(Offtopic?) Textbook on causality in social research

[Tino Nsenene]

Dear All,

although I suspect that some may perceive my request as offtopic, I would be
very grateful for your suggestions regarding an appropriate textbook
(advanced undergarduate level) which contains a chapter of deals with

problems of drawing causal conclusions in applied social research.

I will have to teach a course on this topic soon. My problem is that most
texts I scanned thus far treat the topic in very abstract terms. So, please
let me know your hints, ideas and suggestions for teaching this topic...

Many thanks!!!

Tino

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Nils Braakmann]

You might want to try
Joshua Angrist and Steve Pischke 2009, Mostly harmless econometrics, Princeton University Press.
There's also a good review article by Imbens and Wooldridge in the Journal of Economic Literature in 2009 (can't recall the title right now). Finally, there's also Charles Manski, Identification problems in the social sciences (I think from the mid/late 90s). Sorry for the vague references but I'm not at home right now.
Hope these help nevertheless,
Nils

Sent from my iPhone

On 5 Jun 2012, at 15:55, Tino <[hidden email]> wrote:

> Dear All,
>
> although I suspect that some may perceive my request as offtopic, I would be
> very grateful for your suggestions regarding an appropriate textbook
> (advanced undergarduate level) which contains a chapter of deals with
>
> problems of drawing causal conclusions in applied social research.
>
> I will have to teach a course on this topic soon. My problem is that most
> texts I scanned thus far treat the topic in very abstract terms. So, please
> let me know your hints, ideas and suggestions for teaching this topic...
>
> Many thanks!!!
>
> Tino
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Jason Schoeneberger]

Also see Methods Matter by Murnane & Willett

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Nils Braakmann
Sent: Tuesday, June 05, 2012 12:47 PM
To: [hidden email]
Subject: Re: (Offtopic?) Textbook on causality in social research

You might want to try
Joshua Angrist and Steve Pischke 2009, Mostly harmless econometrics,
Princeton University Press.
There's also a good review article by Imbens and Wooldridge in the Journal
of Economic Literature in 2009 (can't recall the title right now). Finally,
there's also Charles Manski, Identification problems in the social sciences
(I think from the mid/late 90s). Sorry for the vague references but I'm not
at home right now.
Hope these help nevertheless,
Nils

Sent from my iPhone

On 5 Jun 2012, at 15:55, Tino <[hidden email]> wrote:

> Dear All,
>
> although I suspect that some may perceive my request as offtopic, I
> would be very grateful for your suggestions regarding an appropriate
> textbook (advanced undergarduate level) which contains a chapter of
> deals with
>
> problems of drawing causal conclusions in applied social research.
>
> I will have to teach a course on this topic soon. My problem is that
> most texts I scanned thus far treat the topic in very abstract terms.
> So, please let me know your hints, ideas and suggestions for teaching this

topic...

>
> Many thanks!!!
>
> Tino
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except
> the command. To leave the list, send the command SIGNOFF SPSSX-L For a
> list of commands to manage subscriptions, send the command INFO
> REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command SIGNOFF SPSSX-L For a list of
commands to manage subscriptions, send the command INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[John F Hall]

Have a look at the late Cathie Marsh's books:

Catherine Marsh
The survey method : the contribution of surveys to sociological explanation
(Allen and Unwin, 1982)

Catherine Marsh & Jane Elliott
Exploring Data
(2nd edition, Polity Press, 2008)

You can access their details via links on my website.
http://surveyresearch.weebly.com/cathie-marsh.html

John Hall

John F Hall (Mr)

Email:    [hidden email]
Website:        www.surveyresearch.weebly.com








-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Tino
Sent: 05 June 2012 16:56
To: [hidden email]
Subject: (Offtopic?) Textbook on causality in social research

Dear All,

although I suspect that some may perceive my request as offtopic, I would be
very grateful for your suggestions regarding an appropriate textbook
(advanced undergarduate level) which contains a chapter of deals with

problems of drawing causal conclusions in applied social research.

I will have to teach a course on this topic soon. My problem is that most
texts I scanned thus far treat the topic in very abstract terms. So, please
let me know your hints, ideas and suggestions for teaching this topic...

Many thanks!!!

Tino

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command SIGNOFF SPSSX-L For a list of
commands to manage subscriptions, send the command INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Bruce Weaver]

I had not heard of that book.  But having read (most of) another book co-authored by John Willett ("Applied Longitudinal Data Analysis", with Judith Singer), I suspect it's very good.

Jason Schoeneberger wrote

Also see Methods Matter by Murnane & Willett

--- snip ---

[Maguin, Eugene]

If you can, i think it might be quite interesting to troll this question through the semnet listserv. I think there are people on the list that have written on this topic. For what it's worth, my thought is that your class is about this question:
If I claim that A causes B, what are the necessary and sufficient propositions that I have to show to be true to prove my claim.

I don't know that statistics, per se, matters, but I think that probability and how probability interacts with logic does.

Gene Maguin


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Bruce Weaver
Sent: Tuesday, June 05, 2012 1:57 PM
To: [hidden email]
Subject: Re: (Offtopic?) Textbook on causality in social research

I had not heard of that book.  But having read (most of) another book co-authored by John Willett ("Applied Longitudinal Data Analysis", with Judith Singer), I suspect it's very good.



Jason Schoeneberger wrote
>
> Also see Methods Matter by Murnane & Willett
>
> --- snip ---
>
>


-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Offtopic-Textbook-on-causality-in-social-research-tp5713516p5713520.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Bruce Weaver]

In addition to the textbooks that have been suggested, you might find this useful:

  http://core.ecu.edu/psyc/wuenschk/stathelp/Correlation-Causation.htm

HTH.

Tino Nsenene wrote

Dear All,

although I suspect that some may perceive my request as offtopic, I would be
very grateful for your suggestions regarding an appropriate textbook
(advanced undergarduate level) which contains a chapter of deals with

problems of drawing causal conclusions in applied social research.

I will have to teach a course on this topic soon. My problem is that most
texts I scanned thus far treat the topic in very abstract terms. So, please
let me know your hints, ideas and suggestions for teaching this topic...

Many thanks!!!

Tino

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Cleland, Patricia (EDU)]

You might also want to look at Estimating Causal Effects Using Experimental and Observational Designs, published by the AERA (American Educational Research Association) in 2007.  In addition to discussing causality and randomized experiments, (the gold standard that we’re all taught in grad school), it also covers more real world causality including observational data and large scale data sets.

It can be downloaded here:

http://www.aera.net/Publications/Books/EstimatingCausalEffectsUsingExperimentaland/tabid/12625/Default.aspx

Pat

-----Original Message-----
From: SPSSX(r) Discussion [[hidden email]] On Behalf Of Maguin, Eugene
Sent: June 5, 2012 2:12 PM
To: [hidden email]
Subject: Re: [SPSSX-L] (Offtopic?) Textbook on causality in social research

If you can, i think it might be quite interesting to troll this question through the semnet listserv. I think there are people on the list that have written on this topic. For what it's worth, my thought is that your class is about this question:

If I claim that A causes B, what are the necessary and sufficient propositions that I have to show to be true to prove my claim.

I don't know that statistics, per se, matters, but I think that probability and how probability interacts with logic does.

Gene Maguin

-----Original Message-----

From: SPSSX(r) Discussion [[hidden email]] On Behalf Of Bruce Weaver

Sent: Tuesday, June 05, 2012 1:57 PM

To: [hidden email]

Subject: Re: (Offtopic?) Textbook on causality in social research

I had not heard of that book.  But having read (most of) another book co-authored by John Willett ("Applied Longitudinal Data Analysis", with Judith Singer), I suspect it's very good.

Jason Schoeneberger wrote

>

> Also see Methods Matter by Murnane & Willett

>

> --- snip ---

>

>

-----

--

Bruce Weaver

[hidden email]

http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.

To send me an e-mail, please use the address shown above.

--

View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Offtopic-Textbook-on-causality-in-social-research-tp5713516p5713520.html

Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================

To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

=====================

To manage your subscription to SPSSX-L, send a message to

[hidden email] (not to SPSSX-L), with no body text except the

command. To leave the list, send the command

SIGNOFF SPSSX-L

For a list of commands to manage subscriptions, send the command

INFO REFCARD

[Rich Ulrich]

I don't have any recommendation directly on this -

[Asking about a book with a chapter on ... ]
> problems of drawing causal conclusions in applied social research.
>

For comparison, or for extra reading, I suggest
passing out the (non-abstract) Bradford-Hill criteria
for epidemiological research -
  http://en.wikipedia.org/wiki/Bradford_Hill_criteria

And for a good general orientation, I recommend the
book, "Statistics as Principled Argument" by Abelson.

--
Rich Ulrich

[Hector Maletta]

The "classic" book on causal inferences in non-experimental situations (and
addressed to social scientists) is Hubert Blalock's Causal Inferences in
Nonexperimental Research. Four decades old and still illuminating.

Newer works of a more general nature, also oriented towards the social
sciences, are:
Judea Pearl (2009), Causality: Models, Reasoning and Inference (2nd
edition). Cambridge University Press.
Stephen Morgan & Christopher Winship (2007). Counterfactuals and Causal
Inference. Cambridge University Press.

There is a flurry of books and articles in the latest ten years or so on the
application of experimental designs to social research. Randomized social
and economic experiments, quasi-experiments and natural experiments are all
the rage. No time now to dig out references, but an example is the recent
book by A. Banerjee & Esther Duflo (2011), Poor Economics (New York: Public
Affairs) where various randomized experiments are used to decide questions
about microcredit, conditional cash transfers and other common instruments
of poverty-reduction policies. On the use of experiments in Economics see
Vernon Smith (2008), Rationality in Economics: Constructivist and Ecological
Forms, which under an intimidating title hides a lot of applications of
experimental methods in Economics (Smith won a Nobel award for his work in
experimental economics). Another very important source of insight in this
matter (though not specifically focused on social science) is the book by
Hugh Gauch (2003), Scientific Method in Practice (look especially for his
application of Bayesian rules to extract maximum causal information from
imperfect and uncertain data with lots of "noise").

Hope this helps.

Hector

-----Mensaje original-----
De: SPSSX(r) Discussion [mailto:[hidden email]] En nombre de Nils
Braakmann
Enviado el: Tuesday, June 05, 2012 13:47
Para: [hidden email]
Asunto: Re: (Offtopic?) Textbook on causality in social research

You might want to try
Joshua Angrist and Steve Pischke 2009, Mostly harmless econometrics,
Princeton University Press.
There's also a good review article by Imbens and Wooldridge in the Journal
of Economic Literature in 2009 (can't recall the title right now). Finally,
there's also Charles Manski, Identification problems in the social sciences
(I think from the mid/late 90s). Sorry for the vague references but I'm not
at home right now.
Hope these help nevertheless,
Nils

Sent from my iPhone

On 5 Jun 2012, at 15:55, Tino <[hidden email]> wrote:

> Dear All,
>
> although I suspect that some may perceive my request as offtopic, I
> would be very grateful for your suggestions regarding an appropriate
> textbook (advanced undergarduate level) which contains a chapter of
> deals with
>
> problems of drawing causal conclusions in applied social research.
>
> I will have to teach a course on this topic soon. My problem is that
> most texts I scanned thus far treat the topic in very abstract terms.
> So, please let me know your hints, ideas and suggestions for teaching this

topic...

>
> Many thanks!!!
>
> Tino
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except
> the command. To leave the list, send the command SIGNOFF SPSSX-L For a
> list of commands to manage subscriptions, send the command INFO
> REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command SIGNOFF SPSSX-L For a list of
commands to manage subscriptions, send the command INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Eero Olli]

My personal favorite for teaching causality to undergraduates and graduates is Tufte, Edward R. (1974) Data Analysis for Politics and Polity. Englewood Cliffs, NJ: Prentice-Hall Inc.
It is old, and it only addresses causality in practical terms. Tufte goes through a series of puzzles: Do compulsory seat-belt use in cars save lives or not? Do laws against smoking have an effect? He uses different techniques, and shows how different analytical approaches give different answers. As a student you will become intrigued by the real life questions, and how researchers have to ask the right questions to the data to find out what is going on. Wrong questions or poor techniques give an erroneous understanding of the causality involved.

Sincerely,
Eero Olli

___________________________________________________________________________
Eero Olli
Senioradviser at the Equality- and Anti-Discrimination Ombud                                Phone: [phone]
Mail: POB 8048 Dep, 0031 Oslo
Visits: Mariboesgate 13, Oslo                                                                                                                   www.ldo.no

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD