Month: May 2018

Causal Analysis in Observation Studies

May 20, 2018 Uncategorized 5 comments

Criteria for A Confounding Factor

We can summarize thus far with the observation that for a variable to be a confounder, it must have three necessary (but not sufficient or defining) characteristics, which we will discuss in detail. We will then point out some limitations of these characteristics in defining and identifying confounding.

A confounding factor must be extraneous risk factor for the disease.

As mentioned earlier, a potential confounding factor need not be an actual cause of the disease, but if it is not, it must be a surrogate for an actual cause of the disease other than exposure. This condition implies that the association between the potential confounder and the disease must occur within levels of the study exposure. In particular, a potentially confounding factor must be a risk factor within the reference level of the exposure under study. The data may serve as a guide to the relation between the potential confounder and the disease, but it is the actual relation between the potentially confounding factor and disease, not the apparent relation observed in the data, that determines whether confounding can occur. In large studies, which are subject to less sampling error, we expect the data to reflect more closely the underlying relation, but in small studies the data are a less reliable guide, and one must consider other, external evidence (“prior knowledge”) regarding the relation of the factor to the disease.

The following example illustrates the role that prior knowledge can play in evaluating confounding. Suppose that in a cohort study of airborne glass fibers and lung cancer, the data show more smoking and more cancers among the heavily exposed but no relation between smoking and lung cancer within exposure levels. The latter absence of a relation does not mean that an effect of smoking was not confounded (mixed) with the estimated effect of glass fibers: It may be that some or all of the excess cancers in the heavily exposed were produced solely by smoking, and that the lack of a smoking-cancer association in the study cohort was produced by an unmeasured confounder of that association in this cohort, or by random error.

As a converse example, suppose that we conduct a cohort study of sunlight exposure and melanoma. Our best current information indicates that, after controlling for age and geographic area of residence, there is no relation between Social Security number and melanoma occurrence. Thus, we would not consider Social Security number a confounder, regardless of its association with melanoma in the reference exposure cohort, because we think it is not a risk factor for melanoma in this cohort, given age and geographic area (i.e., we think Social Security numbers do not affect melanoma rates and are not markers for some melanoma risk factor other than age and area). Even if control of Social Security number would change the effect estimate, the resulting estimate of effect would be less accurate than one that ignores Social Security number, given our prior information about the lack of real confounding by social security number.

Nevertheless, because external information is usually limited, investigators often rely on their data to infer the relation of potential confounders to the disease. This reliance can be rationalized if one has good reason to suspect that the external information is not very relevant to one’s own study. For example, a cause of disease in one population will be causally unrelated to disease in another population that lacks complementary component causes. A discordance between the data and external information about a suspected or known risk factor may therefore signal an inadequacy in the detail of information about interacting factors rather than an error in the data. Such an explanation may be less credible for variables such as age, sex, and smoking, whose joint relation to disease are often thought to be fairly stable across populations. In a parallel fashion, external information about the absence of an effect for a possible risk factor may be considered inadequate, if the external information is based on studies that had a considerable bias toward the null.

A confounding factor must be associated with the exposure under study in the source population (the population at risk from which the cases are derived).

To produce confounding, the association between a potential confounding factor and the exposure must be in the source population of the study cases. In a cohort study, the source population corresponds to the study cohort and so this proviso implies only that the association between a confounding factor and the exposure exists among subjects that compose the cohort. Thus, in cohort studies, the exposure-confounder association can be determined from the study data alone and does not even theoretically depend on prior knowledge if no measurement error is present.

When the exposure under study has been randomly assigned, it is sometimes mistakenly thought that confounding cannot occur because randomization guarantees exposure will be independent of (unassociated with) other factors. Unfortunately, this independence guarantee is only on average across repetitions of the randomization procedure. In almost any given single randomization (allocation), including those in actual studies, there will be random associations of the exposure with extraneous risk factors. As a consequence, confounding can and does occur in randomized trials. Although this random confounding tends to be small in large randomized trials, it will often be large within small trials and within small subgroups of large trials. Furthermore, heavy non adherence or noncompliance (failure to follow the assigned treatment protocol) or drop-out can result in considerable nonrandom confounding, even in large randomized trials.

In a case-control study, the association of exposure and the potential confounder must be present in the source population that gave rise to the cases. If the control  series is large and there is no selection bias or measurement error, the controls will provide a reasonable  estimate of the association between the potential confounding variable and the exposure in the source population and can be checked with the study data. In general, however, the controls may not adequately estimate the degree of association between the potential confounder and the exposure in the source population that produced the study cases. If information is available on this population association, it can be used to adjust findings from the control series. Unfortunately, reliable external information about the associations among risk factors in the source population is seldom available. Thus, in case-control studies, concerns about the control group will have to be considered in estimating the association between the exposure and the potentially confounding factor, for example, via bias analysis.

Consider a nested case-control study of occupational exposure to airborne glass fibers and the occurrence of lung cancer that randomly sampled cases and controls from cases and persons at risk in an occupational cohort. Suppose that we knew the association of exposure and smoking in the full cohort, as we might if this information were recorded for the entire cohort. We could then use the discrepancy between the true association and the exposure-smoking association observed in the controls as a measure of the extent to which random sampling had failed to produce representative controls. Regardless of the size of this discrepancy, if there were no association between smoking and exposure in the source cohort, smoking would not be a true confounder (even if it appeared to be one in the case-control data), and the the unadjusted estimate would be the best  available estimate. More, generally, we could use any information on the entire cohort to make adjustments to the case-control estimate, in a fashion analogous to two-stage studies.


Unfinished, keep updating …

The Summary of Japanese Grammar

May 16, 2018 Japanese, Uncategorized No comments ,

I wrote this thread because I want to intense the study and memorization of Japanese grammar, simply keeping me learning. This thread keeps updating. Hopefully what has been written here could help other Japanese learners.

Grammar Lesson 1

Screen Shot 2018 05 16 at 2 16 06 PM

The function of this grammar structure is to mean “It is”, “I am”, “He is”, etc. The Y is what after the predicate, and the X next to the は is the subject.

Screen Shot 2018 05 17 at 2 27 55 PM


じゅうにじはんです (It) is half past twelve.

がくせいです (I) am a student.

にほんごです (My major) is the Japanese language.

山下先生は桜大学の学生でした Mr. Yamashita was a student at Sakura University.

あれは日本の映画じゃなかったです That was not a Japanese movie.

Screen Shot 2018 05 16 at 2 28 29 PM

By adding か after the predicate です, the sentence is transformed to a “yes / no” question form. In addition, by expanding the predicate into the structure of なんxxxですか , the meaning of the sentence become “what is”.


りゅうがくせいですか (Are you) an international student?

せんこうはなんですか What is your major?

Screen Shot 2018 05 16 at 2 44 51 PM

の is a particle that connects two nouns. The noun after の expressed the main idea and the one before is the specific characteristic of the main idea.

Grammar Lesson 3

Screen Shot 2018 05 16 at 8 14 02 PM

There are generally three types of verbs and Japanese verbs exist in three forms, including: 1) dictionary forms, 2) the present tense affirmative forms, and 3) the present tense negative forms.

Screen Shot 2018 05 16 at 8 16 41 PM

There are three subtypes of dictionary forms, the “ru-verbs”, the “u-verbs”, and the irregular verbs.

The past tense forms of verbs look like the following.

Screen Shot 2018 05 17 at 2 34 16 PM


メアリーさんは九時ごろうさに帰りました Mary returned home at about nine.

私は昨日日本語を勉強しませんでした I did not study Japanese yesterday.

Screen Shot 2018 05 16 at 8 20 44 PM

Nouns used in sentences generally be followed by particles, which indicate the relations that the nouns bear to the verbs.

 The particle を indicates “direct objects,” the kind of things that are directly involved in, or affected by, the event. Note that this particle is pronounced “o”.


コーヒーを飲みます I drink coffee.

音楽を聴きます I listen to music.

テレビをます I watch TV.

 The paticle で indicates where the event described by the verb takes place.


図書館で本を読みます I will read books in the library.

うちでテレビを見ます I will watch TV at home.

 The particle に has many meanings, but there here we focus on two: 1) the goal toward which things move (location), and 2) the time at which an event takes place.


私は今日学校に行きません I will not go to school today.

私はうちに帰ります I will return home.

日曜日に京都に行きます I will go to Kyoto on Sunday.

十一時に寝ます I will go to bed at eleven.

十一時ごろ(に)寝ます I will go to bed at about eleven.

私は今日学校へ行きません I will not go to school today.

私はうちへ帰ります I will return home.

You do not use the particle に with 1) time expressions defined relative to the present moment, such as “today,” and “tomorrow,” 2) expressions describing regular intervals, such as “every day,” and 3) the word for “when.”


明日きます I will come tomorrow.

毎晩テレビを見ます I watch TV every evening.

いつ行きますか When will you go?

Screen Shot 2018 05 16 at 9 17 13 PM

You can use ませんか (= the present tense negative verb, plus the question particle) to extend an invitation. It should be noted that its affirmative counterpart, ますか, cannot be so used.

昼ご飯を食べませんか What do you say to having lunch with me?

テニスをしませんか Will you play tennis with me?

Screen Shot 2018 05 16 at 9 24 49 PM

Japanese sentences are fairly flexible in the arrangement of elements that appear in them. Generally, sentences are made up of several noun-particle sequences followed by a verb or an adjective, which in turn is often followed by a sentence-final particle such as か, ね, orよ. Among the noun-particle sequences, their relative orders are to a large extent free. A typical sentence, therefore, looks like the following, but several other arrangements of non-particle sequences are also possible.

私は今日図書館で日本語を勉強します I will study Japanese in the library today.

私はよく七時ごろうちへ帰ります I often go back home at around seven.

Screen Shot 2018 05 17 at 12 53 07 PM

You can add a frequency adverb such as 毎日, よく, ときどき to a sentence to describe how often you do something.


私はときどき喫茶店に行きます I sometimes go to a coffee shop.

私はぜんぜんテレビを観ません I do not watch TV at all.

たけしさんはあまり勉強しません Takeshi does not study much.

Screen Shot 2018 05 17 at 1 02 31 PM

The particle は presents the topic of one’s utterance. It puts forward the item that you want to talk about and comment on. A topic phrase, however, need not be the subject of a sentence. We see three sentences in the dialogue of this lesson where non subject phrases are made topics with the help of the particle は.

メアリーさん、週末はたいて何をしますか Mary, what do you usually do on the weekend?

今日は京都に行きます I’m going to Kyoto today.

In the above two examples, は promotes time expressions as the topic of each sentence. Its effects can be paraphrased like this: “Let’s talk about weekends; what do you do on weekends?” “Let me say what I will do today; I will go to Kyoto.”

Grammar Lesson 4

Screen Shot 2018 05 16 at 2 54 11 PM

Xがあります means “there is/are X (nonliving thing).” The particle が introduces, or presents, the item X. There are some rules for this verb. First, it calls for the particle に for the place description. Second, place description usually comes at the beginning of the sentence. Third, the thing description is usually followed by the particle が.

You can also use あります to say that you have or own something. Besides, you can use あります when you want to say that an event will take place.


時間があります (I) have time.

時間がありますか (Do you) have time?

時間がありません (I don’t) have time.

Screen Shot 2018 05 17 at 1 41 05 PM

The Japanese version of “X is in front of Y” looks like



あのデパートの前です It’s in front of that department store.

Screen Shot 2018 05 17 at 1 44 42 PM

銀行は図書館のとなりです The bank is next to the library.

かさはテーブルの下です The umbrella is under the table.

レストランはデパート病院の間です The restaurant is between the department store and the hospital.

One can use any of the above location words together with a verb to describe an event that occur in the place.

私はモスバーガーの前でメアリーさんを待ちました I waited for Mary in front of the Mom Burger place.

Screen Shot 2018 05 17 at 3 00 10 PM

The duration of an activity is expressed with a bare noun, like 一時間. Such a noun stands alone (that is, not followed by an particle).


メアリーさんはそこでたけしさんを一時間待ちました Mary waited for Takeshi there for an hour.

私は昨日日本語を三時間くらい勉強しました I studies Japanese for about three hours yesterday.

昨日7時間半寝ました (I) slept for seven and a half hours last night.