九州体育

17：病例对照研究（优势比） 4/7/07

审查问题

1. How do 病例对照 studies differ from cohort studies?
2. 为什么病例对照研究不能估计发病率或流行率？
3. 用什么符号表示比值比参数？ What symbol is used to denote the odds ratio estimator?
4. Before calculating a confidence interval for the odds ratio, we converts the odds ratio estimate to a ______________ scale.
5. 零假设下的比值比参数值是多少？
6. 什么时候用费雪检验代替卡方检验？
7. In a 2-by-2 table for 匹配配对 data, table cells t and w contain co联合国ts for ____________ pairs, while cells u and v contain co联合国ts for ___________ pairs.
8. 对还是错？ 在配对的病例对照研究中，关于一致性配对的信息被忽略。
9. 用于检验配对数据的卡方统计量的名称是什么？
10. 配对的主要好处是什么？
11. [T还是F?]] You can use a 95% confidence for the odds ratio to determine statistical significance at alpha = 0.05.
12. [T还是F?]] You can use a 95% confidence for the odds ratio to determine statistical significance at alpha = 0.01.
13. How do you use a 95% confidence for the odds ratio to determine statistical significance at alpha = 0.05?
14. Which of the following 95% confidence interval for odds ratios are significant at alpha = 0.05? (a) 0.01 ~ 0.77 (b) 0.77 ~ 1.23 (c) 1.23 ~ 2.43

练习

A部分：独立样本

17A.1 手机和脑肿瘤，研究1. A 病例对照 study by Inskip and co-workers (2001) examined cellular telephone use and intracranial tumors. The study was completed between 1994 and 1998 and included 782 cases with various types of intracranial tumors and 799 控制 admitted to the same hospitals for a variety of nonmalignant conditions. 研究对象被分类为 exposed if they reported use of a cellular telephone for more than 100 hours. The odds ratios (95% confidence intervals) calculated by the study were: for glioma 0.9 (0.5 to 1.6), for meningioma: 0.7 (0.3 to 1.7), for acoustic neuroma: 1.4 (0.6 to 3.5), for all tumor types combined: 1.0 (0.6 to 1.5). Do these results 支持 or fail to 支持 the theory that recent hand-held cellular telephones use causes brain tumors? Explain your response.

17 a。 研究2：手机与颅内肿瘤. A different case-control study on intracranial tumors and cell phone use by Muskat and co-worker (2000)[全文] was completed between 1994 and 1998. This study used a structured questionnaire to quantify the statistical relation between cell phone use and primary brain cancer in 469 cases and 422 控制. The results of the study stated "The median monthly hours of use were 2.5 for cases and 2.2 for 控制. Compared with patients who never used handheld cellular telephones, the multivariate odds ratio (或) associated with regular past or current use was 0.85 (95% confidence interval 0.6 to 1.2). The 或 for infrequent users (<0.72 h/mo) was 1.0 (95% confidence interval 0.5 to 2.0) and for frequent users (>10.1 h/mo) was 0.7 (95% confidence interval 0.3 to 1.4). The mean duration of use was 2.8 years for cases and 2.7 years for 控制. The 或 was less than 1.0 for all histologic categories of brain cancer except for 联合国common neuroepitheliomatous cancers (或, 2.1; 95% confidence interval 0.9 to 4.7)." 解释这项研究的结果。 Are they materially different from the study described in Exercise 17A.1?

注1: The studies described in the prior two exercises looked at many types of intracranial tumors (e.g., gliomas, meningiomas, neuromas, epitheliomas, and so on). Different tumor types have different biology and are likely to have different causes. 因此，在这些研究中所做的汇总结果是值得怀疑的。

注2: Without experimentation, or large effects, statistics can play only a modest role in determining causal relations. T在这里fore, other information 必须 come into play. In the two prior exercises, for example, we 必须 consider that the type of energy emitted by cell phones is non-ionizing. Non-ionizing radiation does not cause damage to chemical bonds or to DNA. If we combine with the negative evidence from the epidemiologic studies with these biologic facts, it seems 联合国likely that cell phones can cause brain tumors.

17 a . 食道癌 and tobacco use (same as lab exercise). Data come from the same 病例对照 study on esophageal cancer considered earlier 在本章中. In this analysis we look at tobacco use dichotomized at 20 gms/day. [Data are originally from Tuyns and coworkers (1977) as reported by Breslow and Day (1980). Individual data records for the data set are stored online in the data file bd1.sav as variables TOB2 and 情况下] Cross-tabulation揭示:

(一) Calculate the odds ratio for the data and a 95% confidence interval for the odds ratio parameter. 解读这些统计数据。
(B) Calculate a P value for the problem. 解读这一统计数据。
(C) Download bd1.sav. 并在SPSS中打开。 Create the code book for the data file by clicking 文件>显示数据 信息 > 1型。sav b>好的. 把密码本放在手边，以备将来参考。
(D) Cross-tabulate the data in SPSS (Analyze > Descriptive Statistics > CrossTabs). Select TOB2 as the row variable and 情况下 as the column variable. Click the statistics button and check the boxes for 卡方 and 风险 . Click 继续b>好的. Make certain you confirm these results with your hand calculations.

17A.4 IUDs and infertility. A 病例对照 的研究 contraceptive devices and infertility fo联合国d prior use of intra-uterine devices (IUDs) in 89 of 283 infertile cases. In contrast, 640 of 3833 fertile control women had used IUDs (Cramer et al., 1985; Rosner, 1990, p. 381). 数据显示在下面的2 × 2表格中。 Calculate the odds ratio and its 95%置信区间。 解释结果。

17A.5 Doll & Hills， 1950年. A important study in the history of 病例对照 methods was completed in 1950 by Doll & Hill. This study fo联合国d that 647 of the 649 肺癌 cases were smokers. 相比之下，649名对照组中有622人吸烟。 (Click 在这里 for a reprint of the original article.)

(一) Display data in 2-by-2 cross-tabulation of the co联合国ts
(B) Calculate the odds ratio and its 95%置信区间。
(C) 解释结果。

17A.6 Brain tumors and electric 毯子 use. A 病例对照 study assessed the risks of brain tumors associated with electric 毯子 use. 交叉表格的数据如下所示。 Calculate the odds ratio and its 95% confidence interval. 解释你的发现。

Source: Preston-Martin et al., 1996 . 数据作为单独的记录存储在数据文件中 BRAINTUM。干腊肠

17 a.7 输精管结扎术 and prostate cancer. Data from a 病例对照 study on vasectomy and prostate cancer are cross-tabulated below (Zhu et al., 1996). 计算比值比及其95%置信区间。 解释你的发现。 (可选: Calculate the P value for the problem.)

17日如 石棉、香烟和肺癌. By going through the steps listed below, you will learn how to detect statistical interaction. Data stored in asbestos.sav are from a 病例对照 study on 肺癌, asbestos exposure, and smoking. 右键单击文件名以下载数据集。

(一) Cross-tabulate LUNGCA (column) by 烟 (row). 确定优势比。
(B) Cross-tabulate LUNGCA by 石棉. 确定优势比。
(C) Cross-tabulate LUNGCA by 石棉 stratified by 烟. This is accomplished by filling in the SPSS dialogue box as shown below. Calculate the odds ratios for smokers and non-smokers separately. Are these odds ratios homogeneous? 石棉对吸烟者有什么影响？ … in non-smokers?

17 a.9 食道癌 and alcohol recorded at four levels. The data set BD1 was introduced earlier in these notes. Recall that this is a 病例对照 的研究 esophageal cancer. In this analysis, alcohol consumption is recorded at four levels: 0-39 g/day, 40-79 g/day, 80-119 g/day, and 120 + g /天. 交叉表的结果如下： Calculate the odds ratio associated with each level of alcohol consumption. Is t在这里 evidence of a dose-response relationship?

Hint: To analyze these data, you can break it up into the four 2-by-2 cross-tabulations (shown below):

17 a.10 温德 and 格雷厄姆's 病例对照 的研究 smoking and 肺癌. A historically important 病例对照 study on 吸烟和 肺癌 compared smoking histories of 605 cases with 肺癌 to 780 non-cancer 控制 (温德 & 格雷厄姆, JAMA, 1950). 过去20年平均烟草使用数据如下：

^* If subject smoked for less than 20 years, the amo联合国t of smoking
was reduced in proportion to duration.

(一) Calculate odds ratio for each level of smoking using the non-smokers as the reference group. (可选: Determine 95% confidence intervals for each estimate.)
(B) 先进的：测试数据的趋势。

17 a.11 秃顶 and myocardial infarction, self-assessed baldness. Both baldness and myocardial infarction (heart attacks) are more common in males than in females. 这两者之间有联系吗？ The answer to this question takes on additional importance when one considers treatments for baldness such as minoxidil. If the 联合国derlying condition of baldness elevated cardiovascular disease risk, then any increase in the risk observed in minoxidil users might mistakenly be attributed to the drug and not to the 联合国derlying condition of baldness (so-called 指征混淆). A 病例对照 study addressed the relation between nonfatal myocardial infarction and baldness. 情况下 were men 联合国der 55 years of age admitted to hospitals in Massachusetts and Rhode Island for a first heart attack with no prior history of serious heart problems. 控制 were men admitted to the same hospitals for non-fatal, non-cardiac problems. 既往有心脏病史的对照组被排除在研究之外。 Data for the distribution of baldness according to patients' self-assessments graded on a scale of 1 (no baldness) to 5 (extreme baldness) are shown below (Lesko and co-workers, 1993; Table 6).

秃顶	例*	控制
1(没有)	251	331
2	165	221
3	195	185
4	50	34
5 (extreme)	2	1
总	663	772

* 2例暴露资料缺失

(一) Calculate odds ratios associated with each level of baldness using baldness level 1 as the reference category. 解释这些结果。
(B) Perform a chi-square test for association Report the chi-square statistic, its df and P-value. 解释结果。
(C) 先进的学生：对趋势进行Mantel测试。
(D) Differences 此外，这些都是由于多毛 were fo联合国d between cases and 控制. For example, the median age of case was 47 years, while the median age of 控制 was 43 year. 解释为什么这很重要。
(E) Because they were concerned about the potentially confo联合国ding effects of age and other factors, the investigators adjusted for age, race, religion, years of education, body mass index, use of alcohol and cigarettes, family history of myocardial infarction, history of angina, hypertension, diabetes, hypercholesterolemia, and gout, exercise, personality, number of doctor visits in prior year with multivariate logistic regression model. The multivariate adjusted 或s and crude 或s are listed below. Does this materially effect you interpretation of results?

17 a.12。 秃顶 and myocardial infarction, interviewer assessed baldness. 这个练习是练习17 a.11的延续。 In addition to using self-assessments of baldness (by study subjects), the study in question used interviewer assessments of baldness based on the Hamilton baldness scale. Here are the data according the this measurement of the explanatory variable: 秃顶 例* 控制* * 没有一个 a 238 480 额 b 44 82 Mild vertex c 108 137 Mod. vertex d 40 46 Severe vertex e 35 23 总 465 768 *数据缺失200例； * * 4个控制缺少数据。 a = Hamilton baldness categories I and II on the modified b = Hamilton categories IIa, III, IIIa, and IVa. c = Hamilton categories III and IV d = Hamilton categories V and Va. e = Hamilton categories VI and VI [Source: Table 5 in Lesko et al., 1993] (一) Compare the assessments of baldness used in this analysis to the self-assessments used in Exercise 17 a.11. 哪种方法更可取？ (Explain your reasoning.) How could misclassification of baldness affect the results of the study? (B) 计算与每个暴露水平相关的比值比。 (C) 将这些结果与先前练习的结果进行比较。

B部分：配对

17 b。1 Fruits, vegetables, and adenomatous polyps (same as lab exercise). A 病例对照 study by Witte and co-workers (1996) used 匹配配对s to study the risk of adenomatous polyps of the colon in relation to diet. All cases and 控制 had 联合国dergone sigmoidoscopic screening. 对照在筛查时间、诊所、年龄和性别方面与病例相匹配。 One of the study's analyses considered the effects of low fruit and vegetable consumption on colon polyp risk. T在这里 were 45 pairs in which the case but not the control reported low fruit/veggie consumption. T在这里 were 24 pairs in which the control but not the case reported low fruit/veggie consumption [Summary co联合国ts reported in Rothman & Greenland, 1998； 287页。; same data as StatPrimer illustrative example.]

(一) 计算与低水果/蔬菜摄入量相关的比值比。 Interpret this result.
(B) Calculate a 95% confidence interval for the odds ratio. Interpret this result.
(C) Calculate a P value for testing H₀: 或 = 1.
(D) Do data 支持 a connection between low fruit/veggie consumption and colon cancer?

17 b.2 Smoking and mortality in identical twins. When smoking was first suspected as a cause of disease, Sir Ronald Fisher offered the constitution hypothesis as an explanation for the observed association. Fisher (1957, 1958年,一个, 1958 b) did not entirely dispose of the causal hypothesis, however.) The constitutional hypothesis suggested that people genetically disposed to 肺癌 were more likely to smoke. In other words, the relation between 吸烟和 disease was 抱愧蒙羞 by constitutional factors. The constitutional hypothesis was put to the ultimate test by a study in which 22 smoking-discordant monozygotic twins w在这里 studied to see which twin first succumbed to death (Kaprio & Koskenvuo, 1989). In this study, the smoking-twin died first in 17 of the pairs (i.e., u = 17, while u + v = 22). Calculate the odds ratio for these data. In addition, calculate a P -value for testing H₀: 或 = 1. 宪法假说被驳倒了吗？

17 b.3 血栓性斯托克 在年轻女性中. The Collaborative Group Study of Stroke in Yo联合国g Women (1975) used 病例对照 sampling to study cerebrovascular disease (stroke) and oral contraceptive use in women between 14- to 44-years. 情况下 were matched to 控制 according to neighborhood, age, sex, and race. Here are the matched data for the 血栓形成的 stroke cases from the study (Lilienfeld & Lilienfeld, 1980, p. 220):

研究;	控制E +	控制E -	总
例E +	2	44	46
例E -	5	55	60
总	7	99	106

(一) 计算这些数据的比值比。
(B) Now suppose the match was broken and investigators had analyzed the data 联合国aware of the importance of matched analysis. Rearrange the information from the above 匹配配对 table to show how it would appear in an 联合国matched 2-by-2 cross-tabulation. Notice that t在这里 are 106 pairs, so make certain your 2-by-2 table shows results for all 212 individuals. Then, calculate the odds ratio for the data with the match broken. How does this odds ratio compare to that of the (proper) 匹配配对 odds ratio?

17 b.4 出血性斯托克 在年轻女性中. 锻炼17 b。3 introduced data from the Collaborative Group Study of Stroke in Yo联合国g Women. The outcome in this prior exercise was 血栓形成的 stroke. Now we consider 出血性 stroke. 匹配的数据如下所示。 "Break the match" and then rearrange the data into a 2-by-2 cross-tabulation, (A total of 310 individuals should appear in this table.) Calculate odds ratios for both the matched and 联合国matched data. 结果如何比较？

17 b。5 雌激素与子宫颈癌. Data from a matched 病例对照 的研究 conjugated estrogen use and cervical cancer by Ant联合国es and co-workers (1979) are shown below (Abramson & Gahlinger, 2001, p. 137).

(一) 计算比值比及其95%置信区间。 解释你的结果。
(B) Calculate a P value for the problem

奇数问题的关键 偶数问题的关键 （可能不会张贴）