This document outlines common statistical inference formulas and procedures, including:
- Z-tests, t-tests, and confidence intervals for one and two sample proportions and means.
- Chi-square tests for goodness of fit, homogeneity, and independence to analyze categorical data.
- Linear regression to model the relationship between independent and dependent variables and test for a linear trend.
It provides the null hypotheses, test statistics, and confidence intervals/formulas for each test based on the sampling and data assumptions.
Copyright:
Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOC, PDF, TXT or read online from Scribd
This document outlines common statistical inference formulas and procedures, including:
- Z-tests, t-tests, and confidence intervals for one and two sample proportions and means.
- Chi-square tests for goodness of fit, homogeneity, and independence to analyze categorical data.
- Linear regression to model the relationship between independent and dependent variables and test for a linear trend.
It provides the null hypotheses, test statistics, and confidence intervals/formulas for each test based on the sampling and data assumptions.
Original Description:
Contain Statistics Test formulas (Ex: 1-sample Z test, T test, paired test...)
This document outlines common statistical inference formulas and procedures, including:
- Z-tests, t-tests, and confidence intervals for one and two sample proportions and means.
- Chi-square tests for goodness of fit, homogeneity, and independence to analyze categorical data.
- Linear regression to model the relationship between independent and dependent variables and test for a linear trend.
It provides the null hypotheses, test statistics, and confidence intervals/formulas for each test based on the sampling and data assumptions.
Copyright:
Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOC, PDF, TXT or read online from Scribd
This document outlines common statistical inference formulas and procedures, including:
- Z-tests, t-tests, and confidence intervals for one and two sample proportions and means.
- Chi-square tests for goodness of fit, homogeneity, and independence to analyze categorical data.
- Linear regression to model the relationship between independent and dependent variables and test for a linear trend.
It provides the null hypotheses, test statistics, and confidence intervals/formulas for each test based on the sampling and data assumptions.
Copyright:
Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOC, PDF, TXT or read online from Scribd
Situation/Tes Conditions Null Hypothesis Test Statistic Confidence Interval
t 1 sample z 1. SRS H 0 :µ = µ − µ σ z= x ± test And either: σ 2. Pop is normal, or large sample size ( n ≥ ), or if n<30, the sample dist is not severely skewed and does not have extreme outliers. 2 sample z Same as above for BOTH H 0 : µ = µ − − µ − µ σ σ z= test samples or (x1 − ± + σ σ + H 0 : µ − µ = 1 sample t 1. SRS H 0 :µ = µ − µ t= x ± ; df = n-1 test and either: ; df = n-1 2. Pop is normal, or n>40 (even if skewed & outliers), or 15<n<40 with npp showing little skewness, or n<15 with npp showing no outliers and no skewness 2 sample t 1. Populations are H 0 :µ = µ − − µ − µ t= test independent (x1 − ± + ; df = n-1 2. Same as above, replace + n with n1 + Matched Same as 1 sample t test H 0 :µ = − µ t= x ± ; df = n-1 pairs where µ d is the ; df = n-1 t test difference of dependent sample means 1 proportion 1. SRS H 0 : p = − − z= pö ± z test 2. Population ≥ 10n − 3. CI: npö ≥ , n(1 − ≥ HT: np0 ≥ , n(1 − ≥ (Verify use of normal approx) 2 proportion 1. Populations are H 0 : p1 = − − − − − z= ( pö1 − ± + z test independent or 2. SRS (both samples) H 0 : p1 − = − + 3. Populations ≥ 10n 4. CI: n1 pö1 ≥ , n1 (1 − ≥ + n2 pö2 ≥ , n2 (1 − ≥ where pö = + HT: n1 pö ≥ , n1 (1 − ≥ n2 pö ≥ , n2 (1 − ≥ (Verify use of normal approx) Chi Square 1. All expected counts ≥ 1 H 0 : Actual (O - E)2 One-way table Goodness of 2. 80% of expected counts proportions are χ2 = å Single SRS, one categorical E Fit ≥ 5 equal to df = k-1 variable hypothesized k = # of categories proportions Chi Square Same as above. H 0 : Proportions (O - E)2 Two-way table Homogeneit are all equal or a χ2 = å Two SRS, two categorical E y fixed value df = (r-1)(c-1) variables Chi Square Same as above. H 0 : No associations (O - E)2 Two way table Independenc between variables χ2 = å Single SRS, two categorical E e or the variables are df = (r-1)(c-1) variables independent of each other Linear 1. Independent ordered H 0 :β = no linear b ± ; df = n-2 t= , df = n-2 Regression; pairs relationship regression 2. Roughly linear between the two slope scatterplot variables 3. Standard deviation of response is constant (scatter around LSRL is consistent) 4. Response variable varies normally (residuals are approx normal)