上手 Copilot：在 VS Code 里写 Stata

Hands-on Copilot: Writing Stata in VS Code

沈明宏 · 上海纽约大学 博士后

第15届 · 应用社会科学研究方法研修班
《数据分析专题》系列讲座

2026 年 7 月 22 日

认识 Copilot

你现在怎么写 Stata？

Stata 自带的 do-file 编辑器

• 几乎没有自动补全
• 变量名、宏、结果全靠手敲
• 旧版本（≤ 15）连命令补全都没有
• 记不住选项，就要翻 help

我们今天要换的环境

• VS Code ＋ Stata 扩展
• 语法高亮、代码片段
• GitHub Copilot 行内自动补全
• 一键把代码送进 Stata 运行

写 Stata 的痛，多半不在统计，而在重复敲字。

Open by naming the pain they actually feel. Most Stata users on Windows are on the built-in do-file editor with little or no autocomplete - and on Stata 15 or earlier there is none at all. Frame today’s first tool (Copilot) as the gentlest possible upgrade, not a leap. We will get to the big leap (agents) in the main talk.

三个层次：对话 → 补全 → 智能体

今天起点：② 补全。 你仍然逐行掌控代码，只是敲得更快。

本场后半段：③ 智能体。 用一句话，让它读数据、写代码、出结果。

This is the spine of the whole lecture. Three tiers of AI assistance, increasing in autonomy. Copilot completes the line you are already writing - you stay in control of every keystroke. Chat explains and drafts. Agents do the whole job end to end. We deliberately start at tier 1 because it is the smallest behavior change for a Stata user, and it sets up the contrast that motivates the rest of the talk. Mirrors the “do not climb the ladder, jump” slide later.

什么是 GitHub Copilot？

它是什么

• 编辑器里的 AI 行内补全
• 灰色”幽灵文字”，按 Tab 接受
• 读你光标周围的上下文来猜
• 装在 VS Code 里，不离开编辑器

和聊天机器人的区别

• 聊天：你切到网页问一段
• Copilot：在你写代码时就地接话
• 不打断节奏，边写边补
• 学生 / 教师 可免费申请

一句话：Copilot 是会写代码的输入法。你起头，它补全；你定夺，按 Tab 收下。

Keep this concrete. Copilot is autocomplete on steroids - grey ghost text appears as you type, Tab accepts it. The mental model “code-writing IME / input method” lands well with a Chinese audience who all use pinyin input prediction every day. Mention the free education license (GitHub Student / Teacher) so cost is not a barrier - they can all get it.

Copilot 怎么帮你写 Stata（注释即提示）

技巧：先用一行注释说清你要做什么，Copilot 顺着补出命令。

你输入（一行 Stata 注释）→ Copilot 自动补全（灰色幽灵文字，按 Tab 接受）：

▌

▌⇥ Tab 接受

注释写得越具体，补全越准。变量名、选项、if/in 条件 都可以在注释里点名。

This is the single most useful Copilot habit for Stata: comment-as-prompt. Write a clear Stata comment describing the step, and the completion follows. Demo this live if possible. Emphasize that specificity in the comment (naming the variable, the option you want, the row/col percent) steers the suggestion. This is also a good moment to foreshadow the honesty slide: the suggestion is a draft, not gospel.

用好 Copilot：技巧

六个核心技巧

①　注释即提示 先写一行注释说清你要做什么，让它顺着补。

②　顶部先写目标 文件开头写下整体目标，给 Copilot 全局上下文。

③　拆成小步 一次只写一行，接受后再写下一句，预测更准。

④　给个例子 在注释里写一个「输入 → 输出」样例，照着补。

⑤　命名要清楚 不怕变量名长，只怕晦涩难懂。

⑥　打开相关文件 Copilot 会读你打开的标签页，借此理解上下文。

These six are GitHub’s own documented best practices for steering inline completions (Best Practices page + “how to write better prompts” blog). The throughline: you are giving the model context and structure. Comment-as-prompt and naming are the two that pay off fastest. Decompose (3) is the habit most people miss - accept one line, then write the next comment, rather than expecting a whole function at once. The neighboring-tabs trick (6) is non-obvious and worth a beat: open your data dictionary or a sibling script and suggestions improve. Bottom rule: always review before accepting.

统计工具选择

同一招”注释即提示”，在训练数据丰富的语言上效果最好：

R · dplyr

▌

▌

Python · pandas

▌

▌

This slide demonstrates the techniques where Copilot is genuinely strong - R and Python. Both blocks come from a single intent comment; Copilot completes idiomatic dplyr and pandas. Say plainly that completions are non-deterministic, so “you will get something like this”. The orange box is deliberate foreshadowing: hold this feeling of fluency, because the Stata limitations slide later will contrast against it. This is also where you acknowledge that some of the audience also use R or Python - the techniques transfer, the editor is the same.

接受与切换：快捷键 ＋ 行内对话

操作	快捷键 (Windows)
接受建议	Tab
拒绝 / 取消	Esc
接受下一个词	Ctrl + →
下一个 / 上一个建议	Alt + ]　·　Alt + [
手动触发建议	Alt + \
打开补全面板（多个候选）	Ctrl + Enter
行内对话	Ctrl + I

现场看看： 写一行注释 → 看灰色补全 → 按下面的键操作（每按一次 → 演示一个键）。

▌

▌

⇥ Tab 接受整行 ␛ Esc 放弃 Ctrl + → 接一词

行内对话（Ctrl + I）＋ 斜杠命令 是”一次补全不够”时的定点操作：
/explain 解释 · /fix 修错 · /tests 写测试 · /doc 写文档。

Keybindings are Windows defaults, verified against GitHub and VS Code docs. The two people forget: Ctrl+Right accepts just the next word (keep the good half, re-steer the rest), and the Alt-bracket pair cycles alternatives because the first suggestion is not always best. Do NOT promise a separate accept-next-line key - it is not a documented default. Inline chat is the escape hatch: when ghost text is not enough, Ctrl+I opens chat in place, and slash commands scope the request. Frame autocomplete as “flow” and inline chat as “targeted operations”.

搭环境：VS Code + Stata

为什么用 VS Code，而不是 Stata 自带编辑器？

Stata 自带编辑器的自动补全，长期很弱，且高度依赖版本：

Stata 版本	自带补全	能补什么
≤ 15	无	完全没有
16 – 18	部分	命令 / 关键词 / 括号；不补变量名
19 / StataNow	较全	命令 ＋ 变量名 ＋ 宏 ＋ 存储结果

VS Code ＋ Copilot 把这条线拉平： 无论你用的是 Stata 14 还是 19，都能获得行内 AI 补全。

This table is the core justification for the whole VS Code detour, and it is honest. Native autocomplete did not exist before Stata 16; 16-18 only complete commands and keywords, not variable names; only Stata 19 / StataNow does the full thing. Many in the room are on older versions. The pitch: VS Code + Copilot gives AI completion on ANY version, including old ones - which the Stata Automation bridge (next slide) makes possible.

三步搭建（Windows）

1

装 VS Code ＋ Stata 扩展。 推荐 Stata All in One（高亮＋补全＋运行＋数据浏览）， 或更轻的 vscode-stata / stataRun。

2

注册 Stata 自动化接口（一次性，让 VS Code 能把代码送进 Stata）：

给 StataMP-64.exe 建快捷方式，目标末尾加 /Register：
"C:\Program Files\Stata18\StataMP-64.exe" /Register
右键 → 以管理员身份运行（一次即可）

← 这一步用的是老牌 Automation 接口，旧版本 Stata 同样适用。

3

在扩展设置里填上 Stata 可执行文件路径。 例如 C:\Program Files\Stata18\StataMP-64.exe（旧版常在 Program Files (x86)）。

Three steps, Windows-specific. Step 2 is the one people get stuck on and the one worth doing slowly: the /Register trick registers Stata’s COM Automation server so VS Code can push code into a running Stata. It must be run as administrator once. Stress that this is StataCorp’s own long-standing Automation API (not an AI thing), which is precisely why it works on Stata 14/15/16 too. Step 3: the extension needs the exact exe path; old versions live under Program Files (x86), and MP/SE/IC is chosen by which exe you point at.

让 .do 识别为 Stata ＋ 装 Copilot

告诉 VS Code：.do 是 Stata

在 settings.json 里加：

"files.associations": {
  "*.do": "stata",
  "*.ado": "stata"
}

语言被认成 stata 后，高亮、补全、Copilot 的上下文 才会对。

装 CodeGeeX 并登录

1. 扩展市场搜 CodeGeeX，安装
2. 用智谱账号登录
3. 打开 .do，开始打字 → 看灰字

Tab 接受，Esc 拒绝，Alt+] 看下一个建议。

Two finishing touches. First, file association: Copilot scopes its context off the editor’s language ID, so if .do is not recognized as Stata the suggestions get worse. The settings.json snippet fixes it globally. Second, install the Copilot extension and sign in - remind them of the free education license again. The screenshot placeholder is where a live screen grab goes; if demoing live, just switch to the real VS Code here.

运行代码：把 .do 送进 Stata

操作	vscode-stata	stataRun
运行选中 / 当前行	Shift + Enter	Shift + Ctrl + S
运行整个文件	Ctrl + Shift + D	Shift + Ctrl + A
运行光标以下	–	Shift + Ctrl + D

代码在右侧真正的 Stata 窗口里执行，结果、图、r()/e() 都和平时一模一样。 快捷键名因扩展而异，以你装的扩展为准。

The run-code loop is what makes VS Code a real Stata front end rather than just a text editor. Select lines, hit the key, they execute in the actual Stata window - same results, same graphs, same stored results. Keybindings differ by extension (vscode-stata vs stataRun), so tell them to check whichever they installed. This is a good live-demo beat: run a line and show it land in Stata.

实战：World Values Survey

数据：World Values Survey

世界价值观调查

• 跨国、跨期的价值观与态度调查
• 信任、宗教、政治参与、性别观念……
• 第 7 波覆盖 60＋ 国家 / 地区
• 社科里最常用的跨国数据之一

我们的数据位置

D:\Data\WVS\
  └─ WVS_Wave7.dta

⚠ 演示前：把真实 .dta 放进该目录， 并核对文件名与变量名（下页代码里的变量为占位示例）。

目标：用 Copilot 在 VS Code 里，对 WVS 做一段清理 → 描述 → 回归，全程 Stata。

Introduce WVS briefly for anyone unfamiliar - it is a staple cross-national values survey, Wave 7 covers 60-plus societies. Be transparent about the data path: the file lives at D:. IMPORTANT reminder to self - that folder is currently empty; drop the real .dta in and confirm the actual variable names before the live demo, because the next two slides use Wave-7 placeholder names (Q57, Q71, B_COUNTRY, etc.) that may differ in your extract.

Copilot 写清理 ＋ 描述统计

同一页演示三种用法：写注释出命令、写几个字补全一行、顺上下文接下一步（变量名为 WVS 第 7 波占位示例）：

▌

▌

▌

▌

▌

▌

▌

▌

Walk this top to bottom as a live demo if you can. Three habits on this slide: (1) comment drives the command, (2) type a few chars and Copilot completes the line, (3) Copilot suggests the next line from context (no comment). Q57 = “most people can be trusted”, recoded to 0/1; B_COUNTRY = country; Q262 = age; Q275 = education. These are Wave-7 conventional names - confirm against your actual file. Run each block with Shift+Enter so they see results land in Stata.

Copilot 写回归

继续做制度信任的 logit；其中第二条反过来：写命令、让 Copilot 给你写注释（变量为占位示例）：

▌

▌

▌

▌

▌

▌

Second demo block: a logit of confidence in government on sex, age, education, with country fixed effects and survey weights, plus average marginal effects of education. Mostly comment-driven; the middle line flips it - type the logit, Copilot writes the comment. Deliberately end on the orange warning box - it teees up the honesty slide. Do not oversell the output; if running live, glance at whether the signs are plausible and say “we will verify this”.

Copilot 的边界

Copilot 在 Stata 上的短板

为什么它对 Stata 偏弱

• 训练数据里 Stata 代码稀少（do-file 很少公开）
• Stata 没有语言服务器，只能靠文本猜
• 会编造命令、把 SAS / R 语法混进来
• 越是冷门命令，越容易翻车

真实翻车例子

• 有人让它算加权方差，它凭空造出 一个根本不存在的 pwvariance
• 把别的语言的函数名安到 Stata 上
• 系数、选项时对时错

来源：Ozier（世界银行）、Goldsmith-Pinkham 等公开评测

铁律：Copilot 给的是草稿，不是答案。每一行都要自己跑、自己核。

This is the honest heart of the segment, and it is what makes the talk credible rather than hype. Two reasons Copilot is weak at Stata: training-data scarcity (few do-files are public) and the absence of a Stata language server, so it pattern-matches text with no structural code intelligence. The pwvariance anecdote (Owen Ozier’s World Bank post) is the memorable example - it invents a command that does not exist, and bleeds in SAS/R syntax. Goldsmith-Pinkham, an economist, says plainly “Stata was really not very good with Copilot.” The iron rule: drafts, not answers - always verify.

从对话与补全，走向智能体

对话 · ChatGPT / Claude 解释报错、给思路。

补全 · Copilot 和你一起写，你按下每一个 Tab。

智能体 · Claude Code 替你读数据、写代码、出结果。

The seam slide. Restate the three tiers and the key distinction: with Copilot you still drive every line (you press each Tab); chat explains; agents do the whole job for you. Copilot makes you type faster - agents mean you barely type. End here and hand straight off to slides-theory-shu.typ, which is the rest of the two-hour lecture. This is the natural pivot from “AI helps me code” to “AI does the research task”.