Formula Review

10.1 Two Population Means with Unknown Standard Deviations

Standard error SE = (s1)2n1+(s2)2n2(s1)2n1+(s2)2n2

Test statistic (t-score) t = (x¯1x¯2)(μ1μ2)(s1)2n1+(s2)2n2(x¯1x¯2)(μ1μ2)(s1)2n1+(s2)2n2

Degrees of freedom


 
df= ((s1)2n1+ (s2)2n2)2(1n11)((s1)2n1)2+(1n21)((s2)2n2)2df= ((s1)2n1+ (s2)2n2)2(1n11)((s1)2n1)2+(1n21)((s2)2n2)2

where

s1 and s2 are the sample standard deviations, and n1 and n2 are the sample sizes.

x¯1x¯1 and x¯2x¯2 are the sample means.

Cohen’s d is the measure of effect size

d=x¯1x¯2spooledd=x¯1x¯2spooled


 
where spooled=(n11)s12+(n21)s22n1+n22.spooled=(n11)s12+(n21)s22n1+n22.

10.2 Two Population Means with Known Standard Deviations

Normal distribution

 
X¯1X¯2N[μ1μ2,(σ1)2n1+(σ2)2n2]X¯1X¯2N[μ1μ2,(σ1)2n1+(σ2)2n2].

 
Generally µ1µ2 = 0.

Test statistic (z-score)


 
z=(x¯1x¯2)(μ1μ2)(σ1)2n1+(σ2)2n2z=(x¯1x¯2)(μ1μ2)(σ1)2n1+(σ2)2n2

 
Generally µ1 - µ2 = 0

where

 
σ1 and σ2 are the known population standard deviations, n1 and n2 are the sample sizes, x¯1x¯1 and x¯2x¯2 are the sample means, and μ1 and μ2 are the population means.

10.3 Comparing Two Independent Population Proportions

Pooled proportion pc = xF + xMnF + nMxF + xMnF + nM

Distribution for the differences


 
pApBN[0,pc(1pc)(1nA+1nB)]pApBN[0,pc(1pc)(1nA+1nB)]

where the null hypothesis is H0: pA = pB or H0: pApB = 0.

Test statistic (z-score): z=(pApB)pc(1pc)(1nA+1nB)z=(pApB)pc(1pc)(1nA+1nB)

where the null hypothesis is H0: pA = pB or H0: pApB = 0

and where

p′A and p′B are the sample proportions, pA and pB are the population proportions,

Pc is the pooled proportion, and nA and nB are the sample sizes.

10.4 Matched or Paired Samples (Optional)

Test statistic (t-score): t = x¯dμd(sdn)x¯dμd(sdn)

where

x¯dx¯d is the mean of the sample differences, μd is the mean of the population differences, sd is the sample standard deviation of the differences, and n is the sample size.