Sampling - Interview - Armén Hakhverdian (Part 3 of 4)

Loading...

來自 University of Amsterdam 的課程

计量方法

979 個評分

Explore Related Videos

At Coursera, you will find the best lectures in the world. Here are some of our personalized recommendations for you

University of Amsterdam

计量方法

979 個評分

課程 1（共 5 門，Specialization 社会科学的方法和统计）

Discover the principles of solid scientific methods in the behavioral and social sciences. Join us and learn to separate sloppy science from solid research! This course will cover the fundamental principles of science, some history and philosophy of science, research designs, measurement, sampling and ethics. The course is comparable to a university level introductory course on quantitative research methods in the social sciences, but has a strong focus on research integrity. We will use examples from sociology, political sciences, educational sciences, communication sciences and psychology.

從本節課中

Sampling

In the previous two modules we discussed research designs and methods to measure and manipulate our variables of interest and disinterest. Before a researcher can move on to the testing phase and can actually collect data, there is just one more procedure that needs to be decided on: Sampling. Researchers need to determine who potential participants are and how they will be selected and recruited.

Sampling - Interview - Armén Hakhverdian (Part 1 of 4)8:39

Sampling - Interview - Armén Hakhverdian (Part 2 of 4)7:56

Sampling - Interview - Armén Hakhverdian (Part 3 of 4)4:29

Sampling - Interview - Armén Hakhverdian (Part 4 of 4)5:34

與講師見面

Annemarie Zand Scholten
Assistant Professor
Economics and Business

Maybe I can come back to something you said a moment ago

about overselling your research results.

I think that's an interesting link to a question that I

ask of all the people that are being interviewed.

One thing that's happening in, and that's a, an important topic in this course,

is the focus on questionable research practices, research integrity.

Fraud cases that have come up recently.

So the, the overselling your research results activates that in my mind.

How is,

is this whole controversy experienced in the field of political sciences?

How is your field been affected?

I know that social psychology has been impacted very greatly.

>> Yeah. >> Other fields somewhat less so.

How is that in political sciences?

Obviously it's, it's had an impact on a, I think on social science, and

even science in general.

I think within the discipline of political science, I don't know of fraud cases

that are so big as the ones you've had in social psychology and so incredibly.

They're widespread, but

I think it is a potential problem, obviously.

I mean, where, wherever people collect their own data and wherever people

analyze their own data, there is a risk of of, of something like that.

I mean it would be silly to, to think that political scientists are inherently

different than other science, that's just, it's just simply not true.

So, there, I, wherever data is collected by individuals,

there will be a, a, a risk of fraud, whether this is qualitative or

quantitative, by the way, I mean so-

>> Yeah. >> So lead interviews use,

with, with policymakers, especially if they're anonymous sources or-

>> Exactly. >> Are just as prone to

fraud as experimental approaches or.

One thing in my, in my research, so for instance, in the survey tradition,

I think it's fairly difficult because I don't collect my own data.

And as I just, I mean, as I just said, it's impossible to collect your own data.

So what we usually do,

is use data that have been collected by, you have professional agencies or, or-

>> Right. >> I mean, where.

So we might have a say in what questions are being asked.

>> Mm-hm. >> And the question wording and

categories and all that sort of stuff.

But not the actual collection of the data or the interview process or anything.

So we get we basically, me and, and many others in my field, we simply

get the data set in SPSS or Stata or Excel or wherever and then we start working.

>> Oh, okay.

>> So if I, if I were to publish something that I made up that is a surprising

finding, because it's always a surprising findings that should get scrutinized not.

>> Yeah.

>> then, that would be incredibly stupid because a lot of

people have that same data set.

>> Right. >> I mean, they can simply.

So if I were to, if I were to set, correlate for instance.

Let's say there's a correlation between education and and political participation.

Higher educated people participate more in politics than lower educated people.

>> Right.

>> Let's say that I say that I've you know, I've conducted, I've

conducted research on National Kiezers Onderzoek, Dutch Parliamentary Studies 2012,

and I find no evidence of that whatsoever.

Education has no role whatsoever in in predicting political participation.

Big surprise.

Everyone's talking about-

>> Yeah. >> The Netherlands as a diploma democracy,

and the higher educated are so powerful and influential.

And here's my research that, that shows there's no correlation whatsoever.

Obviously you can just open a data set yourself-

>> And check.

>> And check and you will find that there is an actual correlation.

So you use, I mean in my, in my particular field lying with

data that actually everyone has access to is just-

>> Stupid. >> It's stupid.

>> Yeah.

探索我們的目錄

免費加入並獲得個性化推薦、更新和優惠。

Coursera 致力於普及全世界最好的教育，它與全球一流大學和機構合作提供在線課程。

© 2019 Coursera Inc. 保留所有權利。

通過 App Store 下載

通過 Google Play 獲取