09/21/14

No Data Are Better Than Bad Data


Avoid bias
The full name of an article I read today is, “The Fallacy of Online Surveys: No Data Are Better Than Bad Data.” It’s from 2010 and very good. You can find it on the Responsive Management website. It makes some key points about the invalidity of online surveys:

  • For a study to be unbiased, every member of the population under study must have an equal chance of participating.
  • When online surveys are accessible to anyone who visits a website, the researcher has no control over sample selection. These self-selected opinion polls result in a sample of people who decide to take the survey — not a sample of scientifically selected respondents who represent the larger population.
  • Non-response bias in online surveys is complicated by the most egregious form of self-selection. People who respond to a request to complete an online survey are likely to be more interested in or enthusiastic about the topic and therefore more willing to complete the survey, which biases the results.
  • Unless specific technical steps are taken with the survey to prevent it, people who have a vested interest in survey results can complete an online survey multiple times and urge others to complete the survey in order to influence the results.
  • Because of the inability to control who has access to online surveys, there is no way to verify who responds to them — who they are, their demographic background, their location, and so on.

I’ve said this all before. The article concludes:

As a result of these problems, obtaining representative, unbiased, scientifically valid results from online surveys is not possible at this time, except in the case of the closed population surveys, such as with employee surveys, described earlier. This is because, from the outset, there is no such thing as a complete and valid sample — some people are systematically excluded, which is the very definition of bias. In addition, there is no control over who completes the survey or how many times they complete the survey. These biases increase in a stepwise manner, starting out with the basic issue of excluding those without Internet access, then non-response bias, then stakeholder bias, then unverified respondents. As each of these becomes an issue, the data become farther and farther removed from being representative of the population as a whole.

There’s also a good slide show on internet surveys here that goes over the basics presented in the article above. A 2008 paper addressed just issue with online surveys: self-selection. The author, Jelke Bethlehem, wrote:

…web surveys are a fast, cheap and attractive means of collecting large amounts of data. Not surprisingly, many survey organisations have implemented such surveys. However, the question is whether a web survey is also attractive from a quality point of view, because there are methodological problems. These problems are caused by using the Internet as a selection instrument for respondents.
This paper shows that the quality of web surveys may be seriously affected by these problems, making it difficult, if not impossible to make proper inference with respect to the target population of the survey. The two main causes of problems are under-coverage and self-selection.

The author concludes:

It was shown that self-selection can cause estimates of population characteristics to be biased. This seems to be similar to the effect of nonresponse in traditional probability sampling based surveys. However, it was shown that the bias in selfselection surveys can be substantially larger. Depending on the response rate in a web survey, the bias can in a worst case situation even be more than 13 times as large.

In other words: most online surveys are bunk. You might also recall I wrote about online surveys in past posts. I won’t repeat what I said then, but here are the links to those posts:

08/27/14

Social media and social dialogue


Angry at social media
A recent poll done by Pew Research reiterated what I’ve been saying for the past two years: social media (SM) doesn’t necessary facilitate social debate and in fact may be stifling it. Discussion on many SM platforms tends to reinforce existing beliefs because in general only those who feel their beliefs are shared by their circle of “friends” or followers will express them. It’s called the “spiral of silence.”

The Pew report noted:

…social media did not provide new forums for those who might otherwise remain silent to express their opinions and debate issues. Further, if people thought their friends and followers in social media disagreed with them, they were less likely to say they would state their views… Previous research has shown that when people decide whether to speak out about an issue, they rely on reference groups—friendships and community ties—to weigh their opinion relative to their peers… Those who do not feel that their Facebook friends or Twitter followers agree with their opinion are more likely to self-censor their views…

When social media emerged as a concept or platform that could be labelled* it was hailed as the new tool for social engagement, the panacea for flagging social interaction in many spheres like politics, education and government. And for a while, it was.

But that proved not to be the case any more than previously existing platforms (forums and list servers). In fact, for many who embraced it, social media proved more of a liability (think Anthony Weiner).

Blogger Raed El-Younsi blames the technology as at least partially responsible for the way we interact online. He wrote:

The internet gives us an unprecedented opportunity to understand one another. And yet anyone familiar with internet “discussion” boards knows that NOISE, group think and personal attacks can drown out most attempts at constructive dialogue. (For an extreme example, try discussing politics or religion in the YouTube comments.)
Similarly, the recent U.S. Government shutdown is a visible symptom of a much deeper trend: the polarization of our global society, online and offline…
Going into online discussion boards often means going into “hostile” territory and, as such, it can be a risky proposition. People often resort to attacks out of boredom, to be seen, or to “rally the troops” and win the numbers game. Strategically, our options are usually fight or flight – aggression or avoidance.

I have written in the past that it’s equally because we see the Internet as ours and respond to things online as if they were a threat to our personal property. It’s our computer, our modem, our house, our phone or cable bill, our wireless router… of course it’s our internet, too. And we respond to anyone who dissents or offers different ideas as we would a home invader or trespasser: with aggression. (Read the signs of narcissism here: listening only to dismiss; feeling the rules don’t apply to you; quick to anger; refusal to take responsibility; inability to take criticism.)

The notion of digital democracy at first suggested a great step forward. After all, what’s to dislike about free speech, freedom of expression, free exchange of ideas and open debate without borders? That quickly proved naive. The new social media proved an easier platform for the expressions of ideology than an exchange of ideas – just as the old forms had been. And in these situations, people who offered alternate or conflicting positions often found themselves denounced, attacked, insulted and vilified; their ideas or comments drowned out in a sea of vituperation. Instead of civil debate or an intelligent exchange of ideas, often these threads degenerated into a race to see who could type the nastiest rejoinder soonest.

Social networking sites (SNS) opened a whole new venue for harassment and spawned a neologism: cyberbullying.**

One recent poll suggests 25% of Americans have been harassed, bullied or threatened online and 62% of those had been harassed on Facebook. Some writers have suggested countermeasures, but these seem not to have gained much traction yet:

While keeping in mind that this is a self-reporting survey, the findings nevertheless illustrate the seriousness of online harassment and attacks, and the fact that people are increasingly becoming disenchanted with the negative behavior they experience.
We know online harassment and attacks are a huge social problem. We know they are a huge social GLOBAL problem. And it’s up to all of us to help turn things around.
While the steps needed to make this happen aren’t simply or easy, and also won’t solve the problem overnight, they will be concrete actions towards creating a positive cultural shift in online communication.

Free speech in social media does not come with any sense of responsibility, just narcissistic entitlement. People feel they have the right to comment on anything, in any manner, for any reason, regardless of their involvement in the issue, understanding of the idea, or respect for the feelings and rights of the others. Look what happens when some “hot-button” issues are broached – look at the angry back-and-forth over gun control or abortion.

Strangers can enter the fray, too, and anonymous posters can sling mud and spew invective at the original poster. It is difficult enough to argue with people you know or work with but generally much more polite and engaging; arguing with violent strangers or angry cowards hiding their identities through pseudonyms quickly makes people reluctant to engage.

Compounding it is the sheer number of people who can participate almost simultaneously: the confusion of multiple comments can turn what began as a discussion into a cacophony. A mob mentality that takes over and users on one side gang up to batter the outsider or dissenter into submission to the group mind – it’s called “seal clubbing.”

When ideology enters the fray – particularly political or religious – there is often no real civil debate on social media, but there is clearly intolerance as opposing sides batter away at each other.

And it doesn’t seem to be getting better: the Pew report found people are more willing to self-censor themselves on social media than among friends and co-workers. Based on earlier studies done by the organization, this suggests to me that the initial enthusiasm with which many people embraced social media has been curbed by the actions/words of the users themselves.
Continue reading

06/4/14

Pondering Responsive web design


Mashable graphicI’ve been building websites since the early 1990s, and have had my own websites continually since 1995. For a few years, I did website design and analysis for commercial clients – mostly small local businesses. I even taught web design at a local adult learning centre for a couple of years. Way back when the Net was relatively new, I even did some pages for local events. Although I do less coding today, mostly for my own use, I still have an interest in the developments in web technology and layout.

I taught myself the basics of HTML back when it was version 1.0, 20 years ago – not all that difficult if you were schooled in using the old word processors like Perfect Writer and Wordstar. The first word processors used similar markup styles. Some even required users to compile the text in transient files, in order to see the formatting results, because they couldn’t be shown onscreen at the same time as the markup. That’s because these programs were small, tight and efficient enough to fit in the limited physical computer memory – 16 to 64KB in the early days of computing – but not very feature rich. Ah, the good old days of the Z80 and 6502 processors.

HTML was fairly easy (for me), but clumsy. It was a flat, 2D system and building some elements – tables in particular – was awkward and time-consuming. HTML tried – with limited success – to mix design with structure in one all-encompassing language. It was predicated on the printed page – basically replicating it onscreen. The initial versions of HTML were a desktop-publishing-like environment for the screen.

But the old ways are not always suited for the new devices. Page designs and layouts done even five years ago may be outdated and ill-suited for mobile devices (as I have found from my own work). New design paradigms are needed to stay current with the ebb and flow of technologies.

Continue reading

05/22/14

World of Tanks


Battlefield view
Tanks are a long distance weapon, you know. They are best used in concert with one another to provide cover and overwatch fire, and are best placed in a covered or hull-down position where their profile is reduced to the minimum. Tanks should never travel alone; they should always advance with supporting vehicles on their flanks.

That’s pretty much what I said to my teammates that Saturday morning. However, I may have typed it a little more tersely. Something like, “%#$&@ idiots. Y R U in the open w/o support?

I watched as the majority of them rushed across the field to be picked off in the open by well-placed enemy tanks, and turned into smoldering wrecks that dotted the battlefield. Don’t these people know anything about basic tank doctrine, I wondered? Well, probably not. This is the internet, after all.

Firing
Still, I want to shout out. Tanks are not close-range weapons. Or rather, they weren’t intended to be. This isn’t paintball. You can’t exactly sneak around in 25 or 30 tons of metal. But you can be clever and use the terrain to your advantage: peek carefully around corners, over rises, and stay hidden in bushes while you wait.

But there they were – half the team racing towards the enemy flag like heavy-metal Rambos, ignoring terrain, elevation, cover, overwatch or even one another. And paying the price. Boom! Another teammate in flames. You might have heard me swearing as you walked by the house that morning.

That left me with three others out of an initial 15 to guard the base; trying to cover all possible paths of approach, stay hidden and stay alive. And pick off the enemy, now bold enough to move forward. An enemy which still had nine intact vehicles, including a very active artillery and two tank destroyers, each with two kills each already. A team that seemed to understand how to play much better than our side.

We lost that one.
Defeat!

Good thing it’s just a game and the losers merely have to wait it out until the match ends, then come to life and play again. When there’s no other penalty for dying except to wait, you won’t learn anything.

Continue reading

02/15/14

BL2: Resistance is futile


Borderlands 2I tried to resist. I really did. I avoided it for more than a year, skillfully averting my eyes from the store shelves where it sat, ignoring the emails with invitations, sales offers that dangled newly-released DLC packages before me. I looked the other way when ads popped on on websites.

I have more serious things to do, I’d tell myself. Getting too old for games, I’d mutter under my breath. I have better things to do with my time. Like reading. Studying. Developing website material. Learning music. Besides, I’m running out of hard disc space.

But then I saw the intro, below. And I succumbed. It just seemed way too much fun. And I love the theme song (it was also the theme for the excellent British action TV series, Flash Point). Watch it. Stick with it because it gets fun around the 1:50 mark.

I had seen the “Wimoweh” trailer, below, before I saw the one above, and it almost convinced me. It’s hard to resist such a call. And if you haven’t seen it either, give it a watch.

Late in 2013, Steam had Borderlands 2 on sale – the whole Game of The year package at one low price – and I gave in. GOTY was just too damned tempting.

Now I have a handful of characters scattered throughout Pandora in various stages of game completion, edging up their stats slowly as I learn and test each one’s style, weapons and special features. Finishing quests. Opening chests of loot. Gathering eridium. To be honest, I’ve played only three of the possible six characters so far, but I plan to try them all.

And I’m not alone. On many missions, I am accompanied by a friend in Nova Scotia who joins me for co-op play sessions. Two old farts playing edgy computer games. What a lark.

Continue reading

01/26/14

The Mac celebrates 30 years


MacintoshA recent article on Gizmodo shows off some previously unseen (or perhaps just forgotten) footage of a young Steve Jobs unveiling the Macintosh computer, back on January 30, 1984.

Thirty years ago, this week.

Seems like forever ago. But I remember it, and reasonably well. I remember where I was living then, what I was working on, and who I was with (I’m still with her…)

The video clip also includes the famous Orwellian “1984” TV ad Apple used to launch the Mac. That’s worth watching for itself. It was a really cheeky ad, and generated a lot of chatter about marketing at the time. The clip includes other Mac ads you should watch.

I had a Mac around then, bought, as I recall, in late 84 or early 85. I had had a Lisa – the Mac’s unsuccessful predecessor – on loan for a few months in 83 or early 84. I wasn’t impressed with the Lisa, but the Mac really captivated me.

I also had an IBM PC, from 82 or 83, and never quite understood the anti-IBM sentiments Jobs and Apple promoted among users. But then PC users fought back just as adamantly over the superiority of their platform.

As a computer geek from way back, I just loved having any – every – computer. When I started computing, I lived in a two-bedroom apartment; the second (the Iarger of the two, of necessity) bedroom became a workroom filled with computers, books, manuals, printers, modems, tools, chips, soldering irons, cables, and printers. As a technical and documentation writer, I always had extra hardware and software on loan from manufacturers and distributors. I once described my room as looking like a “NASA launch site.”

When we eventually bought our own house, I had a room for my books and computers, too, although they tended to escape and overrun the rest of the house. Same thing has happened here, although the amount of hardware is much reduced from the glory days (more ukuleles today than computers).

But ever since my first computer, I have not been a day without at least one computer in the house, usually several.

By the time the Mac was released, I had been computing for more than six years. I bought my first computer in the fall of 1977, a TRS-80, and soon had several machines (an Apple in 79, an Atari 400 in 1980 and then an 800 in 81). I belonged to user groups, subscribed to at least a dozen computer magazines, and wrote for several, including one of the earliest columns on computer gaming (in Moves magazine). I attended many computer fests and exhibitions in Canada and the USA – in fact, I helped organize a microcomputer fair in Toronto, at the International Centre, in the mid-80s.

As you read this, in 2014, I’ve been at it for almost 37 years.

So I take some umbrage when I read this condescending snippet on Gizmodo:

30 years ago the landscape of personal computing was vastly different. That is to say, it hardly existed.

Hogwash. It was alive and well – thriving in its entrepreneurial glory. Only poorly-informed journalists who have not done their research would make such a claim. Or perhaps they are too young to know of the rich history of personal computing prior to their own acquisition of a device.

By 1984, we had seen the TRS-80, Commodore Pet, Apple II, Kaypro, IBM PC, Atari 400, 800 and 1200, Sinclair, TI-99, the Acorn, Coleco Adam and many others. Apple’s own IIc would be released later in 1984.

We would soon see both the Commodore Amiga and Atari ST 16-bit computers launched. Of which I had them all, and a few others passed through my hands in that time, too.

In the 80s, CompuServe dominated the field of online services with millions of customers as it spread. I was a sysop on CompuServe for many of those years. I even operated my own BBS for a while.

CompuServe was challenged – aggressively, but not very successfully – by several competitors in that decade including The Source and Delphi (I was later a sysop on Delphi, too, before moving to Collingwood).

Continue reading