Introduction to Statistics: Self-Paced Course Summer 2016

Welcome to the students of online Self paced Summer course on "Introduction to Statistics"developed by Dr. Asad Zaman, Vice Chancellor, PIDE. The department of Econometrics and Statistics, PIDE has offered this course particularly for the already enrolled students from 3rd semester (to be commenced in Fall, 2016) of MPhil and PhD students who are still in course work. It is required to complete the course before commencement of new semester.

All students should subscribe to this blog, as it will be used to deliver notices about the course i.e. lectures, quizzes and assessment details. ALSO, students can use the blog to post comments and ask questions about the course.Although this course only covers basic concepts (mostly), it does so in a new way, so that even people with advanced training in statistics will find many of the ideas to be very new, and different from what they have been taught. This is a unique course which offers a deep learning experience to students who make an effort.


Material for the course is gathered on the following website:

Self Paced Course Summer 2016


All students are encouraged to watch the lecture delivered by Dr. Asad Zaman at PIDE, in which unique Islamic approach to education is explained. It conveys the message of Allama Iqbal to the Muslim youth:


https://www.youtube.com/watch?v=QgfJxi0GdwA

Intro Stats at Arid Agri U- March 2016

Welcome to students from Arid Agricultural University. Four sections of Intro to Statistics will be taught by Uzma and Nadia under my supervision. All students should subscribe to this blog, as it will be used to deliver notices about the course. ALSO, students can use the blog to post comments and ask questions about the course.

Material for the course is gathered on the following website:

Intro Stats: Arid Agricultural University

This will be unique course which will offer a deep learning experience to students who make an effort. It will require a lot of work from the students. We will follow the principle of the "INVERTED CLASSROOM" which has proven extremely effective. In the inverted classroom, lectures are delivered outside class, while homework and discussion takes place inside class. The sequence of videotaped lectures for the classroom has already been taped and is available from the link given above. In early March, I will personally take a first combined class for all four sections, after which separate classes will be held for each section by Uzma and Nadia on a routine basis. We will provide an assignment to be done BEFORE coming to class, which will involve watching a lecture and doing a quiz on it. To ensure compliance, a quiz very similar to the one assigned to be done at home will be given at the beginning of class, in every class.

I recently delivered a lecture at PIDE, in which I explained the unique Islamic approach to education. I encourage all students to watch this lecture, which conveys the message of Allama Iqbal to the Muslim youth:

https://www.youtube.com/watch?v=QgfJxi0GdwA

Lessons on Hendry Methodology

While evaluating research proposals at a recent PSSP meeting, I realized that the level of knowledge about current econometric methodology both among researcher AND among those who evaluate -- is ABYSMALLY low. 

Now that I am VC PIDE, an adequate level of understanding of econometric methodology will automatically be expected from researchers. I would like to provide some training along these lines on a weekly basis. 

The FIRST place to start is the Davidson-Hendry-Srba-Yeo (DHSY) paper on the estimation the consumption function in England. This is my dividing line -- if you understand this paper, you can call yourself an econometrician, otherwise not. This is BY NO MEANS the state of the art -- it was written forty years ago, in 1970's. BUT it does provide the minimal level of understanding required to do sensible econometrics. Unfortunately, I have rarely seen applied work which conforms to this minimal level of understanding. 

I have created a website where I plan to do a detailed explanation of all the issues discussed in the paper. The truth is that the paper is highly compact -- a lot of deep ideas are condensed into a very brief text, so it requires a HASHIA -- explanations written on the margin. I and my students have finished the first section, which is available on the website DHSY

I would like to explain the Hendry methodology in the context of a critique of real paper which are submitted to our journals. I am attaching a few extracts from a recent submission which was rejected. 

The paper explores the relation between Economic Growth (EG) and FDI. After doing the usual integration cointegration analysis, author finds that EG and FDI are both stationary, and they are also co-integrated, so have a long term relationshipl. Then he runs a Vector Error Correction model following the Engle-Granger two step procedure -- first step is to save the errors from the cointegration equation, the second step is to run current EG and FDI on lagged errors. The results are displayed in the extract from the paper, which is available from the links below. The SECOND (and final equation) estimated in the paper is a regression Log (EG) on Log (FDI ) and some other variables -- you are asked to PROVIDE  a CRITIQUE of this SECOND equation on the basis of your understanding of the first section of DHSY

Please write your critique on THIS BLOG -- ALL are welcome to write there own critiques -- I will give a prize to the best critique -- I will also provide additional hints and information as we go along.

For Online Students: Certificate

Anyone who wishes to receive certificate, should submit final exam within one week. Also, take any missing quizzes, and submit midterm. These will be the bases for assessing pass/fail in the course and for issuing certificate.

Some More Details on Final Exam

The way I have made quizzes and exams in the past (and same method will be used on Final) is the following. I look at the lecture slides -- each of them present and try to explain a single (or a small number) of concepts. I make up a question which tests understanding of the concept explained on that slide. So if you go over all the slides for the lectures, and make sure that you understand what is being said on all of them, you should be in good shape for the final exam.

The labs just provide numerical and hands on practice for this same thing -- no additional or new concepts are introduced in the labs, just asking the student to do the same computations which have already been carried out in the lecture slides.

FInal Exam

Final Exam will be in-class written exam. It will cover the whole course. The pattern will be similar to the questions that have been asked in the online quizzes. For the lectures for which there was no online quiz, the pattern will be similar to the types of questions worked out in the labs.

The Exam is scheduled for Monday, June 30th, 9:30am to 12:30  on what is likely to be the first day of Ramazan. Study hard and do well. 

Quiz Uploaded

Contrary to my plans, I could not upload quiz to quizstar on Friday. NOW I have uploaded a quiz on Lecture 12 -- Basically on Binomial Probabilities, just a little while ago. This quiz will be open for 48 hours, until Wednesday. Please take this quiz within time period allotted

Quiz on Binomial Probabilities

The bad news is that for some reason, my lecture on monday was not taped. So you will only have access to my slides and lecture notes, which are being put up on website in the usual place.

On Wednesday Waqar conducted practice session on solving Binomial problems. Perhaps worse news is that On Friday a quiz will be put up on QUIZSTAR regarding binomial probabilities. This will follow the pattern of questions drilled by myself as well as Waqar. I will post a note on this blog when the quiz becomes available for taking.  

Exercises on Lecture 12

Wednesday Class will be on exercises on computing the Binomial and Poisson probabilities. Several problems are given in the lecture notes, which are available from LINK. Also, the videotaped recording of the lecture is available from this same link.

Lecture 12: Probabilities & Discrete Random Variables

I am back from Umrah -- I prayed that all of my students may become assets for the Ummah, and the key to the creation of the changes needed for creating new directions.

Unfortunately, I did not have time to finish recording the 12th Lecture. I have just finished writing it up, and have posted it on the website: See Lecture 12. I will prepare the slides, but will not have time to record the lecture and so I will deliver it live tomorrow (Monday) morning at 9:00 am, insha Allah. 

Lec 10: Quiz

Quiz on lecture 10 has been available at Quizstar, and will remain open till Monday midnight.

Midterm + Schedule for Next Week

My goal in giving tests is NOT to judge students or compare or evaluate. The test is a LEARNING tool -- students are motivated to work hard to solve it, and thereby to understand the material covered. During grading, we have discovered several areas of weakness, which vary among students. Accordingly, by Friday, my TA's UZMA, IRFAN & WAQAR will mail INDIVIDUALIZED MAKEUP QUIZZES to each student. Each student will be asked to REDO calculations and computations that he/she did wrong, and will be given a little additional work that needs to be done to ensure that he/she has the background necessary to solve the problem.

UZMA: Please coordinate this work, assigning each of the three roughly equal share of quizzes to handle, and providing email addresses of the students to send them these individualized assignments.

ASSIGNMENT/QUIZ due SUNDAY midnite April 27th. This is in replacement for this weeks (two) quizzes which are not being given. The assignment is to pick a pair of variable from the WDI data set such that one is related to the other, and DRAW a graph of Y versus X in the manner shown in the Lecture 9 on BIVARIATE relationships. Comment on the nature of this relationship -- what does it tell you about the real world? Please learn how to download and handle the WDI data set in order to get variables for your study. Make sure that every student chooses different variables.  TA's please help students to get data they want.


NEXT: I am going to Jeddah for one week, leaving this Sunday 27th Apr and arriving back on 4th May. In my absence, WAQAR & IRFAN will be taking the lecture 11 and conducting lab on monday and wednesday as usual.
WAQAR & IRFAN: Please design quiz on Lecture 11, on the pattern of the previous quizzes. UZMA will LOAD the quiz onto QUIZSTAR. The pattern is as follows -- Look at the Lecture Slides, and ASSUME that students have these slides in front of them. MAKE questions to test comprehension of the material being presented on the slides.
UZMA: Please provide them with previous quizzes, and tell them how to get access to quizstar so that they have a better idea about the type of quiz they are supposed to design. You will make the final edits and fix and finalize the questions before loading onto quizstar -- this quiz should be available to students on 2,3,4 MAY.

Technical Issues

Some students said that sound was bad on Lecture 10. I just listened to it, but did not find any problems.  You do have to TURN ON the sound from within powerpoint. Go to the SLIDE SHOW tab, and click on Set Up Slide Show. In this menu, there is a check box marked: Show Without Narration. If this is checked then there will be no sound. If you UNCHECK it, then the slide show will play with the narrations. 

Unit 2: Prob & Stat

Congratulations to the class for finishing the first unit on DESCRIPTIVE STATISTICS. This is a unique course, based on concepts and techniques not currently available anywhere in the world. I know that the class has worked hard, and learned a lot of valuable skills.

The second unit starts on Monday. The first lecture provide an entirely new approach to probability theory, currently not available anywhere else. I have just revised and put up the new lecture (anyone who downloaded or viewed/listened to the old version should get the new one. It has a few additional slides with additional material. Similarly the files for the lecture and the lab have been updated and put up recently. This can be downloaded from:  LECTURE 10: RANDOM DRAW 

The lecture will be on the usual time 9 to 10:30 on Monday morning. One of my students will be available to explain. Students can also put up questions on the blog about things they do not understand.

The lab will be done on Wednesday, and probably there will be a combined quiz on lab & lecture on Friday.

Lecture 9: Comprehension Quiz

Lecture 9 Comprehension Quiz is now available at QuizStar and the deadline of the quiz is Sunday Midnight.

Lecture 9: Bivariate Relations

Lab on Lecture 8 contains a Do It yourself section at the end which will be taken as the calculation quiz, so there will be no separate calculation. Those who did lab at PIDE already emailed their solutions to Irfan. Those outside PIDE can solve and send their labs to Uzma.

Next Lecture 9 on bivariate relationships will be delivered on Monday between 9 to 10:30 as usual. Comprehension Quiz on Tuesday, and Lab on Wednesday.

A missing comprehension quiz on histograms will be posted by Uzma to be solved during the weekend. The midterm itself was the replacement for the calculation quiz on histograms. 

Lab 8: Density Estimates

This morning, we will do Lab 8 at PIDE from 9 to 10:30AM. Other students can do lab on their own which has been posted on the webpage for Lecture 8. The lab, and associated data set RAINFALL02.xlsx is attached to the bottom of the page. The Computational Quiz for this lab should be available by Friday morning on Quizstar. 

Lec 8: Comprehension Quiz

Lec 8 Comprehension Quiz is now available. You need to open Excel file lec8comp while solving the quiz. which is available at:
https://sites.google.com/site/introstats4muslims/textbook/density

Schedule for April 7th to 14th

We had a disturbed schedule in the past few weeks because of the necessity of going back over material that students had not learned. Hopefully, everyone is caught up by now, and has submitted the midterm. For any special cases having difficulty, I can arrange tutoring sessions -- if they come to me (or to my TA's) for help -- but NOT if they copy and pretend to understand what they dont.

From this week, we should resume regular schedule. Monday, all should watch lecture 8 on density estimation. This is an improvement over the histogram. The class from 9:00 to 10:30 will have my TA's Irfan and Waqar present, and they will explain any issues that are not clear to the students. Then students should READ the textbook chapter: Lec08 Density.docx -- this is attached at the bottom of the webpage for this lecture:
https://sites.google.com/site/introstats4muslims/textbook/density
You may want to watch the lecture again after reading the text -- this time you should be able to follow and understand it much better.

Tomorrow, you should be able to take the Comprehension Quiz on this lecture.  Now we are going to try to take you off bottle feed, so you will only have one day - complete this quiz by midnite on tuesday

On Wednesday, you will have the computer lab, in which you will learn how to make density plots for data in EXCEL, with varying windowsizes.

On Thursday, you should practice these computer techniques on your own, and redo the lab exercises to make sure that you understand how to do it on your own without any help from anyboy.

On Friday you should take the Computational Quiz on Lecture 8. THEN you can rest Sat Sun and prepare for the same schedule next week which will cover Lecture 9.

Clarifications about MIDTERM

1. Question 3 refers to ALL countries -- you should look at the mean and median for all countries -- that will tell you something about what has been happening globally.
2. For question 5, pick ONE small binsize for all the data -- A binsize is TOO small if every bin contains only one or zero points. At the very least, many bins should contain TWO points for very small binsize. A binsize to TOO large if all the data is in one bin. At the very least there should be three or more nonempty bins. 
3. One important aspect of data analysis is to find out any peculariaties in the data. Look at the countries with maximum value and minimum values, and try to explain why some country is high and why some are low. Also look for any unusual events, like countries which had rapid change (relative to other countries. You will get points for pointing out UNUSUAL aspects of your data. EVEN more points if you can explain why this unusual aspect happened because of real world events.
4. Whereas we have been quite lax about deadlines in the past, the deadline on the MIDTERM will be strict. You must submit via email to uzma (uzma.economist@gmail.com) by MIDNIGHT on SUNDAY. Late exams will not be accepted. I have a record of who downloaded their data sets when, and I note that people are still downloading! Excuses will not be accepted. Even 24 hours is enough for finishing this exam -- my estimate is that it should take no more than 3 to 4 hours of work.