listed▯on▯last▯page… Confidence▯Interval▯(α=1▯C)▯ CI for β CI for β ----------------------------------------- ▯ 2 ) ) 0 0 0 b1 ( ) ij − ( − ( −ij E ij b0 SE b1 SE ) O E 0---- = ▯ + ( ) t t ▯ − − p −p 1D 0 − ∑ all cells------β ------β1-----F= MSM/MSE F=MSM/MSE▯ ( ( n ) 1= n Where▯df=(r▯1)(c▯1)▯ F= MSM/MSE Where▯df=DFE=N▯p▯▯ Test▯Statistp1▯ p1 p2 p2 Test-stat: Test-stat:
More Less

Related notes for COMM 291
Me

Log In

OR

Join OneClass

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

Sign up

Join to view

OR

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.

Request Course
Submit