Discussion Week 1 (4/1/13 – 4/5/13)

Slides:

Advertisements

Similar presentations

Two-sample tests. Binary or categorical outcomes (proportions) Outcome Variable Are the observations correlated?Alternative to the chi- square test if.

Advertisements

Analysis of Categorical Data Nick Jackson University of Southern California Department of Psychology 10/11/

Slide Slide 1 Copyright © 2007 Pearson Education, Inc Publishing as Pearson Addison-Wesley. Lecture Slides Elementary Statistics Tenth Edition and the.

Contingency Tables Chapters Seven, Sixteen, and Eighteen Chapter Seven –Definition of Contingency Tables –Basic Statistics –SPSS program (Crosstabulation)

Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.

Simple Logistic Regression

Matched designs Need Matched analysis. Incorrect unmatched analysis. cc cc exp,exact Proportion | Exposed Unexposed | Total Exposed

1 If we live with a deep sense of gratitude, our life will be greatly embellished.

EPI 809 / Spring 2008 Final Review EPI 809 / Spring 2008 Ch11 Regression and correlation  Linear regression Model, interpretation. Model, interpretation.

Measures of Disease Association Measuring occurrence of new outcome events can be an aim by itself, but usually we want to look at the relationship between.

Basic epidemiologic analysis with Stata

BIOST 536 Lecture 3 1 Lecture 3 – Overview of study designs Prospective/retrospective  Prospective cohort study: Subjects followed; data collection in.

Sociology 601 Class12: October 8, 2009 The Chi-Squared Test (8.2) – expected frequencies – calculating Chi-square – finding p When (not) to use Chi-squared.

Notes on Logistic Regression STAT 4330/8330. Introduction Previously, you learned about odds ratios (OR’s). We now transition and begin discussion of.

Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.

Review for Exam 2 Some important themes from Chapters 6-9 Chap. 6. Significance Tests Chap. 7: Comparing Two Groups Chap. 8: Contingency Tables (Categorical.

The Chi-Square Test Used when both outcome and exposure variables are binary (dichotomous) or even multichotomous Allows the researcher to calculate a.

Biostat 200 Lecture 8 1. Hypothesis testing recap Hypothesis testing – Choose a null hypothesis, one-sided or two sided test – Set , significance level,

Analysis of Categorical Data

September 15. In Chapter 18: 18.1 Types of Samples 18.2 Naturalistic and Cohort Samples 18.3 Chi-Square Test of Association 18.4 Test for Trend 18.5 Case-Control.

Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.

EPI 811 – Work Group Exercise #2 Team Honey Badgers Alex Montoye Kellie Mayfield Michele Fritz Anton Frattaroli.

1 Applied Statistics Using SAS and SPSS Topic: Chi-square tests By Prof Kelly Fan, Cal. State Univ., East Bay.

Dr.Shaikh Shaffi Ahamed Ph.D., Dept. of Family & Community Medicine

Basic epidemiologic analysis with Stata Biostatistics 212 Lecture 5.

Bandit Thinkhamrop, PhD. (Statistics) Department of Biostatistics and Demography Faculty of Public Health Khon Kaen University, THAILAND.

April 4 Logistic Regression –Lee Chapter 9 –Cody and Smith 9:F.

Analysis of Qualitative Data Dr Azmi Mohd Tamil Dept of Community Health Universiti Kebangsaan Malaysia FK6163.

Biostat 200 Lecture 8 1. The test statistics follow a theoretical distribution (t stat follows the t distribution, F statistic follows the F distribution,

Please turn off cell phones, pagers, etc. The lecture will begin shortly.

BIOST 536 Lecture 1 1 Lecture 1 - Introduction Overview of course  Focus is on binary outcomes  Some ordinal outcomes considered Simple examples Definitions.

Biostat 200 Lecture 8 1. Where are we Types of variables Descriptive statistics and graphs Probability Confidence intervals for means and proportions.

Tests of Association (Proportion test, Chi-square & Fisher’s exact test) Dr.L.Jeyaseelan Dept.of Biostatistics Christian Medical College Vellore, India.

Henrik Støvring Basic Biostatistics - Day 4 1 PhD course in Basic Biostatistics – Day 4 Henrik Støvring, Department of Biostatistics, Aarhus University©

1 G Lect 7a G Lecture 7a Comparing proportions from independent samples Analysis of matched samples Small samples and 2  2 Tables Strength.

Types of Categorical Data Qualitative/Categorical Data Nominal CategoriesOrdinal Categories.

Exact Logistic Regression

THE CHI-SQUARE TEST BACKGROUND AND NEED OF THE TEST Data collected in the field of medicine is often qualitative. --- For example, the presence or absence.

Doing Analyses on Binary Outcome. From November 14 th Dr Sainani talked about how the math works for binomial data.

EPI 811 WORK GROUP EXERCISE #1 Team Honey Badgers Alex Montoye Kellie Mayfield Michele Fritz Anton Frattaroli.

Dr.Shaikh Shaffi Ahamed Ph.D., Dept. of Family & Community Medicine

Fall 2002Biostat Inference for two-way tables General R x C tables Tests of homogeneity of a factor across groups or independence of two factors.

Bandit Thinkhamrop, PhD. (Statistics) Department of Biostatistics and Demography Faculty of Public Health Khon Kaen University, THAILAND.

Megan Templin, MPH, M.S. H. James Norton, PhD Dickson Advanced Analytics Research Division Carolinas Healthcare System.

Categorical data analysis

March 28 Analyses of binary outcomes 2 x 2 tables

Sample size calculation

BINARY LOGISTIC REGRESSION

Advanced Quantitative Techniques

Notes on Logistic Regression

The binomial applied: absolute and relative risks, chi-square

Lecture 8 – Comparing Proportions

Random error, Confidence intervals and P-values

Chapter 18 Cross-Tabulated Counts

Examples and SAS introduction: -Violations of the rare disease assumption -Use of Fisher’s exact test January 14, 2004.

Chapter 18 Cross-Tabulated Counts Part A

Lecture Slides Elementary Statistics Tenth Edition

Risk ratios 12/6/ : Risk Ratios 12/6/2018 Risk ratios StatPrimer.

If we can reduce our desire,

Statistical Analysis using SPSS

Categorical Data Analysis

Applied Statistics Using SPSS

Applied Statistics Using SPSS

Common Statistical Analyses Theory behind them

A Brief Introduction to Stata(2)

Research Techniques Made Simple: Interpreting Measures of Association in Clinical Research Michelle Roberts PhD,1,2 Sepideh Ashrafzadeh,1,2 Maryam Asgari.

Summary of Measures and Design 3h

Chapter 18 Part C: Matched Pairs

Summary of Measures and Design

Presentation transcript:

Discussion Week 1 (4/1/13 – 4/5/13) Biostat 513 Discussion Week 1 (4/1/13 – 4/5/13)

Aims Review key Stata commands OR RR RD Data manipulation Categorical data OR RR RD Data manipulation

Stata tab, tabi – basic tabling cs, csi – analysis of prospective/cross-sectional studies, single binary covariate cc, cci – analysis of case-control studies, single binary covariate mcc, mcci – analysis of matched data epitab – “help epitab” provides summary of most relevant commands expand – expand summary dataset reshape – convert between long and wide formats

UGDP The ugdp.dta dataset describes the results from a drug trial among diabetics. The exposure (exposed) is tolbutamide, and the outcome (case) is death within a fixed time period. The dataset is provided in tabular form with pop indicating the number of subjects in each cell.

use http://courses. washington. edu/b513/datasets/ugdp. dta . use http://courses.washington.edu/b513/datasets/ugdp.dta . list +----------------------------+ | age case exposed pop | |----------------------------| 1. | <55 0 0 115 | 2. | <55 0 1 98 | 3. | <55 1 0 5 | 4. | <55 1 1 8 | 5. | 55+ 0 0 69 | 6. | 55+ 0 1 76 | 7. | 55+ 1 0 16 | 8. | 55+ 1 1 22 |

use http://courses. washington. edu/b513/datasets/ugdp. dta . use http://courses.washington.edu/b513/datasets/ugdp.dta . list +----------------------------+ | age case exposed pop | |----------------------------| 1. | <55 0 0 115 | 2. | <55 0 1 98 | 3. | <55 1 0 5 | 4. | <55 1 1 8 | 5. | 55+ 0 0 69 | 6. | 55+ 0 1 76 | 7. | 55+ 1 0 16 | 8. | 55+ 1 1 22 | . tab case exposed | exposed case | 0 1 | Total -----------+----------------------+---------- 0 | 2 2 | 4 1 | 2 2 | 4 Total | 4 4 | 8

use http://courses. washington. edu/b513/datasets/ugdp. dta . use http://courses.washington.edu/b513/datasets/ugdp.dta . list +----------------------------+ | age case exposed pop | |----------------------------| 1. | <55 0 0 115 | 2. | <55 0 1 98 | 3. | <55 1 0 5 | 4. | <55 1 1 8 | 5. | 55+ 0 0 69 | 6. | 55+ 0 1 76 | 7. | 55+ 1 0 16 | 8. | 55+ 1 1 22 | . tab case exposed | exposed case | 0 1 | Total -----------+----------------------+---------- 0 | 2 2 | 4 1 | 2 2 | 4 Total | 4 4 | 8

use http://courses. washington. edu/b513/datasets/ugdp. dta . use http://courses.washington.edu/b513/datasets/ugdp.dta . list +----------------------------+ | age case exposed pop | |----------------------------| 1. | <55 0 0 115 | 2. | <55 0 1 98 | 3. | <55 1 0 5 | 4. | <55 1 1 8 | 5. | 55+ 0 0 69 | 6. | 55+ 0 1 76 | 7. | 55+ 1 0 16 | 8. | 55+ 1 1 22 | . tab case exposed [freq=pop] | exposed case | 0 1 | Total -----------+----------------------+---------- 0 | 184 174 | 358 1 | 21 30 | 51 Total | 205 204 | 409

Common options for tab: by, chi2, exact, row, col, missing . expand pop (401 observations created) . tab case exposed | exposed case | 0 1 | Total -----------+----------------------+---------- 0 | 184 174 | 358 1 | 21 30 | 51 Total | 205 204 | 409 . tabi 30 21 \ 174 184 | col row | 1 2 | Total 1 | 30 21 | 51 2 | 174 184 | 358 Total | 204 205 | 409 Fisher's exact = 0.181 1-sided Fisher's exact = 0.112 Common options for tab: by, chi2, exact, row, col, missing

. bysort age: tab case exposed ----------------------------------------------------------------------------------- -> age = <55 | exposed case | 0 1 | Total -----------+----------------------+---------- 0 | 115 98 | 213 1 | 5 8 | 13 Total | 120 106 | 226 -> age = 55+ 0 | 69 76 | 145 1 | 16 22 | 38 Total | 85 98 | 183

Why choose column percents? . tab case exposed, chi2 exact col +-------------------+ | Key | |-------------------| | frequency | | column percentage | | exposed case | 0 1 | Total -----------+----------------------+---------- 0 | 184 174 | 358 | 89.76 85.29 | 87.53 1 | 21 30 | 51 | 10.24 14.71 | 12.47 Total | 205 204 | 409 | 100.00 100.00 | 100.00 Pearson chi2(1) = 1.8651 Pr = 0.172 Fisher's exact = 0.181 1-sided Fisher's exact = 0.112 Why choose column percents? Which Fisher’s test corresponds to the chi-squared test?

Why choose column percents? P(died | exp) . tab case exposed, chi2 exact col +-------------------+ | Key | |-------------------| | frequency | | column percentage | | exposed case | 0 1 | Total -----------+----------------------+---------- 0 | 184 174 | 358 | 89.76 85.29 | 87.53 1 | 21 30 | 51 | 10.24 14.71 | 12.47 Total | 205 204 | 409 | 100.00 100.00 | 100.00 Pearson chi2(1) = 1.8651 Pr = 0.172 Fisher's exact = 0.181 1-sided Fisher's exact = 0.112 Why choose column percents? P(died | exp) Which Fisher’s test corresponds to the chi-squared test?

Better to use cs or cc for these data? why? Okay or not to use the other? why?

Better to use cs or cc for these data? why? prospective study Okay or not to use the other? why?

Better to use cs or cc for these data? why? prospective study Okay or not to use the other? why? OR is fine to report

Better to use cs or cc for these data? why? Okay or not to use the other? why? . cs case exposed, or | exposed | | Exposed Unexposed | Total -----------------+------------------------+------------ Cases | 30 21 | 51 Noncases | 174 184 | 358 Total | 204 205 | 409 | | Risk | .1470588 .102439 | .1246944 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | .0446198 | -.0192936 .1085332 Risk ratio | 1.435574 | .8510221 2.421645 Attr. frac. ex. | .3034146 | -.1750577 .5870576 Attr. frac. pop | .1784792 | Odds ratio | 1.510673 | .8381198 2.722012 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Note “exposed, case” in upper left. Interpret OR and RR.

Predict the RD, RR and OR for each of these csi <exposed cases> <unexposed cases> <exposed controls> <unexposed controls> . csi 30 21 174 184, or | Exposed Unexposed | Total -----------------+------------------------+------------ Cases | 30 21 | 51 Noncases | 174 184 | 358 Total | 204 205 | 409 | | Risk | .1470588 .102439 | .1246944 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | .0446198 | -.0192936 .1085332 Risk ratio | 1.435574 | .8510221 2.421645 Attr. frac. ex. | .3034146 | -.1750577 .5870576 Attr. frac. pop | .1784792 | Odds ratio | 1.510673 | .8381198 2.722012 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Predict the RD, RR and OR for each of these . csi 21 30 184 174 /* switch exposed and unexposed */ . csi 174 184 30 21 /* switch death and no death */ . csi 184 174 21 30 /* switch both */

Predict the RD, RR and OR for each of these RD RR OR csi <exposed cases> <unexposed cases> <exposed controls> <unexposed controls> . csi 30 21 174 184, or | Exposed Unexposed | Total -----------------+------------------------+------------ Cases | 30 21 | 51 Noncases | 174 184 | 358 Total | 204 205 | 409 | | Risk | .1470588 .102439 | .1246944 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | .0446198 | -.0192936 .1085332 Risk ratio | 1.435574 | .8510221 2.421645 Attr. frac. ex. | .3034146 | -.1750577 .5870576 Attr. frac. pop | .1784792 | Odds ratio | 1.510673 | .8381198 2.722012 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Predict the RD, RR and OR for each of these RD RR OR . csi 21 30 184 174 /* switch exposed and unexposed */ -.045 1/1.44 1/1.5 . csi 174 184 30 21 /* switch death and no death */ . csi 184 174 21 30 /* switch both */

Predict the RD, RR and OR for each of these RD RR OR csi <exposed cases> <unexposed cases> <exposed controls> <unexposed controls> . csi 30 21 174 184, or | Exposed Unexposed | Total -----------------+------------------------+------------ Cases | 30 21 | 51 Noncases | 174 184 | 358 Total | 204 205 | 409 | | Risk | .1470588 .102439 | .1246944 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | .0446198 | -.0192936 .1085332 Risk ratio | 1.435574 | .8510221 2.421645 Attr. frac. ex. | .3034146 | -.1750577 .5870576 Attr. frac. pop | .1784792 | Odds ratio | 1.510673 | .8381198 2.722012 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Predict the RD, RR and OR for each of these RD RR OR . csi 21 30 184 174 /* switch exposed and unexposed */ -.045 1/1.44 1/1.5 . csi 174 184 30 21 /* switch death and no death */ -.045 ??? 1/1.5 . csi 184 174 21 30 /* switch both */

Predict the RD, RR and OR for each of these RD RR OR csi <exposed cases> <unexposed cases> <exposed controls> <unexposed controls> . csi 30 21 174 184, or | Exposed Unexposed | Total -----------------+------------------------+------------ Cases | 30 21 | 51 Noncases | 174 184 | 358 Total | 204 205 | 409 | | Risk | .1470588 .102439 | .1246944 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | .0446198 | -.0192936 .1085332 Risk ratio | 1.435574 | .8510221 2.421645 Attr. frac. ex. | .3034146 | -.1750577 .5870576 Attr. frac. pop | .1784792 | Odds ratio | 1.510673 | .8381198 2.722012 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Predict the RD, RR and OR for each of these RD RR OR . csi 21 30 184 174 /* switch exposed and unexposed */ -.045 1/1.44 1/1.5 . csi 174 184 30 21 /* switch death and no death */ -.045 ??? 1/1.5 . csi 184 174 21 30 /* switch both */ .045 ??? 1.5

Which of these statements is correct? | Exposed Unexposed | Total -----------------+------------------------+------------ Alive | 174 184 | 358 Died | 30 21 | 51 Total | 204 205 | 409 | | Risk | .8529412 .897561 | .8753056 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | -.0446198 | -.1085332 .0192936 Risk ratio | .9502877 | .8830483 1.022647 Prev. frac. ex. | .0497123 | -.022647 .1169517 Prev. frac. pop | .0247954 | Odds ratio | .6619565 | .3673752 1.193147 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Which of these statements is correct? The odds of death among those exposed to tolbutamide is 1.51 (1/.662) times the odds of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is 1.05 (1/.950) times the risk of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is ~1.51 (1/.662) times the risk of death among those not exposed to tolbutamide

Which of these statements is correct? | Exposed Unexposed | Total -----------------+------------------------+------------ Alive | 174 184 | 358 Died | 30 21 | 51 Total | 204 205 | 409 | | Risk | .8529412 .897561 | .8753056 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | -.0446198 | -.1085332 .0192936 Risk ratio | .9502877 | .8830483 1.022647 Prev. frac. ex. | .0497123 | -.022647 .1169517 Prev. frac. pop | .0247954 | Odds ratio | .6619565 | .3673752 1.193147 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Which of these statements is correct? The odds of death among those exposed to tolbutamide is 1.51 (1/.662) times the odds of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is 1.05 (1/.950) times the risk of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is ~1.51 (1/.662) times the risk of death among those not exposed to tolbutamide

Which of these statements is correct? | Exposed Unexposed | Total -----------------+------------------------+------------ Alive | 174 184 | 358 Died | 30 21 | 51 Total | 204 205 | 409 | | Risk | .8529412 .897561 | .8753056 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | -.0446198 | -.1085332 .0192936 Risk ratio | .9502877 | .8830483 1.022647 Prev. frac. ex. | .0497123 | -.022647 .1169517 Prev. frac. pop | .0247954 | Odds ratio | .6619565 | .3673752 1.193147 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Which of these statements is correct? The odds of death among those exposed to tolbutamide is 1.51 (1/.662) times the odds of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is 1.05 (1/.950) times the risk of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is ~1.51 (1/.662) times the risk of death among those not exposed to tolbutamide

Which of these statements is correct? | Exposed Unexposed | Total -----------------+------------------------+------------ Alive | 174 184 | 358 Died | 30 21 | 51 Total | 204 205 | 409 | | Risk | .8529412 .897561 | .8753056 | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Risk difference | -.0446198 | -.1085332 .0192936 Risk ratio | .9502877 | .8830483 1.022647 Prev. frac. ex. | .0497123 | -.022647 .1169517 Prev. frac. pop | .0247954 | Odds ratio | .6619565 | .3673752 1.193147 (Cornfield) +------------------------------------------------- chi2(1) = 1.87 Pr>chi2 = 0.1720 Which of these statements is correct? The odds of death among those exposed to tolbutamide is 1.51 (1/.662) times the odds of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is 1.05 (1/.950) times the risk of death among those not exposed to tolbutamide The risk of death among those exposed to tolbutamide is ~1.51 (1/.662) times the risk of death among those not exposed to tolbutamide

HIVNET VPS 750 individuals participating in an HIV vaccine preparedness study were administered a questionnaire at enrollment and after 6 months. Between the two questionnaires, all subjects participated in an educational program about HIV and vaccines. We focus on a single question, asking about the safety of an HIV vaccine (coded 1=correct answer, 0=incorrect).

What’s wrong with this analysis? . use http://courses.washington.edu/b513/datasets/hivnet.dta . tab q4safe0 q4safe0 | Freq. Percent Cum. ------------+----------------------------------- 0 | 331 44.13 44.13 1 | 419 55.87 100.00 Total | 750 100.00 . tab q4safe6 q4safe6 | Freq. Percent Cum. 0 | 254 33.87 33.87 1 | 496 66.13 100.00 . cci 496 419 254 331 Proportion | month 6 month 0 | Total Exposed -----------------+------------------------+------------------------ correct | 496 419 | 915 0.5421 incorrect | 254 331 | 585 0.4342 Total | 750 750 | 1500 0.5000 | | | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Odds ratio | 1.542631 | 1.244963 1.911765 (exact) Attr. frac. ex. | .3517567 | .1967632 .4769231 (exact) Attr. frac. pop | .190679 | +------------------------------------------------- chi2(1) = 16.61 Pr>chi2 = 0.0000 What’s wrong with this analysis?

What’s wrong with this analysis? Paired data! (McNemar) . use http://courses.washington.edu/b513/datasets/hivnet.dta . tab q4safe0 q4safe0 | Freq. Percent Cum. ------------+----------------------------------- 0 | 331 44.13 44.13 1 | 419 55.87 100.00 Total | 750 100.00 . tab q4safe6 q4safe6 | Freq. Percent Cum. 0 | 254 33.87 33.87 1 | 496 66.13 100.00 . cci 496 419 254 331 Proportion | month 6 month 0 | Total Exposed -----------------+------------------------+------------------------ correct | 496 419 | 915 0.5421 incorrect | 254 331 | 585 0.4342 Total | 750 750 | 1500 0.5000 | | | Point estimate | [95% Conf. Interval] |------------------------+------------------------ Odds ratio | 1.542631 | 1.244963 1.911765 (exact) Attr. frac. ex. | .3517567 | .1967632 .4769231 (exact) Attr. frac. pop | .190679 | +------------------------------------------------- chi2(1) = 16.61 Pr>chi2 = 0.0000 What’s wrong with this analysis? Paired data! (McNemar)

Interpret the OR . tab q4safe6 q4safe0 | q4safe0 q4safe6 | 0 1 | Total -----------+----------------------+---------- 0 | 169 85 | 254 1 | 162 334 | 496 Total | 331 419 | 750 . mcci 334 162 85 169 | month 0 | month 6 | correct incorrect | Total -----------------+------------------------+------------ correct | 334 162 | 496 incorrect | 85 169 | 254 Total | 419 331 | 750 McNemar's chi2(1) = 24.00 Prob > chi2 = 0.0000 Exact McNemar significance probability = 0.0000 Proportion with factor Cases .6613333 Controls .5586667 [95% Conf. Interval] --------- -------------------- difference .1026667 .0609249 .1444084 ratio 1.183771 1.106427 1.266522 rel. diff. .2326284 .151107 .3141498 odds ratio 1.905882 1.456995 2.508149 (exact) Interpret the OR

Interpret the OR . tab q4safe6 q4safe0 | q4safe0 q4safe6 | 0 1 | Total -----------+----------------------+---------- 0 | 169 85 | 254 Discordant pairs 1 | 162 334 | 496 Total | 331 419 | 750 . mcci 334 162 85 169 | month 0 | month 6 | correct incorrect | Total -----------------+------------------------+------------ correct | 334 162 | 496 incorrect | 85 169 | 254 Total | 419 331 | 750 McNemar's chi2(1) = 24.00 Prob > chi2 = 0.0000 Exact McNemar significance probability = 0.0000 Proportion with factor Cases .6613333 Controls .5586667 [95% Conf. Interval] --------- -------------------- difference .1026667 .0609249 .1444084 ratio 1.183771 1.106427 1.266522 rel. diff. .2326284 .151107 .3141498 odds ratio 1.905882 1.456995 2.508149 (exact) Interpret the OR

RESHAPE Wide form . input id cd1 cd2 cd3 cd4 cd5 cd6 1. 1 450 423 387 320 349 299 2. 2 187 220 201 177 140 101 3. 3 380 369 348 331 303 329 4. end . list +----------------------------------------+ | id cd1 cd2 cd3 cd4 cd5 cd6 | |----------------------------------------| 1. | 1 450 423 387 320 349 299 | 2. | 2 187 220 201 177 140 101 | 3. | 3 380 369 348 331 303 329 | Wide form

reshape keyword stem, i(unit id) j(newvar) . reshape long cd, i(id) j(visit) reshape keyword stem, i(unit id) j(newvar) . list +------------------+ | id visit cd | |------------------| 1. | 1 1 450 | 2. | 1 2 423 | 3. | 1 3 387 | 4. | 1 4 320 | 5. | 1 5 349 | 6. | 1 6 299 | 7. | 2 1 187 | 8. | 2 2 220 | 9. | 2 3 201 | 10. | 2 4 177 | 11. | 2 5 140 | 12. | 2 6 101 | 13. | 3 1 380 | 14. | 3 2 369 | 15. | 3 3 348 | 16. | 3 4 331 | 17. | 3 5 303 | 18. | 3 6 329 | Long form

reshape keyword stem, i(unit id) j(dropvar) . reshape wide cd, i(id) j(visit) reshape keyword stem, i(unit id) j(dropvar)  New variable is stem+dropvar (cd+visit) . list +----------------------------------------+ | id cd1 cd2 cd3 cd4 cd5 cd6 | |----------------------------------------| 1. | 1 450 423 387 320 349 299 | 2. | 2 187 220 201 177 140 101 | 3. | 3 380 369 348 331 303 329 | Wide form